MicrostockGroup
Microstock Photography Forum - General => General Stock Discussion => Topic started by: Artist on September 15, 2022, 22:36
-
I got an access to one of the tool and the results I am seeing are mind blowing.
An artist who takes days to get the job done... is now happens in few clicks.
I am not in support of AI but the awesome results are making me bit lean towards it.
I am really concerned as this is very initial stage and is ready to kill jobs for photographer, concept artist, texture artist, digital painters, matte painters etc.
Huge dark clouds ahead.
-
Progress is not killing jobs.
It just moves them elsewhere, where scarce resources are utilized more efficiently.
-
At best it will add another creative asset class. Especially for artsy book cover content.
But it has legal and copyright issues.
Obviously all agencies will have their own ai tool at some point.
-
Obviously all agencies will have their own ai tool at some point.
This will be for sure.
Soon there will be first tests, giving buyer otpion to create their own unique images instead of doing database search.
For tomatoes on white background will be the end, but for more complex images there will be always space for human work; also editorial will still have life.
There are a couple of big issues in AI:
It's not so easy for buyer to give an exact description; probably most of the buyer only search for a subject without exact idea of the way in which they want to see it. AI works well only if you give detailed descriptions.
About legal issue, I don't think an agency can use its own database to feed AI learning. Maybe some will offer a fee to authors. Once the feed issue will be solved, also legal issues about ownership of new images will be solved as well.
So there are some questionable points, but I'm sure that they will be managed and soon we'll see an option in search page, something like "describe and create your own original unique image"
-
"It's not so easy for buyer to give an exact description; probably most of the buyer only search for a subject without exact idea of the way in which they want to see it. "
Exactly. A lot of times people will look for something without knowing exactly what they want. They're looking for a Christmas background and after several pages, ah, that's what I want. But if you were to ask them to describe what they want before seeing anything... not so easy. Creatives don't just create the image, they come up with the idea... and for non-creative types, that is just as hard if not harder than creating the actual image.
Mind you, I'd have thought those who produce white background imagery would still make money. They'd sell them to the AI software companies who store them as reference and would either buy them exclusively or, as a per usage in an each AI created image.
-
Nobody's killing anything. Results are out there for everyone to see and those that are cherry picked are mildly impressive. Technology displacement will make some jobs redundant eventually and will create new ones, like it did many times before. So please stop with this doom and gloom clickbait nonsense
-
Nobody's killing anything. Results are out there for everyone to see and those that are cherry picked are mildly impressive. Technology displacement will make some jobs redundant eventually and will create new ones, like it did many times before. So please stop with this doom and gloom clickbait nonsense
I completely agree. I can add that I'm working with AI for almost a month now with great fun:it is another tool, multifaceted and there is a lot to learn to master and to build your own style.
I'm also lucky to have developed software for so many years and this helps to understand how to move to get results. AI is continuously learning and in one year I expect the developments will be huge. Better to be ready ;)
-
https://www.microstockgroup.com/general-big-6/dall-e-2-will-make-us-all-redundant/msg577732/#msg577732 (https://www.microstockgroup.com/general-big-6/dall-e-2-will-make-us-all-redundant/msg577732/#msg577732)
-
(http://aiworldcat.png)
-
(https://www.microstockgroup.com/general-stock-discussion/artificial-intelligence-killing-the-whole-industry/?action=dlattach;attach=18941;image)
It already has, look at the way people drool on their keyboards over FB, Redit and those kind of sites. They don't seem to realize that We Are The Product and provide free information that they use to sell to marketers. (That I'm bitter that all the Gen ??? have taken over and Baby Boomers are considered old and irrelevant? ;D ) We’re unable to distinguish between what feels good and what’s true. But we have revisionist history, dumbing down of reality and cancel culture.
Hawking said, "the development of full artificial intelligence could spell the end of the human race." In an interview with the BBC Hawking said A.I. poses no threat to the human race today but could in the future as machines -- specifically robots -- become smarter, bigger and stronger than their human developers.
Yeah why worry so much about climate change, the robots are going to take over everything anyway?
(https://i.postimg.cc/8zC5bZhk/truth_is_out_there_fork.jpg)
-
rather than AI threat to a minor field of stock photography (where 'good enough' is a goal AI will meet) - here's a larger view
https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/ (https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/)
-
And so it begins:
https://arstechnica.com/information-technology/2022/09/artists-begin-selling-ai-generated-artwork-on-stock-photography-websites/
-
And so it begins:
https://arstechnica.com/information-technology/2022/09/artists-begin-selling-ai-generated-artwork-on-stock-photography-websites/
slow claps for all the defenders
-
Maybe there's an opportunity to use our own portfolios, to generate thousands more AI images and videos? We also have a head start on anyone just getting into selling images. AI won't be much use for some things, like editorial photos. I intend to use it, and work in areas where it won't be much use.
-
I've uploaded this particular AI image created by DALLE2 throughout and testing the results.
Quality is pretty bad (particularly after up-sizing) so I suspect that it will be rejected by all, but interesting to see either way.
-
Love the missing fingertips, I wonder what the AI backstory for that would be?
-
I've uploaded this particular AI image created by DALLE2 throughout and testing the results.
Quality is pretty bad (particularly after up-sizing) so I suspect that it will be rejected by all, but interesting to see either way.
I have seen these AI tool are not so good in creating human figures. Look at the model hands, those doesn't feels natural to me.
But since it is still learning, in couple of months or years it will generate very perfect image. This is not the end, its beginning of AI.
-
Love the missing fingertips, I wonder what the AI backstory for that would be?
"proud, overweight woman, posing, full length wearing tight clothes, feminist”
-
Should I upload my seagull sheep? Far from killing the industry, I think this opens up subjects I had never thought of before :)
(https://i.ibb.co/BPH8XpB/download-46.png)
-
There's a quickly diminishing amount of creative/artist jobs already and this will just accelerate the decline. Once this is perfected over the next 5-10 years stock agencies will adopt AI and have little need for contributors. Free money for them and less of having to deal with us. AI wont kill the industry but it will be a big shift much like macro to micro. People will need to adjust to the shift and find a profitable niche. Editorial cant be replaced by AI.
I wonder how many buyers will want images that are authentic and real versus artificial.
-
What tools are you using? Has anyone tried putting the (uncommon) name of a microstock photographer and the full title of some of their images? Wondering what happens when you limit the pool it can draw from.
-
There's a quickly diminishing amount of creative/artist jobs already and this will just accelerate the decline. Once this is perfected over the next 5-10 years stock agencies will adopt AI and have little need for contributors. Free money for them and less of having to deal with us. AI wont kill the industry but it will be a big shift much like macro to micro. People will need to adjust to the shift and find a profitable niche. Editorial cant be replaced by AI.
I wonder how many buyers will want images that are authentic and real versus artificial.
Eventually there will be an agency with no artists where the buyer types in what they want and gets a selection of AI images to choose from.
-
Eventually there will be an agency with no artists where the buyer types in what they want and gets a selection of AI images to choose from.
But that's already here and pretty much what people are talking about here.
-
Should I upload my seagull sheep? Far from killing the industry, I think this opens up subjects I had never thought of before :)
Far currently, but will soon reach.
Accept the reality, AI is a continuous self learning program, everyday it is getting smarter.
The foundation is strong, and soon it will cover all the sectors.
-
Eventually there will be an agency with no artists where the buyer types in what they want and gets a selection of AI images to choose from.
But that's already here and pretty much what people are talking about here.
What agency has make a request and get an AI image assortment? I haven't seen that yet, but I think that will be part of the future. No artists at all at that one.
Where is it already here?
-
There's a quickly diminishing amount of creative/artist jobs already and this will just accelerate the decline. Once this is perfected over the next 5-10 years stock agencies will adopt AI and have little need for contributors. Free money for them and less of having to deal with us. AI wont kill the industry but it will be a big shift much like macro to micro. People will need to adjust to the shift and find a profitable niche. Editorial cant be replaced by AI.
.....
it's not free if agencies create their own AI images - they have to pay the designers - much cheaper to rely on contributors to create, weed out, refine, keyword, etc
-
What tools are you using? Has anyone tried putting the (uncommon) name of a microstock photographer and the full title of some of their images? Wondering what happens when you limit the pool it can draw from.
it really doesnt limit it, since it starts from nothing & tweaks using its entire knowledge. once trained, it doesnt need to actually look at images, so there's no copying from any particular image
here's a quick example
(http://cascoly.com/1-tfr/dalll-e-yeni.jpg)
none of my images look anything like this - my images are taken from the other side of the mosque! in fact these images are more precise than mine, where my images don't actually show the golden horn and these are taken FROM the golden horn
altho Yeni translates as 'new mosque' The mosque was completed in 1663.
https://cascoly-images.com/exploring-the-other-mosques-of-istanbul/ (https://cascoly-images.com/exploring-the-other-mosques-of-istanbul/)
-
Eventually there will be an agency with no artists where the buyer types in what they want and gets a selection of AI images to choose from.
But that's already here and pretty much what people are talking about here.
no, since buyers want an image they can use directly & these AI need additional selection, processing, etc
-
If AI can make any picture you want why would anyone need agencies? You just buy the software and add any picture you want to your article. So it's not just the contributors losing here. It's also the agencies. They will be redundant, like us.
-
There's a quickly diminishing amount of creative/artist jobs already and this will just accelerate the decline. Once this is perfected over the next 5-10 years stock agencies will adopt AI and have little need for contributors. Free money for them and less of having to deal with us. AI wont kill the industry but it will be a big shift much like macro to micro. People will need to adjust to the shift and find a profitable niche. Editorial cant be replaced by AI.
.....
it's not free if agencies create their own AI images - they have to pay the designers - much cheaper to rely on contributors to create, weed out, refine, keyword, etc
Well, cost depends on if the agency licenses an existing AI or builds its own. Eventually, AI will fully automate everything eliminating the need for contributors except for editorial. I would expect the AI to be cheaper but who knows. Hard to say the cost of AI development or licensing vs contributor payouts.
Agencies will likely have curated stock AI images picked by staff, plus stock images generated by AI, and then virtual AI images created when a buyer types in search terms where AI just creates images on the spot. AI will learn over time buyer patterns and it will fine-tune creating new images that are more likely to sell. Eventually it will learn enough that the need for designers and contributors will diminish. At some point AI will keyword and curate images accurately.
I hope we're at least ten years or more away from photo AI being fully mature otherwise this may really screw up my retirement plans.
-
If AI can make any picture you want why would anyone need agencies? You just buy the software and add any picture you want to your article. So it's not just the contributors losing here. It's also the agencies. They will be redundant, like us.
They will have curated work and customer service to help buyers save time and bypass the unusable garbage. However, at some point, the AI will have learned so much it may work so well that it does actually eliminate the need for an agency. It will just generate images based on what the buyer types in. As it learns patterns of what people buy, the images will get better and it will create more sellable work reducing the need for curation.
-
This is a link to an text to image generator developed by Baidu-currently free to use
https://huggingface.co/spaces/PaddlePaddle/ERNIE-ViLG
-
If AI can make any picture you want why would anyone need agencies? You just buy the software and add any picture you want to your article. So it's not just the contributors losing here. It's also the agencies. They will be redundant, like us.
because it's just not that simple - RYFM - this has already been discussed
-
Eventually there will be an agency with no artists where the buyer types in what they want and gets a selection of AI images to choose from.
But that's already here and pretty much what people are talking about here.
What agency has make a request and get an AI image assortment? I haven't seen that yet, but I think that will be part of the future. No artists at all at that one.
Where is it already here?
I am not sure what you mean by "make a request", but AI generation sites like DALL E are pretty much what was described: You go to a site, you "types in what they want and gets a selection of AI images to choose from".
-
If AI can make any picture you want why would anyone need agencies? You just buy the software and add any picture you want to your article. So it's not just the contributors losing here. It's also the agencies. They will be redundant, like us.
What if you can't buy the software and the only way to create images is license them from the AI site? The companies are not developing this AI for pleasure, they want to make as much money as possible. They could become an agency no artists for an annual fee around the cost of a SS subscription. This would hurt the agencies, you're right.
-
The guys saying "it's just another tool" and telling us how exciting it is now that they've tried it.... it's like they've been hit by a car and are still in shock, not comprehending what's happened.
This stuff is going to flood microstocks and PODs. But wait - those companies can now generate their own "content". On demand. Oh wait again... the customers won't need the agencies because EVERYONE can generate what they think they want, and just pay they "AI" company. Or pay Meta after they buy all the technology.
Any existing work that's visible on the web can be copied, in subtle and unproveable ways. Oh did I say "copied"? I meant "used to train the AI".
This will take years to play out and it's going to be hilarious. Eventually, some photographers and artists will figure out how to effectively sue these fake-AI companies and pull back the curtains to expose how the software really works. You won't see anything you'd call "intelligence".
-
Eventually there will be an agency with no artists where the buyer types in what they want and gets a selection of AI images to choose from.
But that's already here and pretty much what people are talking about here.
What agency has make a request and get an AI image assortment? I haven't seen that yet, but I think that will be part of the future. No artists at all at that one.
Where is it already here?
I am not sure what you mean by "make a request", but AI generation sites like DALL E are pretty much what was described: You go to a site, you "types in what they want and gets a selection of AI images to choose from".
What I meant was, someone will create an agency, no artists, that will have "enter what you want your image to be", then it will create a selection. The buyer will then pay to download the image(s) they want. Dall-E and the rest are just in beta right now, and yes we can use them free, but the results are unreliable and often not professional. When the AI gets to "good enough" ;) Someone will charge for it. There is no free lunch.
Selling the software, would be a bad idea, as people have pointed out, then anyone can spend days or months and just create and create new images. You don't buy your operating system on your computer, you pay for a license. Adobe CC is an example, you pay for a subscription. If these people create a useful tool, they should have an expensive license to use it.
I think a better way would be, they start a service, that charges for each image to be created, to specifications, and no one else gets their software or the code to make it operate.
On the other hand, lets say they license the software to people, and hundreds of thousands of people can make all the fake images they want of anything? The image market for that kind of work, would soon be so flooded that it wouldn't make sense to license the software. There would be 5 billion images of anything, anyone can imagine.
Anyway, no there isn't a service or agency right now that allows anyone to produce commercial AI created images that are good enough. Some day there will be. And personally the 5-10 years is a laugh. I remember the predictions of how many years before digital photos would have enough quality to surpass film. How digital could resolve the lens quality, and why we could not have video cameras that recorded to memory cards, instead of a hard drive or DVD, because of the speed and size of memory.
Every one of those predictions of many years, turned out to be, a year maybe two.
I don't want this, but I see AI images being refined, available and high enough quality in 2 years or less. You want a penguin on a surfboard, with pineapples in it's hands... it's going to be made.
Death to certain segments of stock photography, AI creations will absolutely do that. Real people, news, products, and creative art, (probably other areas) will not be replaced by AI so soon.
-
If AI can make any picture you want why would anyone need agencies? You just buy the software and add any picture you want to your article. So it's not just the contributors losing here. It's also the agencies. They will be redundant, like us.
What if you can't buy the software and the only way to create images is license them from the AI site? The companies are not developing this AI for pleasure, they want to make as much money as possible. They could become an agency no artists for an annual fee around the cost of a SS subscription. This would hurt the agencies, you're right.
but there are no images to buy on the AI site - they are more like PS than an agency
-
Anyway, no there isn't a service or agency right now that allows anyone to produce commercial AI created images that are good enough.
Ah Uncle Pete they are, they are already of enough good quality.
And strange enough, nobody commented here this
https://www.theverge.com/2022/9/1/23332684/ai-generated-artwork-wins-state-fair-competition-colorado (https://www.theverge.com/2022/9/1/23332684/ai-generated-artwork-wins-state-fair-competition-colorado)
-
If AI can make any picture you want why would anyone need agencies? You just buy the software and add any picture you want to your article. So it's not just the contributors losing here. It's also the agencies. They will be redundant, like us.
What if you can't buy the software and the only way to create images is license them from the AI site? The companies are not developing this AI for pleasure, they want to make as much money as possible. They could become an agency no artists for an annual fee around the cost of a SS subscription. This would hurt the agencies, you're right.
but there are no images to buy on the AI site - they are more like PS than an agency
Try to learn to read and comprehend sometimes what other people are saying before you react to something. It is not that it is now but it could be in the near future. That is what she meant.
-
I think a better way would be, they start a service, that charges for each image to be created, to specifications, and no one else gets their software or the code to make it operate.
that's what DALL-E does! with a few free images a month & about $.10 per image after that
On the other hand, lets say they license the software to people, and hundreds of thousands of people can make all the fake images they want of anything? The image market for that kind of work, would soon be so flooded that it wouldn't make sense to license the software. There would be 5 billion images of anything, anyone can imagine.
...
that's a big reason why this is unlikely for DALL-E since they have a commitment to prevent this scenario. Thus, they have to keep control of the software.
- They’re rejecting image uploads that include recognizable faces, as well as generation prompts that seek to recreate the likeness of public figures (celebrities and politicians, for example), or realistic photos of real individuals.
- They’re improving their filters to block users from creating harmful content –this includes violent, adult, or political content– and also removing this kind of data from the software’s training altogether.
- They’re using both automated and human monitors to supervise the platform and avoid misuse
-
that's a big reason why this is unlikely for DALL-E since they have a commitment to prevent this scenario. Thus, they have to keep control of the software.
- They’re rejecting image uploads that include recognizable faces, as well as generation prompts that seek to recreate the likeness of public figures (celebrities and politicians, for example), or realistic photos of real individuals.
- They’re improving their filters to block users from creating harmful content –this includes violent, adult, or political content– and also removing this kind of data from the software’s training altogether.
- They’re using both automated and human monitors to supervise the platform and avoid misuse
Got this email today:
You can now upload and edit photos with faces with DALL·E.
Many of you have told us that you miss using DALL·E to dream up outfits and hairstyles on yourselves and edit the backgrounds of family photos. A reconstructive surgeon told us that he’d been using DALL·E to help his patients visualize results. And filmmakers have told us that they want to be able to edit images of scenes with people to help speed up their creative processes.
With improvements in our safety system, DALL·E is now ready to support these delightful and important use cases – while minimizing the potential of harm from deepfakes.
We made our filters more robust at rejecting attempts to generate sexual, political, and violent content – while also working to reduce false flags – and built new detection and response techniques to stop misuse.
Our content policy still prevents uploading images of anyone without their consent, or images that you do not have the rights to.
We hope this update helps you use DALL·E in even more creative and practical ways. We’re excited to see what you create!
- The OpenAI Team
______________________________________________
Nothing is permanent here, something not available today will be available tomorrow.
Small resolution, fast rendering, more accurate generation etc. will all come very soon.
This is not any tool, it's AI, it is self learning everyday and will become smarter and smarter.
-
Anyway, no there isn't a service or agency right now that allows anyone to produce commercial AI created images that are good enough.
Ah Uncle Pete they are, they are already of enough good quality.
And strange enough, nobody commented here this
https://www.theverge.com/2022/9/1/23332684/ai-generated-artwork-wins-state-fair-competition-colorado (https://www.theverge.com/2022/9/1/23332684/ai-generated-artwork-wins-state-fair-competition-colorado)
Is that a commercial service or production site?
-
Anyway, no there isn't a service or agency right now that allows anyone to produce commercial AI created images that are good enough.
Ah Uncle Pete they are, they are already of enough good quality.
And strange enough, nobody commented here this
https://www.theverge.com/2022/9/1/23332684/ai-generated-artwork-wins-state-fair-competition-colorado (https://www.theverge.com/2022/9/1/23332684/ai-generated-artwork-wins-state-fair-competition-colorado)
Is that a commercial service or production site?
production
-
Anyway, no there isn't a service or agency right now that allows anyone to produce commercial AI created images that are good enough.
Ah Uncle Pete they are, they are already of enough good quality.
And strange enough, nobody commented here this
https://www.theverge.com/2022/9/1/23332684/ai-generated-artwork-wins-state-fair-competition-colorado (https://www.theverge.com/2022/9/1/23332684/ai-generated-artwork-wins-state-fair-competition-colorado)
Is that a commercial service or production site?
production
State Fair competition, but yes, some of the work is "good enough". We don't know how much hand editing that artist put into the AI created image, after the fact.
https://pixexid.com/read/midjourney-ai-text-to-image-generator (https://pixexid.com/read/midjourney-ai-text-to-image-generator)
Some of these are pretty darn good. People and animals look a bit strange. Last one on the page, fairy castle sure looks like something from Disney? People are now starting prompt generators for the images. For the good examples, the people promoting this AI aren't usually showing the spectacular failures.
As many have posted, much of the results are questionable or distorted, missing fingers, face with strange features. My point is, there isn't a system yet that allows buyers to come in and effectively say, "I want a photo created with this, this and this..." and the AI can make what they want, in a useful quality, reliably.
When that happens, and I still say sooner than predicted, there will be some major changes to how stock photos are supplied.
If things are bad now and slow for many people, AI being perfected, is not going to make anything better.
-
I think it will never replace real photos. Especially editorial where reality and authenticity is needed.
-
Getty & iStock have just banned all images from AI software and will be be removing all existing ones submitted to them over concerns around copyright of the raw images used to create the finished images as well as the metadata.
I have a feeling they won't be the only ones, it could be a potential legal minefield.
-
Great move by Getty:
Effective immediately, Getty Images will cease to accept all submissions created using AI generative models (e.g., Stable Diffusion, Dall‑E 2, MidJourney, etc.) and prior submissions utilizing such models will be removed.
There are open questions with respect to the copyright of outputs from these models and there are unaddressed rights issues with respect to the underlying imagery and metadata used to train these models.
These changes do not prevent the submission of 3D renders and do not impact the use of digital editing tools (e.g., Photoshop, Illustrator, etc.) with respect to modifying and creating imagery.
Best wishes,
Getty Images | iStock
-
Yes, well done Getty!
-
Good job banning these AI images, but how do they know it was generated via AI? How will they be going back to purge previously accepted AI imagery?
-
Good job banning these AI images, but how do they know it was generated via AI? How will they be going back to purge previously accepted AI imagery?
They probably need another AI to detect AI.. haha ;D
-
iStock, Getty & Shutterstock will not accept content from AI generated models
https://app.engage.gettyimages.com/e/es?s=1591793372&e=11409538&elqTrackId=178baed6532740e59ffea78497faafe5&elq=fa80202c7d8e41b287b6737c139f8bd6&elqaid=51367&elqat=1&elqcst=272&elqcsid=25098 (https://app.engage.gettyimages.com/e/es?s=1591793372&e=11409538&elqTrackId=178baed6532740e59ffea78497faafe5&elq=fa80202c7d8e41b287b6737c139f8bd6&elqaid=51367&elqat=1&elqcst=272&elqcsid=25098)
https://www.vice.com/en/article/v7vzpj/shutterstock-is-removing-ai-generated-images (https://www.vice.com/en/article/v7vzpj/shutterstock-is-removing-ai-generated-images)
Probably all the articles about this prompted them to act:
https://arstechnica.com/information-technology/2022/09/artists-begin-selling-ai-generated-artwork-on-stock-photography-websites/ (https://arstechnica.com/information-technology/2022/09/artists-begin-selling-ai-generated-artwork-on-stock-photography-websites/)
https://petapixel.com/2022/09/16/thousands-of-ai-generated-images-are-for-sale-on-stock-photo-websites/ (https://petapixel.com/2022/09/16/thousands-of-ai-generated-images-are-for-sale-on-stock-photo-websites/)
-
i've been submitting test images from DALL-E, noting that they are computer generated - i'll post results when all are reviewed
only 10 images were submitted to AS & 6 were accepted and agencies are accepting different images
of course the real test will be whether any of these actually sell
-
Getty sent an email announcing they won't be accepting these works and removing any from their image library due to concerns around copyright...
AI Generated Content
Effective immediately, Getty Images will cease to accept all submissions created using AI generative models (e.g., Stable Diffusion, Dall‑E 2, MidJourney, etc.) and prior submissions utilizing such models will be removed.
There are open questions with respect to the copyright of outputs from these models and there are unaddressed rights issues with respect to the underlying imagery and metadata used to train these models.
These changes do not prevent the submission of 3D renders and do not impact the use of digital editing tools (e.g., Photoshop, Illustrator, etc.) with respect to modifying and creating imagery
-
here's a set created yesterday - i checked each of these thru tinyeye & it didnt find any similar images
(http://cascoly.com/1-tfr/220920-sadhu-2x2.jpg)
-
here's a set created yesterday - i checked each of these thru tinyeye & it didnt find any similar images
I have to say that at least they are of a much better quality then your own photos in your portfolio. So DALL-E might actually help you out here.
That is if agencies will not reject them or remove them eventually from your portfolio.
Good luck with that :)
-
Since the advent of the computer in graphic design/advertising/photography there have been several waves of technological advances that have killed off various highly skilled professions. Typesetters, filmstrippers, old school photo retouchers, etc. Old jobs disappear and new ones appear. It's tough when you're on the losing end but inevitable. What is more worrying to me, is the gradual devaluing of all creative work, from music, to photography, to design. As time goes on the big Internet players seem increasingly determined to give away our work for free while making millons for themselves.
-
I assume Getty and SS are only removing images which specifically state that AI has been used. 'Getty Images will rely on users to identify and report such images'
https://www.theverge.com/2022/9/21/23364696/getty-images-ai-ban-generated-artwork-illustration-copyright (https://www.theverge.com/2022/9/21/23364696/getty-images-ai-ban-generated-artwork-illustration-copyright)
-
Getty AI doesn't recognize AI = fail
-
The copyright violations are blatant and they can't be hidden behind "used to train the AI". Getty is slime, but they're smart, corporate slime. Their business is based on this legal stuff and their lawyers know what's going on here.
-
here's a set created yesterday - i checked each of these thru tinyeye & it didnt find any similar images
([url]http://cascoly.com/1-tfr/220920-sadhu-2x2.jpg[/url])
All of those images look terribly unrealistic. The faces seem thoroughly airbrushed of realistic wrinkles and textures. Look fake even to an untrained naked eye.
-
All of those images look terribly unrealistic. The faces seem thoroughly airbrushed of realistic wrinkles and textures. Look fake even to an untrained naked eye.
Correct, but remember, its been only one month and some programs are still in beta mode.
-
Correct, but remember, its been only one month and some programs are still in beta mode.
Judging by those pictures, they have a very long way to go.
-
Many are happy with the AI, but when they lose some source of income because of it they won't be so excited! On the one hand, the reduction of the world population is sought, many people will be without work and they will be left over being a burden for governments.
-
This sort of thing is the reason agencies are rejecting this kind of content, because someone is going to get sued for a lot of money somewhere:
https://arstechnica.com/information-technology/2022/09/artist-finds-private-medical-record-photos-in-popular-ai-training-data-set/
-
here's a set created yesterday - i checked each of these thru tinyeye & it didnt find any similar images
I have to say that at least they are of a much better quality then your own photos in your portfolio. So DALL-E might actually help you out here.
That is if agencies will not reject them or remove them eventually from your portfolio.
Good luck with that :)
if you're offering unsolicited critiques, it's common courtesy to provide a link to your portfolio
-
i've been submitting test images from DALL-E, noting that they are computer generated - i'll post results when all are reviewed
only 10 images were submitted to AS & 6 were accepted and agencies are accepting different images
of course the real test will be whether any of these actually sell
That is the real question in the end. Just like someplace accepting what some people find to be terrible images and similar and trash. If they don't sell, it really doesn't effect me. Good Luck.
-
Good job banning these AI images, but how do they know it was generated via AI? How will they be going back to purge previously accepted AI imagery?
It shouldn't be that hard. If it's a real model the person submitting the image will need a model release. You can't get a model release from an AI, so no model release, no acceptance.
-
We're all talking about "pure" AI generated images here, but since I'm "playing" on Midjourney (so much fun!), I can see a lot of potential for backgrounds. It is great to be able to offer my studio clients more than the standard studio backdrops. Midjourney makes absolutely wonderful "fairytale like" landscapes, and if I photograph a client with the right direction of lighting, I can offer her a portrait both with standard background + photoshopped into a Midjourney backdrop. This is completely OK with Midjourney (free commercial use).
1 step further would be submitting real, model released people photos with AI backgrounds to stock agencies. Since that is obviously not allowed by most agencies, I will not put any effort in creating these for stock, but what a pity! So much potential lost ...
-
Good job banning these AI images, but how do they know it was generated via AI? How will they be going back to purge previously accepted AI imagery?
It shouldn't be that hard. If it's a real model the person submitting the image will need a model release. You can't get a model release from an AI, so no model release, no acceptance.
Not quite. If its a photo and contains any person, it requires a model release. My understanding is you can only submit your own work, you have to be the copyright owner. Submitting AI images you neither created it or own the copyright and therefore should not be submitting the image to the agency. End of.
If you have created a rendered illustration, you are submitting your own work, you have the copyright and I'd imagine, if it's not the case already, you will need to provided a property release stating it is your own work (inc reference material).
-
Good job banning these AI images, but how do they know it was generated via AI? How will they be going back to purge previously accepted AI imagery?
It shouldn't be that hard. If it's a real model the person submitting the image will need a model release. You can't get a model release from an AI, so no model release, no acceptance.
Not quite. If its a photo and contains any person, it requires a model release. My understanding is you can only submit your own work, you have to be the copyright owner. Submitting AI images you neither created it or own the copyright and therefore should not be submitting the image to the agency. End of.
If you have created a rendered illustration, you are submitting your own work, you have the copyright and I'd imagine, if it's not the case already, you will need to provided a property release stating it is your own work (inc reference material).
Getty isn't banning AI images. They are only banning AI created models. That's what their e-mails says. If it's a real model the person submitting the image will need a model release. If there is no model release they know it was generated via AI or the person does not have a model release. In both cases the image gets rejected. Quite easy.
-
Not quite. If its a photo and contains any person, it requires a model release. My understanding is you can only submit your own work, you have to be the copyright owner. Submitting AI images you neither created it or own the copyright and therefore should not be submitting the image to the agency. End of.....
AI is just a tool, like 3D rendering and other apps that help create images. the images created with these apps have the creator's copyright - none of the AI tools attemp.t to claim such a copyright
-
AI is just a tool, like 3D rendering and other apps that help create images. the images created with these apps have the creator's copyright - none of the AI tools attemp.t to claim such a copyright
For Midjourney that is only partially correct. Yes, the person who types in the instructions owns the copyright and can sell the images, BUT unless you took the most expensive "private" subscription to the software (more than 50 euros per month on top of the standard subscription), every other subscriber can see, download and use your images. And you don't have the raw format to prove they are yours ... So yes, you absolutely have the (copy)right to sell them, but knowing that some one else can do the same thing with the same images does give an "insecure" feeling.
-
...
-
AI is just a tool, like 3D rendering and other apps that help create images. the images created with these apps have the creator's copyright - none of the AI tools attemp.t to claim such a copyright
For Midjourney that is only partially correct. Yes, the person who types in the instructions owns the copyright and can sell the images, BUT unless you took the most expensive "private" subscription to the software (more than 50 euros per month on top of the standard subscription), every other subscriber can see, download and use your images. And you don't have the raw format to prove they are yours ... So yes, you absolutely have the (copy)right to sell them, but knowing that some one else can do the same thing with the same images does give an "insecure" feeling.
i should have noted I'm using DALL-E which doesn't work that way
-
Results from my first DALL-E submissions:
Accepted:
AS 6 of 10
DT 2 of 16
SS 9 of 16
10 different, none accepted by all 3!
-
Results from my first DALL-E submissions:
Accepted:
AS 5 of 5
DT 5 of 5
SS 0 of 5
-
Results from my first DALL-E submissions:
Accepted:
AS 6 of 10
DT 2 of 16
SS 9 of 16
10 different, none accepted by all 3!
Why are you advocating for this AI stuff? As said before, I understand it, looking at your own portfolio (and hey, you place links under each comment you write). But it could be devastating to photographers once the technique is perfected. So, are you just looking for a quick buck here? Where is your moral? Nobody who comes here will benefit from this stuff if it is getting accepted.
-
Results from my first DALL-E submissions:
Accepted:
AS 6 of 10
DT 2 of 16
SS 9 of 16
10 different, none accepted by all 3!
Why are you advocating for this AI stuff? As said before, I understand it, looking at your own portfolio (and hey, you place links under each comment you write). But it could be devastating to photographers once the technique is perfected. So, are you just looking for a quick buck here? Where is your moral? Nobody who comes here will benefit from this stuff if it is getting accepted.
If there are buyers for it, if the agencies are accepting it, and it's proven to be Ok from a legal point of view, what's the problem?
Microstockers already took jobs from dedicated newspaper photographers (and others), so why are you still here?
Hiding your head in the sand, will not prevent progress to be "devastating" for you. You better embrace it.
This is why you should be thankful to them for generously sharing their experience, instead of playing their cards close to chest (as I would do), while "others" have their mouths full of sand. ;D
-
If there are buyers for it, if the agencies are accepting it, and it's proven to be Ok from a legal point of view, what's the problem?
Microstockers already took jobs from dedicated newspaper photographers (and others), so why are you still here?
Hiding your head in the sand, will not prevent progress to be "devastating" for you. You better embrace it.
This is why you should be thankful to them for generously sharing their experience, instead of playing their cards close to chest (as I would do), while "others" have their mouths full of sand. ;D
The problem is that AI generated photos have nothing to do anymore with the art of photography. Luckily I am not dependent at all on photography (it's a mere hobby) but a lot of others here are.
But you do have a point with "keep your friends close but your enemies closer" reasoning.
-
...
If there are buyers for it, if the agencies are accepting it, and it's proven to be Ok from a legal point of view, what's the problem?
...
This isn't proven. They are using other people's work to create the images. Be that keywords/ definitions or the images to tell the AI what to create and how to create it. I don't really care how much processing it goes through in the middle. It has to have ingested our images and definitions in some way to create the "new" images. "I pressed control C control V, see it's completely new pixels (with extra steps)" doesn't wash.
-
"What's the problem with it?"
Basics of Economics: supply and demand, scarcity (what's abundant sells for less).
Something that can be created with a few clicks of a button can saturate the market really fast.
Automation will remove the humans from the production of the images.
-
This isn't proven
I know that, and I even tend to agree with it.
But SVH didn't use this argument. This is why I said "if".
"If" it will be proven to be legal, etc..., then he should better embrace progress... etc.
"What's the problem with it?"
Basics of Economics: supply and demand, scarcity (what's abundant sells for less).
Something that can be created with a few clicks of a button can saturate the market really fast.
Automation will remove the humans from the production of the images.
The law of supply and demand is not a problem, it's an opportunity. You can't fight progress for too long. You better embrace it.
It has been the case for thousands of years.
-
If there are buyers for it, if the agencies are accepting it, and it's proven to be Ok from a legal point of view, what's the problem?
Microstockers already took jobs from dedicated newspaper photographers (and others), so why are you still here?
Hiding your head in the sand, will not prevent progress to be "devastating" for you. You better embrace it.
This is why you should be thankful to them for generously sharing their experience, instead of playing their cards close to chest (as I would do), while "others" have their mouths full of sand. ;D
...
The problem is that AI generated photos have nothing to do anymore with the art of photography. ...
stock photography itself has little to do with art! and who says art has to be created by humans?
-
stock photography itself has little to do with art! and who says art has to be created by humans?
Pretty much everyone. I understand that "What is art" has always been a tricky question. Believe me, I have a degree in art.
But, while the definitions seem to be a bit different depending on who you ask or in what time period you asked them, it is most often defined by human activity that involves creative or imaginative talent, a product of imagination and creativity.
Try looking up a few definitions online yourself. You will most often find words like "human", "Person", "creativity", "imaginaton", "expression" and so on. None of this applies to AI generated images. An AI might create something "pretty to look at", but AI generated images are a product of programming/calculation, not of imagination or creativity. Maybe there is an aspect of creativity in the process where a human describes an image to an AI, but take for example that AI generated image that won the art contest that was linked above. A human would have needed to write an essay that is several pages long to really describe this image as it is to every single detail like a fold in clothing and I very much doubt that is what happened.
So, at least as of now I have a hard time accepting that an AI could create "art" the way it is defined now. Art is always meant to express something. Can you imagine how many hours I spent at university analyzing artworks? "What did the artist want to express with this?" "Why did he pick this color?" "Why this composition?" "What feelings did he want to convey?" Imagin sitting in a lecture analyzing AI generated art like this. No point in doing it, because all the AI really did is calculate some pixel.
However, time changes, definitions change. I am sure one day the definition will include AI just the same as human produced products. But for now I still have a hard time accepting it.
But you are completely right about the first thing: Microstock is not about art. Microstock is solely about producing useful images. An AI can do that. At least once it gets better. As of now I find the results I have seen underwhelming in too many case. I even tried to produce some images with DALL for my other job. After a few tries I gave it up and drew something myself instead, because the AI results never really looked good to me.
-
What stock agencies reject this kind of stuff?
-
stock photography itself has little to do with art! and who says art has to be created by humans?
Pretty much everyone. I understand that "What is art" has always been a tricky question. Believe me, I have a degree in art.
Age old question to silence critics. And a good philosophical question.
I don't think a rotting banana taped on a blank canvas with duct tape is "art", but someone else might. So I guess, art is in the eye of the beholder.
We hashed over, how painters said photography is not art in the 1800s.
To answer your question of AI, I will say... Fractal art? Is that more creative and human and all the other things you asked about? Is that more art than AI, where someone enters words to have the machine create something?
I don't welcome AI invading the world of human expression, personal ideas, and efforts, but here it is.
-
I don't welcome AI invading the world of human expression, personal ideas, and efforts, but here it is.
Even I don't welcome, but this is unstoppable and inevitable. We have to accept it sadly.
-
stock photography itself has little to do with art!
Exactly, this is only a craft, like carpentry, like masonry, etc.
Agencies are calling us "artists" only to caress our egos, because it costs them nothing.
Otherwise, while re-watching Mad Men, I noticed an illustrator (Salvatore Romano, in the show) complaining when all clients were asking for photos, instead of his illustrations.
It's very obvious that photographers displaced some illustrators' jobs, when looking at those vintage advertisements from the 50s and before.
Now, AI may displace some photographers' jobs in return.
This is how the story goes!
-
Exactly, this is only a craft, like carpentry, like masonry, etc.
Agencies are calling us "artists" only to caress our egos, because it costs them nothing.
Yeah, I mean, if you get even a wee bit artistic with your photos, you're probably staring at a rejection. That's how artistic they like their "artists" to be.
-
If there are buyers for it, if the agencies are accepting it, and it's proven to be Ok from a legal point of view, what's the problem?
Microstockers already took jobs from dedicated newspaper photographers (and others), so why are you still here?
Hiding your head in the sand, will not prevent progress to be "devastating" for you. You better embrace it.
This is why you should be thankful to them for generously sharing their experience, instead of playing their cards close to chest (as I would do), while "others" have their mouths full of sand. ;D
...
The problem is that AI generated photos have nothing to do anymore with the art of photography. ...
stock photography itself has little to do with art! and who says art has to be created by humans?
Nothing. However, with regards to submitting work to agencies, they require you to be the original copyright owner. If you use AI software, you're not! Same as submitting someone else's work as your own.
AI software is scraping images and metadata from the internet without the original copyright owners permission and using it to create the images in the AI software. So, submitting images from AI software under your name is similar to you downloading images from the internet, slicing and dicing them, merging them and then selling them as your own. How happy would you be if someone did that to your portfolio?!?!
-
If there are buyers for it, if the agencies are accepting it, and it's proven to be Ok from a legal point of view, what's the problem?
Microstockers already took jobs from dedicated newspaper photographers (and others), so why are you still here?
Hiding your head in the sand, will not prevent progress to be "devastating" for you. You better embrace it.
This is why you should be thankful to them for generously sharing their experience, instead of playing their cards close to chest (as I would do), while "others" have their mouths full of sand. ;D
...
The problem is that AI generated photos have nothing to do anymore with the art of photography. ...
stock photography itself has little to do with art! and who says art has to be created by humans?
Nothing. However, with regards to submitting work to agencies, they require you to be the original copyright owner. If you use AI software, you're not! Same as submitting someone else's work as your own.
AI software is scraping images and metadata from the internet without the original copyright owners permission and using it to create the images in the AI software. So, submitting images from AI software under your name is similar to you downloading images from the internet, slicing and dicing them, merging them and then selling them as your own. How happy would you be if someone did that to your portfolio?!?!
no - copyright is owned by the creator of the work & DALL-E makes this clear.
your description of how AI works perpetuates a false and misleading narrative - again RYFM - this is NOT how machine learning works and saying it 3 times doesnt make it true. no one making this argument has shown actual evidence that this is true. it's easy enough to do the experiment
-
I used the following words,using an AI app, "Donald Trump astronaut" and i got this.
https://www.craiyon.com/?prompt=donald%20trump%20astronaut (https://www.craiyon.com/?prompt=donald%20trump%20astronaut)
-
I used the following words,using an AI app, "Donald Trump astronaut" and i got this...
trying th at with DALL-E yields:"It looks like this request may not follow our content policy."
-
I used the following words, but the pics, i think are awful " layflat vintage typewritter with film camera and cup of coffee on wood table"
-
Why would an "agency" need "contributors" to generate this stuff? Why not just have their own employees do it, on demand, in response to customers' requests? And eventually, of course, those former customers will learn how to generate their own images.
-
Why would an "agency" need "contributors" to generate this stuff? Why not just have their own employees do it, on demand, in response to customers' requests? And eventually, of course, those former customers will learn how to generate their own images.
economics 101 - dont do it in-house when it's cheaper to out-source. for agencies, no employee can produce images as cheaply as available from contributors
buyers have even more incentive to use the agency rather than pay their own designers (if they have them). now a designer can choose from 'thousands' of images - what are the chances the 1st phrase they give AI is going to be what they want?
and, the raw images from AI will likely still need work for some time.
-
no - copyright is owned by the creator of the work & DALL-E makes this clear.
your description of how AI works perpetuates a false and misleading narrative - again RYFM - this is NOT how machine learning works and saying it 3 times doesnt make it true. no one making this argument has shown actual evidence that this is true. it's easy enough to do the experiment
The “evidence” is the people behind this transparently saying this is how the technology works. It has to ingest other people’s IP to “learn” how to make images. The steps in the middle are not really relevant. They have helped themselves to other people's copyright material to produce their product, be that the resulting images or the AI engine itself.
The work they have put in is dwarfed by the amount those thousands (millions?) of artists put into created and cataloguing those images.
-
Nothing. However, with regards to submitting work to agencies, they require you to be the original copyright owner. If you use AI software, you're not! Same as submitting someone else's work as your own.
AI software is scraping images and metadata from the internet without the original copyright owners permission and using it to create the images in the AI software. So, submitting images from AI software under your name is similar to you downloading images from the internet, slicing and dicing them, merging them and then selling them as your own. How happy would you be if someone did that to your portfolio?!?!
no - copyright is owned by the creator of the work & DALL-E makes this clear.
your description of how AI works perpetuates a false and misleading narrative - again RYFM - this is NOT how machine learning works and saying it 3 times doesnt make it true. no one making this argument has shown actual evidence that this is true. it's easy enough to do the experiment
I think you are both a bit right/wrong here. It's not like the AI takes our images and then just hacks them into pieces and puts them together again with parts of our images still intact, but it is STILL our microstock work the AI image generators are using as a base for their learning and there is evidence for this. In some earlier stages of DALL the AI would generate something strongly resembling the Shutterstock watermark on the image, because it had been trained with watermarked Shutterstock images so much, that it thought it belonged into the image. Boris Dayma from DALL even admitted so himself: "In early models, still in some models, you ask for a picture - for example mountains under the snow and then on top of it, the Shutterstock or Alamy watermark." This is a direct quote and I have seen screenshots that showed examples of this happening.
And the saddest thing to me is that they did not even bother to pay for the images used to train the AI, as they were clearly watermarked.
Yes, they give copyright to the "describers" of the AI generated images, but they used images to train it where they did not own copyright themselves. They can probably get away with this legally, but moraly I find all of this highly repulsive. They basically used our own images without paying for them to create something that one day in the future will most likely destroy our line of work.
-
And the saddest thing to me is that they did not even bother to pay for the images used to train the AI, as they were clearly watermarked.
Yes, they give copyright to the"describers" of the AI generated images, but they used images to train it where they did not own copyright themselves. They can probably get away with this legally, but moraly I find all of this highly repulsive. They basically used our own images without paying for them to create something that one day in the future will most likely destroy our line of work.
I agree to it. I have access to some of the AI tools and sometimes when I specifically generate any works I can see watermarks of Getty, Alamy, Shutterstock, Dreamstime etc., Though the watermark is so glitched that it cannot be tracked, but since I work in this industry, I can clearly identify those.
So the point is, they created an AI robot which went through almost all microstock website, scraped the whole library of copyrighted IP images to train their AI system. And now they come-up saying that they have built something unique. Doesn't it comes in plagiarism?
But again, this has grown so badly that you cannot take any action as their legal team will easily bypass the trial.
I am also interested to know that with whose permission did they scrapped whole microstock websites. Do those websites even knew about it?
-
Starting to see the first images produced by AI software appearing at the top of searches. It's noted in the image description.
When looking at their ports, they have 100+ pages, 50 of which have been submitted literally within the last month or so and earlier work in the port that looks very average. This is going to be the new mass spamming
I seriously can see this damaging the business significantly. If it's allowed then we'll all have to do it to keep up and then the agencies will be stuff to the rafters with imagery that all has the same look and feel with all the other work buried underneath it. Concerning times ahead I think.
-
I tried midjourney where all is done in the public Discord channel & also put online so everyone can see both your "art" and the prompts used. As I was working on a concept, someone right after me simply copied my prompt verbatim and made a similar image. This is sort of encouraged, though they tell you to add your own words to the prompt.
I liked some of the stylized background rendered and am thinking about how to combine it with my own hand-painted work using my pen tablet in PS. I was working with a fantasy theme so didn't render anything realistic and nearly ran out of my free time.
It was fun to play around, but overall it's a distressing development - and I agree it will only get better and easier to use.
-
I think the idea of using elements of AI imagery in illustrations would be good idea. My main concern as it stands at the moment is the spamming. If people are able to submit work in the 1000's very quickly it is likely to cause problems with imagery being found as we've seem with other types of spamming. Agencies are likely to be swamped
For now, I've emailed agencies to see if they're happy to receive images produced by AI software straight or used in your own work. I don't want my port locked, suspended for behaviour which they deem is outside there T&C's. Passing review is one thing as reviewers may not be aware of what they're passing so I'd rather hear from contributor support about it.
I know Getty Images no longer accepts any submissions created using AI generative models (e.g., Stable Diffusion, Dall-E 2, MidJourney, etc.). That's ALL images as models refers to the AI modelling software used. I'd rather make sure before investing any time on it. It'll be interesting to see what they say!
Edit -
"As I was working on a concept, someone right after me simply copied my prompt verbatim and made a similar image. This is sort of encouraged, though they tell you to add your own words to the prompt. "
I was just reading the iStock/Getty forums and this came up. People were able to generate images that would look the same or very similar. If you submit work to an agency there is a reasonable chance that other people will end up with similar images in their own portfolios, especially if this is encouraged at the point of creation.
-
Mass production is part of the AI.
The computers don't need to rest, take a coffee break.
Even if AI doesn't prevail it will still be a competitor. Something that didn't exist a few year ago.
-
I tried midjourney where all is done in the public Discord channel & also put online so everyone can see both your "art" and the prompts used. As I was working on a concept, someone right after me simply copied my prompt verbatim and made a similar image. This is sort of encouraged, though they tell you to add your own words to the prompt.
I liked some of the stylized background rendered and am thinking about how to combine it with my own hand-painted work using my pen tablet in PS. I was working with a fantasy theme so didn't render anything realistic and nearly ran out of my free time.
It was fun to play around, but overall it's a distressing development - and I agree it will only get better and easier to use.
You can remove images from the server as soon as you make them
-
I thought the time would come when you'll be able to make video clips from AI art or turn stills into moving image. It looks like it's happening way faster than I thought.
https://makeavideo.studio/
Remember the above link is still in its infancy.
It's a double-edged sword for me. I'm really excited by this new way of creation and think how I can involve and evolve my skills into AI (which I'm doing) but also acknowledge that this will have a big impact on our industry (I've been a full-time stock video producer or 12+ years).
Exciting but also a daunting time ahead. We must evolve people to keep up with the pace as it will not ever slow down.
-
Question about the AI software itself. Can you specify a folder of artwork to draw from, or does it always just scrape the internet?
Could I just tell it to draw fom my folder of my images, to avoid copyright problems? Might be a way to create some new images to sell but not having to shoot any more.
I know about Dall-E and midjourney, what are some other brands? Anyone recommend one that they’ve used?
-
Mass production is part of the AI.
The computers don't need to rest, take a coffee break.
Even if AI doesn't prevail it will still be a competitor. Something that didn't exist a few year ago.
once again, that's not how these AI engines work! they generate a few images based on human input & the results need human post processing & editing metadata
my latest submissions:
DT 21 of 34
SS 34 of 34
AS 18 of 18
for AS 16 were rejected as needing a release, even though others in the batch were accepted!
-
Question about the AI software itself. Can you specify a folder of artwork to draw from, or does it always just scrape the internet?
The AIs don't "scrap" the internet to create images. Images from the internet were used to train the AI to create images on its own. So the "scrapping" process already took part when the AI was programmed.
At least DALL let's you upload your own image to modify it, but you can't have it re-trained based on your own images.
-
Question about the AI software itself. Can you specify a folder of artwork to draw from, or does it always just scrape the internet?
Could I just tell it to draw fom my folder of my images, to avoid copyright problems? Might be a way to create some new images to sell but not having to shoot any more.
I know about Dall-E and midjourney, what are some other brands? Anyone recommend one that they’ve used?
With midjourney you can upload your own image and it will use this to draw it's reference from. You can add a weight prompt to tell it what % to reference your image. So if your weight is high it will look very similar to your original image. Not sure if you can upload more than 1 image at any 1 time. I haven't got that far yet :D
-
Question about the AI software itself. Can you specify a folder of artwork to draw from, or does it always just scrape the internet?
The AIs don't "scrap" the internet to create images. Images from the internet were used to train the AI to create images on its own. So the "scrapping" process already took part when the AI was programmed.
At least DALL let's you upload your own image to modify it, but you can't have it re-trained based on your own images.
Again, so they say. Their code is not transparent and they will protect it as propriety. The images they output up till recently would occasionally had identifiable watermarks from the stock agencies in them. They were saying the same thing then. So the app was and is copy pasting to some extent (lets call it what it is as calling it “AI” is really meaningless; when is something become “AI”). It has just gotten better at hiding its sources. The rest is just buzz words.
“It’s not copy pasting, it’s creating new images” again is pretty meaningless. That’s how copy pasting on a computer always works. You convert it to ones and zeros and output a new images at the other end. You can run as many filters and warps on it as you like, it is still using other people’s work to come up with the “new” images.
-
Question about the AI software itself. Can you specify a folder of artwork to draw from, or does it always just scrape the internet?
Could I just tell it to draw fom my folder of my images, to avoid copyright problems? Might be a way to create some new images to sell but not having to shoot any more.
I know about Dall-E and midjourney, what are some other brands? Anyone recommend one that they’ve used?
With midjourney you can upload your own image and it will use this to draw it's reference from. You can add a weight prompt to tell it what % to reference your image. So if your weight is high it will look very similar to your original image. Not sure if you can upload more than 1 image at any 1 time. I haven't got that far yet :D
The results coming out of Midjourney are mind blowing. The remaster feature is crazy.
-
Question about the AI software itself. Can you specify a folder of artwork to draw from, or does it always just scrape the internet?
The AIs don't "scrap" the internet to create images. Images from the internet were used to train the AI to create images on its own. So the "scrapping" process already took part when the AI was programmed.
At least DALL let's you upload your own image to modify it, but you can't have it re-trained based on your own images.
Again, so they say. Their code is not transparent and they will protect it as propriety. The images they output up till recently would occasionally had identifiable watermarks from the stock agencies in them. They were saying the same thing then. So the app was and is copy pasting to some extent (lets call it what it is as calling it “AI” is really meaningless; when is something become “AI”). It has just gotten better at hiding its sources. The rest is just buzz words.
I was the one who pointed out the watermark issue above, so I am well aware. It has nothing to do with the AI "copying & pasting" pieces of image, but with the fact that the AI had so many watermarked images to train with, that it simply "learned" that this is part of the image. It doesn't understand what a "dog" is. Show it 10.000.000 watermarked Shutterstock images of dogs and it will think that dogs have watermarks.
-
Thank you for all the answers. I have a better idea of how it works. So the software you buy already has “learned” and is based on images from the internet programmed in.
Sounds promising, something fun to play with, and you might get a good image out of it. The watermark copyright issues are concerning, and some of the images posted here so far aren’t good. The desk with coffee cup, apple, etc. are bad. I’ll go have a look to see other examples.
-
Question about the AI software itself. Can you specify a folder of artwork to draw from, or does it always just scrape the internet?
Could I just tell it to draw fom my folder of my images, to avoid copyright problems? Might be a way to create some new images to sell but not having to shoot any more.
I know about Dall-E and midjourney, what are some other brands? Anyone recommend one that they’ve used?
With midjourney you can upload your own image and it will use this to draw it's reference from. You can add a weight prompt to tell it what % to reference your image. So if your weight is high it will look very similar to your original image. Not sure if you can upload more than 1 image at any 1 time. I haven't got that far yet :D
The results coming out of Midjourney are mind blowing. The remaster feature is crazy.
I’ll go have a look at this one, thanks.
-
I was the one who pointed out the watermark issue above, so I am well aware. It has nothing to do with the AI "copying & pasting" pieces of image, but with the fact that the AI had so many watermarked images to train with, that it simply "learned" that this is part of the image. It doesn't understand what a "dog" is. Show it 10.000.000 watermarked Shutterstock images of dogs and it will think that dogs have watermarks.
I get how it works. It isn't alive though. What you call "learning" I call copying. Though what we call it is irrelevant really. The fact is they appropriated our intellectual property to make their product. Without our keywords and images they have no product regardless.
-
The AIs don't "scrap" the internet to create images. Images from the internet were used to train the AI to create images on its own. So the "scrapping" process already took part when the AI was programmed.
At least DALL let's you upload your own image to modify it, but you can't have it re-trained based on your own images.
Again, so they say. Their code is not transparent and they will protect it as propriety. The images they output up till recently would occasionally had identifiable watermarks from the stock agencies in them. They were saying the same thing then. So the app was and is copy pasting to some extent (lets call it what it is as calling it “AI” is really meaningless; when is something become “AI”). It has just gotten better at hiding its sources. The rest is just buzz words.
“It’s not copy pasting, it’s creating new images” again is pretty meaningless. That’s how copy pasting on a computer always works. You convert it to ones and zeros and output a new images at the other end. You can run as many filters and warps on it as you like, it is still using other people’s work to come up with the “new” images.
just because you don't trust a source is no justification to libel them with your unsupported claims, especially when those opinions are presented as 'facts'
and you continue to pose the false narrative that these AI are copying images to create new ones. Even those agencies banning AI do not make that unsupportable claim. instead, they are concerned about the training of AI which is an entirely different issue
-
..
I get how it works. It isn't alive though. What you call "learning" I call copying. Though what we call it is irrelevant really. The fact is they appropriated our intellectual property to make their product. Without our keywords and images they have no product regardless.
you're setting strawman arguments: No one is claiming AI is 'alive'. it's 'artificial' intelligence, not a human neural system. 'calling' it copying doesnt make it so. your implied definition of AI doesnt conform with any objective definition.
the question of copyright appropriation is a separate problem from the question of AI
AI results already are impressive:
https://www.forbes.com/sites/bernardmarr/2018/04/30/27-incredible-examples-of-ai-and-machine-learning-in-practice/?sh=4f56ffdd7502 (https://www.forbes.com/sites/bernardmarr/2018/04/30/27-incredible-examples-of-ai-and-machine-learning-in-practice/?sh=4f56ffdd7502)
other examples include
Deep Blue, netflix recommendations
Google's AlphaGo beats non-masters without knowing the rules of the game
AlphaFold has excellent results better than any other approach in solving the problem of protein folding
-
and you continue to pose the false narrative that these AI are copying images to create new ones. Even those agencies banning AI do not make that unsupportable claim. instead, they are concerned about the training of AI which is an entirely different issue
Then how do you think this works?
Let's take for example the picture that was supposed to be a 19th century naval battle that you created some some ago with the AI. How do you think the AI created this? Clearly it did not learn what a naval battle is, because the picture did not show one. So either it looked on the spot for pictures with a 19th century naval battle in description or keywords and created a similar image, or what it thought is similar or else during the training most of the information from the images the AI was treined must have been written into a massive database and then the AI created the image from that information. Either way, it used more or less directly existing images to create your images. What other way is there?
Clearly the Ai did not make the jump to understand the images it was trained to understand that a naval battle requires ships fighting with each other in water, so it could not for example create a photo realistic image with water and sailing ships, but the style of the image clearly showed that it was created with old oil paintings a a basis. The AI was not able to abstract from that.
-
I don't want to be the guy thinking of smart words of creating an great AI image.
I want to be the guy that that takes a photo of an actual landscape, person or happening. I want to be thinking about composition, light and technique or maybe even having the lucky opportuntiy to take a once in a lifetime shot when a rare situation occurs.
Sorry, that I am not embracing the future with all of it's new capabillities, like DALL-E, but I think it will be a total waste of human's capabillities and good things will truly get lost by it.
It will be really sad if AI programmes could reach the point that they would replace us (by using our work to begin with).
-
I don't want to be the guy thinking of smart words of creating an great AI image.
I want to be the guy that that takes a photo of an actual landscape, person or happening. I want to be thinking about composition, light and technique or maybe even having the lucky opportuntiy to take a once in a lifetime shot when a rare situation occurs.
Sorry, that I am not embracing the future with all of it's new capabillities, like DALL-E, but I think it will be a total waste of human's capabillities and good things will truly get lost by it.
It will be really sad if AI programmes could reach the point that they would replace us (by using our work to begin with).
I see AI as a new means of adding to my creative inputs. You (we) still need the traditional skills as we always will but like all of technology from the first camera obscure to the digital ones we have today. They are tools to capture a moment in time or to capture a thought or inspiration. I see AI as a new tool to help us generate something that could have been impossible or out of reach before it was invented. My thoughts on using AI is exactly like this video... https://www.youtube.com/watch?v=yAy0NlGesOE (https://www.youtube.com/watch?v=yAy0NlGesOE)
I think combining both traditional skills with AI is mindblowing and such a time saver.
-
and you continue to pose the false narrative that these AI are copying images to create new ones. Even those agencies banning AI do not make that unsupportable claim. instead, they are concerned about the training of AI which is an entirely different issue
Then how do you think this works?
Let's take for example the picture that was supposed to be a 19th century naval battle that you created some some ago with the AI. How do you think the AI created this? Clearly it did not learn what a naval battle is, because the picture did not show one. So either it looked on the spot for pictures with a 19th century naval battle in description or keywords and created a similar image, or what it thought is similar or else during the training most of the information from the images the AI was treined must have been written into a massive database and then the AI created the image from that information. Either way, it used more or less directly existing images to create your images. What other way is there?
Clearly the Ai did not make the jump to understand the images it was trained to understand that a naval battle requires ships fighting with each other in water, so it could not for example create a photo realistic image with water and sailing ships, but the style of the image clearly showed that it was created with old oil paintings a a basis. The AI was not able to abstract from that.
I don't want to beat around the bush but all art is copied (influenced) from somewhere else. Music is famously known for it. If I had to make a 19th century naval battle the first thing I'd do is google and look at all the pictures and see how they were composed, mood, structure etc. Let's be honest who wouldn't? Before the internet, I'm sure many an artist would walk into galleries and research and study other painters' techniques.
The way we need to use this new means of creation is to add it to our bucket of already made skills and create something unique. That's the way I see it anyways.
-
and you continue to pose the false narrative that these AI are copying images to create new ones. Even those agencies banning AI do not make that unsupportable claim. instead, they are concerned about the training of AI which is an entirely different issue
Then how do you think this works?
Let's take for example the picture that was supposed to be a 19th century naval battle that you created some some ago with the AI. How do you think the AI created this? Clearly it did not learn what a naval battle is, because the picture did not show one. So either it looked on the spot for pictures with a 19th century naval battle in description or keywords and created a similar image, or what it thought is similar or else during the training most of the information from the images the AI was treined must have been written into a massive database and then the AI created the image from that information. Either way, it used more or less directly existing images to create your images. What other way is there?
Clearly the Ai did not make the jump to understand the images it was trained to understand that a naval battle requires ships fighting with each other in water, so it could not for example create a photo realistic image with water and sailing ships, but the style of the image clearly showed that it was created with old oil paintings a a basis. The AI was not able to abstract from that.
again, unsupported assumptions tending towards conspiracy theories- that's not how machine learning operates, and your claim DALL-E copies other images is specifically denied by open-ai. you may choose not to believe them, but that doesn't justify your claiming to know how the image is created.
the point is that the AI doesn't know anything
Of shoes — and ships — and sealing-wax —
Of cabbages — and kings —
And why the sea is boiling hot —
And whether pigs have wings.'
like the other examples i mentioned, the AI is not mimicking a human
-
I don't want to be the guy thinking of smart words of creating an great AI image.
I want to be the guy that that takes a photo of an actual landscape, person or happening. I want to be thinking about composition, light and technique or maybe even having the lucky opportuntiy to take a once in a lifetime shot when a rare situation occurs.
Sorry, that I am not embracing the future with all of it's new capabillities, like DALL-E, but I think it will be a total waste of human's capabillities and good things will truly get lost by it.
It will be really sad if AI programmes could reach the point that they would replace us (by using our work to begin with).
sad or not, you keep using the same arguments painters used against photography - yet painting hasn't disappeared. creative destruction means you either adopt the new technology or find a way to make photography relevant in an AI age. you describe making 'art' but we're talking about producing stock images.
agribusiness forced out many smaller farmers. those who survived found new approaches - organics, buy-local, heritage veg, etc
-
I see AI as a new means of adding to my creative inputs. You (we) still need the traditional skills as we always will but like all of technology from the first camera obscure to the digital ones we have today. They are tools to capture a moment in time or to capture a thought or inspiration. I see AI as a new tool to help us generate something that could have been impossible or out of reach before it was invented. My thoughts on using AI is exactly like this video... https://www.youtube.com/watch?v=yAy0NlGesOE (https://www.youtube.com/watch?v=yAy0NlGesOE)
I think combining both traditional skills with AI is mindblowing and such a time saver.
In The Third Man, Orson Welles’ character Harry Lime says, “In Italy for thirty years under the Borgias, they had warfare, terror, murder, and bloodshed, but they produced Michelangelo, Leonardo da Vinci, and the Renaissance. In Switzerland, they had brotherly love, they had five hundred years of democracy and peace, and what did that produce? The cuckoo clock.”
-
again, unsupported assumptions tending towards conspiracy theories- that's not how machine learning operates,
Then please enlighten us how it does work.
and your claim DALL-E copies other images is specifically denied by open-ai. you may choose not to believe them, but that doesn't justify your claiming to know how the image is created.
I am not claiming the Ai copies any specific image. I claim that the AI creates images on a variety of existing images and I claim that the AI has to store what it learned somewhere. We store information in our brain, computers typically use databases. Without a database or some other data storage the AI can learn nothing. So the question remains what exactly is stored in this data storage, what does the AI actually learn? Clearly it does not learn what a naval battle is. It only learns how images with that description or that keyword look like and it has to store this information somewhere. So it has to store for hundreds of thousands keywords how the images with those keywords look like. How else would it be able to create images when the user enters those keywords?
You seem to think that this is some kind of magic. I believe it is technology.
-
If I had to make a 19th century naval battle the first thing I'd do is google and look at all the pictures and see how they were composed, mood, structure etc. Let's be honest who wouldn't?
Sure, but you would be able to abstract from the specific images and choose a setting and specifics for the battle yourself, for example you would choose, which countries ships battle each other, for example Turkish ships against Russian ships, indicating this by the flags of the ships. You would probably choose a specific battle, like the Battle of Sinop during the Crimean War. You would show some fighting, like cannons firing, smoke, damage to the ships. You would be able to abstract from the style of the images you looked at so that your image probably would not look like an oil painting.
All of this is missing from the image Cascoly generated with the AI.
-
again, unsupported assumptions tending towards conspiracy theories- that's not how machine learning operates,
Then please enlighten us how it does work.
and your claim DALL-E copies other images is specifically denied by open-ai. you may choose not to believe them, but that doesn't justify your claiming to know how the image is created.
I am not claiming the Ai copies any specific image. I claim that the AI creates images on a variety of existing images and I claim that the AI has to store what it learned somewhere. We store information in our brain, computers typically use databases. Without a database or some other data storage the AI can learn nothing. So the question remains what exactly is stored in this data storage, what does the AI actually learn? Clearly it does not learn what a naval battle is. It only learns how images with that description or that keyword look like and it has to store this information somewhere. So it has to store for hundreds of thousands keywords how the images with those keywords look like. How else would it be able to create images when the user enters those keywords?
You seem to think that this is some kind of magic. I believe it is technology.
That is how I understand it, too.
lI read a little about DALL-E and midjourney today. I thought it was software that you buy, but no it’s a subscription-based site. It sounds like it would be fun to play around with. I just don’t think they have any copyright issues ironed out yet. Because it is learning and storing images found on the internet using keywords.
Tomorrow I will go look at some actual uploaded images (on adobe?) to see the quality. As a person involved in creative work my whole career, this is very intriguing. As mentioned in one of the posts above, I see it as a tool to generate creative ideas, more than actually creating images to submit to microstock. At this point anyway. I’m sure the process will be refined and image quality will improve in the future. Exciting stuff, wish I weren’t at the tail end of my career.
Here’s the midjourney article I read, which talks about the copyright conundrum.
https://expertphotography.com/midjourney/ (https://expertphotography.com/midjourney/)
And this about Dall-E: “This public debut comes without answers to some key questions. It's not clear if AI-generated art is fair use or stolen, for instance — Getty Images and similar services have banned the material out of concern it might violate copyright. While this expansion will be welcome, it might test some legal limits.”
https://www.engadget.com/dall-e-ai-image-generator-beta-no-waitlist-173746483.html (https://www.engadget.com/dall-e-ai-image-generator-beta-no-waitlist-173746483.html)
Interesting that Elon Musk is involved in OpenAI and Dall-E ... I had seen him talk about AI in tweets, but didn’t connect the dots.
-
just because you don't trust a source is no justification to libel them with your unsupported claims, especially when those opinions are presented as 'facts'
and you continue to pose the false narrative that these AI are copying images to create new ones. Even those agencies banning AI do not make that unsupportable claim. instead, they are concerned about the training of AI which is an entirely different issue
I am not making any additional claims at all (let alone libellous ones). Again, you are just arguing semantics. Look at the basic facts. Their product ingests a load of work that they don’t own the copyright to and outputs images based (in some way) on those images and keywords.
Business model:
OUR WORK (taken without permission or compensation) ----->PROCESSING (call it whatever makes you feel good)----->THEIR PRODUCT (and lots of cash for them)
OUR WORK----->PROCESSING----->THEIR PRODUCT
-
I just found this on one forum. This AI has totally ripped of microstock content.
(https://replicate.com/api/models/stability-ai/stable-diffusion/files/d1b2c961-e765-4e26-8505-bd88e02340df/out-0.png)
(https://replicate.com/api/models/stability-ai/stable-diffusion/files/0c7cf8c7-a267-4c12-928d-249c1d603a76/out-1.png)
-
I just found this on one forum. This AI has totally ripped of microstock content.
(https://replicate.com/api/models/stability-ai/stable-diffusion/files/d1b2c961-e765-4e26-8505-bd88e02340df/out-0.png)
(https://replicate.com/api/models/stability-ai/stable-diffusion/files/0c7cf8c7-a267-4c12-928d-249c1d603a76/out-1.png)
The AI was trained with watermarked images so much that it thinks the watermark should belong to the image. It thinks the watermark is part of a businessman, just like his tie or glasses.
This is an issue that has been discussed before and even adressed by members of DALL. It doesn't mean the image itself was "ripped-off", just that the AI was trained wrongly. Could have easily been avoided if the people working for /owning DALL and other AI image generators would have, well, I don't know... bothered to actually PAY for the images they fed their AI with? Can't say I don't feel a little bit gleefull that it's causing hiccups in the image creating process.
-
I just found this on one forum. This AI has totally ripped of microstock content.
No, no it's not copying it. It just "learnt" what the watermark looks like and reproduced the exact same watermark from its “memory” of the essence of its “watermark-ness”. Not the same thing at all (sarcasm of course).
Again I get what happened here, it trained on watermarked images so reproduces the watermark. What it does is give the game away beautifully until they clean it up. It is using images and keywords. Just because it forms a “model” from the information it ingests and spews out a conglomerated version from this “idea” doesn’t make any difference legally IMHO.
-
.
-
again, unsupported assumptions tending towards conspiracy theories- that's not how machine learning operates,
Then please enlighten us how it does work.
and your claim DALL-E copies other images is specifically denied by open-ai. you may choose not to believe them, but that doesn't justify your claiming to know how the image is created.
I am not claiming the Ai copies any specific image. I claim that the AI creates images on a variety of existing images and I claim that the AI has to store what it learned somewhere. We store information in our brain, computers typically use databases. Without a database or some other data storage the AI can learn nothing. So the question remains what exactly is stored in this data storage, what does the AI actually learn? Clearly it does not learn what a naval battle is. It only learns how images with that description or that keyword look like and it has to store this information somewhere. So it has to store for hundreds of thousands keywords how the images with those keywords look like. How else would it be able to create images when the user enters those keywords?
You seem to think that this is some kind of magic. I believe it is technology.
Speaking of database is quite reductive. Never heard of neural networks or deep learning? The images are not "stolen" but used to form concepts, as you do looking around, stimulating your brain through your eyes. Also if you are not a scientist there are tons of information online to begin to have a better idea of the machine learning process.
-
Many here celebrate this, but perhaps it is the beginning of the end of an extra income like microstock. Someone could not agree with I will say, but using images from microstock or from the web makes these AI image creation companies cheaters who are taking advantage of something that is not theirs.It is not as deep a thought as many have written here. In conclusion it is a misappropriation of images.
-
again, unsupported assumptions tending towards conspiracy theories- that's not how machine learning operates,
Then please enlighten us how it does work.
and your claim DALL-E copies other images is specifically denied by open-ai. you may choose not to believe them, but that doesn't justify your claiming to know how the image is created.
I am not claiming the Ai copies any specific image. I claim that the AI creates images on a variety of existing images and I claim that the AI has to store what it learned somewhere. We store information in our brain, computers typically use databases. Without a database or some other data storage the AI can learn nothing. So the question remains what exactly is stored in this data storage, what does the AI actually learn? Clearly it does not learn what a naval battle is. It only learns how images with that description or that keyword look like and it has to store this information somewhere. So it has to store for hundreds of thousands keywords how the images with those keywords look like. How else would it be able to create images when the user enters those keywords?
You seem to think that this is some kind of magic. I believe it is technology.
Speaking of database is quite reductive. Never heard of neural networks or deep learning? The images are not "stolen" but used to form concepts, as you do looking around, stimulating your brain through your eyes. Also if you are not a scientist there are tons of information online to begin to have a better idea of the machine learning process.
The Ai should learn from public domain images, how an image it is! Not use images that are not public domain!
-
Hope the mayority of free web sites about AI for images are like this.
-
A.I. can't use images from microstock because they are watermarked it would have to use Google or PD images. Of course, google would find out that they're using said images and would probably buy them out.
-
At the very least the watermarks show the images that they use to ‘learn’ from are stolen.
-
A.I. can't use images from microstock because they are watermarked
And yet they clearly did.
-
A.I. can't use images from microstock because they are watermarked it would have to use Google or PD images. Of course, google would find out that they're using said images and would probably buy them out.
Look a couple of posts above yours. Obviously they did. Apparently this was happening a lot more earlier on in development (the visible watermarks I mean). The engines have been trained to filter out more of this noise. The founders of some of these companies say they did. The descriptions and keywords in a predictable format are a gold mine for these companies.
I have tried Dall E and have had results of works with what look like blury signatures in the corner.
-
again, unsupported assumptions tending towards conspiracy theories- that's not how machine learning operates,
Then please enlighten us how it does work.
...
i & others have supplied multiple links about ML on the 2 threads about AI -- or just google it
-
I wouldn't be surprised if at some point a company like say SS got paid by one of these places for access to the images and keywords. Did we see any of that money - no. Was it allowed somewhere in SS's multiply rewritten vague terms - probably. Is it "right" probably not. Is there anything we can do about it - probably not.
It would be interesting to see what the results would be for people that have used their own business name as keywords if they used that as a starting input.
-
I wouldn't be surprised if at some point a company like say SS got paid by one of these places for access to the images and keywords.
If this had been the case, then the AI would not have learned to genereate SS watermarks on their images, because if SS gave them access to the images there would not have been a watermark on the images.
-
Here comes Google's text to 3d generation.
(https://lh6.googleusercontent.com/sCHwN9ch-X6SPlG58jTlgfQPxQVL4RThkDKm0GQDh8xrNB-9vm4yYHWIJOMw2YdXgRqKImoTtHT0ciX-KNmJMznO6S1MUTMClNuIjXMkzMM9r7jt5jaocRoA1xvPNO614OxiIxC9817sKZYh62NjTkeJg3ltvjBXBZJwwPewPHvmQT9L0sAKJoPlbQ)
https://dreamfusion3d.github.io/
-
What's interesting experimenting with this technology is what it's good at and what it's bad at.
I think it'll eventually become really good at lifestyle stuff - beautiful woman sitting in private jet, eating a bowl of salad etc. for instance. So those type of photographers are screwed.
Imagined images and illustrations - those artists are largely screwed.
Generic landscapes - misty forests, dramatic mountain ranges, green farmland. Those photographers are screwed.
What it's really bad at is named locations. It doesn't seem to be able to produce decent realistic images of Big Ben or Mt Everest or the Taj Mahal because those images require a single viewpoint and you can't combine images without it looking very odd.
-
...
What it's really bad at is named locations. It doesn't seem to be able to produce decent realistic images of Big Ben or Mt Everest or the Taj Mahal because those images require a single viewpoint and you can't combine images without it looking very odd.
these folk are likely screwed as well - just not as quickly as your other examples. when i asked for images of crowds and the yeni camii near the golden horn, the results showed several different angles
only images got the minarets correct, but it's just a matter of time before that''s improved
3 of the 4 'sherpas on everest' pictures had a reasonable image of everest with a recognizable west ridge & summit pyramid
-
If AI can make any picture you want why would anyone need agencies? You just buy the software and add any picture you want to your article. So it's not just the contributors losing here. It's also the agencies. They will be redundant, like us.
AI can't do everything. It will struggle generating images of places that don't have many photos. It can't do any editorial, where the image can't be manipulated. I'll do everything that AI can't be used for, or it would be too much hard work for AI.
-
A.I. can't use images from microstock because they are watermarked it would have to use Google or PD images. Of course, google would find out that they're using said images and would probably buy them out.
One of the images I made with AI, clearly had the Alamy watermark on it. The AI adjusted it, but was still obvious where the image came from.
-
...
What it's really bad at is named locations. It doesn't seem to be able to produce decent realistic images of Big Ben or Mt Everest or the Taj Mahal because those images require a single viewpoint and you can't combine images without it looking very odd.
these folk are likely screwed as well - just not as quickly as your other examples. when i asked for images of crowds and the yeni camii near the golden horn, the results showed several different angles
only images got the minarets correct, but it's just a matter of time before that''s improved
3 of the 4 'sherpas on everest' pictures had a reasonable image of everest with a recognizable west ridge & summit pyramid
Probably not the best example to use... for fiction it maybe ok depending on the audience but certainly no good for anyone in the world of mountaineering.
You can't use an image that is similar to a mountain when you need the image to highlight a specific route up it. A lot of the books I have for different mountains in the Alps an the Andes were bought as a reference guide so we knew what to expect before we got to the climb. No point having something that looks similar as it could be very dangerous once you're at 4-8000 metres up.
The climbing community as a whole would pickup on it in a flash, they are very protective of tradition. Just try and bolt a route up a mountain in the Lake District, they would hunt you down. Any images that weren't accurate would be ridiculed by the community. Even in the Lake District or Scottish Highlands they need to be accurate. Editors don't even like it when an image is captioned a little wrong as they could use the image incorrectly that could lead to climbers and hikers getting into difficulty on the mountain.
As a photo on the wall, a real photo of Everest and climbers hanging on the wall is like wow, amazing achievement and place. You think of the effort it took to get there, the dangers, the blood sweat and tears etc of each of those captured in the image... there is an emotional connection. An AI rendition is just an empty vessel in comparison. No value at all because it's not real. But I guess that's just the way I see it from a climbers perspective.
Maybe in the future that's what we'll see. People hunting out real imagery over AI as they don't want something that is fake. They want something that is real, something that can connect them to the earth we live in... something that does exist and was seem by a fellow human
-
...
What it's really bad at is named locations. It doesn't seem to be able to produce decent realistic images of Big Ben or Mt Everest or the Taj Mahal because those images require a single viewpoint and you can't combine images without it looking very odd.
these folk are likely screwed as well - just not as quickly as your other examples. when i asked for images of crowds and the yeni camii near the golden horn, the results showed several different angles
only images got the minarets correct, but it's just a matter of time before that''s improved
3 of the 4 'sherpas on everest' pictures had a reasonable image of everest with a recognizable west ridge & summit pyramid
Probably not the best example to use... for fiction it maybe ok depending on the audience but certainly no good for anyone in the world of mountaineering.
You can't use an image that is similar to a mountain when you need the image to highlight a specific route up it. A lot of the books I have for different mountains in the Alps an the Andes were bought as a reference guide so we knew what to expect before we got to the climb. No point having something that looks similar as it could be very dangerous once you're at 4-8000 metres up.
The climbing community as a whole would pickup on it in a flash, they are very protective of tradition. Just try and bolt a route up a mountain in the Lake District, they would hunt you down. Any images that weren't accurate would be ridiculed by the community. Even in the Lake District or Scottish Highlands they need to be accurate. Editors don't even like it when an image is captioned a little wrong as they could use the image incorrectly that could lead to climbers and hikers getting into difficulty on the mountain.
As a photo on the wall, a real photo of Everest and climbers hanging on the wall is like wow, amazing achievement and place. You think of the effort it took to get there, the dangers, the blood sweat and tears etc of each of those captured in the image... there is an emotional connection. An AI rendition is just an empty vessel in comparison. No value at all because it's not real. But I guess that's just the way I see it from a climbers perspective.
Maybe in the future that's what we'll see. People hunting out real imagery over AI as they don't want something that is fake. They want something that is real, something that can connect them to the earth we live in... something that does exist and was seem by a fellow human
I was an active mountaineer & backcountry skier - reaching 21K in Himalaya & many climbs in Alps, Andes, & Rockies and winter climbs in the Cascades & Canada (retired now). I was a committee chair in the Seattle Mountaineers club and climb & ski mountaineering leader. I recently received my 50 yr pin from the Mazamas mountaineering club. I also designed an Everest climbing game in the90s. So i agree with your comment on the climbing community.
But the image was never aimed at that group! Anyone thinking it was intended as a route map would not have a long career! it was aimed at the microstock market for those looking for generic moutain or climbing image or an impressionist view of the Himalaya. My comment on the 'accuracy' of the result was about the quality of the AI
-
I agree... Once things settle down, I think AI imagery will only used for "fiction" work. Anything that requires a degree of accuracy, tourism, guides & realism to a degree, people will look to use images created by humans.
I still feel we haven't seen the end of agencies banning AI imagery for sale as stock though. When companies buy imagery from agencies they want the security of knowing all required releases are on file etc and that there is no potential for a legal challenge. It's often the case that the client that buys the image is a designer or advertising agency and the damage that could be caused by their client being sued is often too big a risk to take. One bad case could cost them their client book.
The enquires I've made to agencies so far is they are very reluctant to give any answer on AI and I assume that is due to their legal teams reviewing the situation and watching what others will do. In a world that loves to sue each other, it is a sizeable risk and for what? The agencies already receive plenty of imagery without making things more complicated. I can see it more as a tool for places / people who want to cut out the stock agency / artist altogether.
If it's easier to look through a library of images that have already been created (rather than trying to come up with a written line of text to create an image) then people will often take the line of least resistance.
-
Good aesthetic and visual judgment is still needed to get a decent image of the AI. They also show some inaccuracies that need to be retouched. In other words, work changes, but it does not disappear. And it will be a good tool to save time and money. I believe that new horizons are opening... Art is more a state of mind than a mere technical ability.
-
Canva adds AI too: https://petapixel.com/2022/11/10/canva-adds-a-free-and-unlimited-ai-text-to-image-generator/
-
Canva adds AI too: https://petapixel.com/2022/11/10/canva-adds-a-free-and-unlimited-ai-text-to-image-generator/
Here’s the harsh reality; if businesses and brands find an effective way to cut out the middle person (the photographer) they will do it. If it’s more cost-effective to use AI for generic stock, food, and product photography, then photographers in those fields are likely going to have to look to other avenues for work. Is it fair? No. but it’s business. As we’ve seen with automated checkouts, factories powered by robots, and, more recently, the driverless car, the upper echelon of this world is constantly looking to replace humans with tech. As much as we want to shout about our disdain of the direction of society, there’s little we can do about it.
What we’re likely to see is AI replace some [photography disciplines] almost completely – stock photography, product photography, food photography are most at risk…
-
Canva adds AI too: https://petapixel.com/2022/11/10/canva-adds-a-free-and-unlimited-ai-text-to-image-generator/
Here’s the harsh reality; if businesses and brands find an effective way to cut out the middle person (the photographer) they will do it. If it’s more cost-effective to use AI for generic stock, food, and product photography, then photographers in those fields are likely going to have to look to other avenues for work. Is it fair? No. but it’s business. As we’ve seen with automated checkouts, factories powered by robots, and, more recently, the driverless car, the upper echelon of this world is constantly looking to replace humans with tech. As much as we want to shout about our disdain of the direction of society, there’s little we can do about it.
What we’re likely to see is AI replace some [photography disciplines] almost completely – stock photography, product photography, food photography are most at risk…
You explained it very well. And I believe it will become harsh reality as soon as more users find out about AI and learn how to use it. We'll probably see in the near future.
-
This made me chuckle...
-
This made me chuckle...
Not so good for wheels, gears, handles, connection points, or anything mechanical that requires logical engineering.
I hate to add to the extent of the problem, but once the AI gets smarter at still images, the next advance will be video and motion.
-
I shoot video, I don't face these problems.
-
I shoot video, I don't face these problems.
Some of these sites said their next step is video, Dall-e I think. Just wait.
-
I shoot video, I don't face these problems.
Some of these sites said their next step is video, Dall-e I think. Just wait.
Rhetorical questions...
1. After how many decades?
2. What will be the demand for artificial cartoon video?
3. Can you imagine what processing power a stock should have in order to generate not a photo, but a video, in 4K format and with a normal bitrate.
4. The video has always been different from the photo, I think there will be no problems for sure in the coming decades.
-
Dall-e I think. Just wait.
Wake up when they start. If we all live to see that time.
-
Video has already started
https://makeavideo.studio/
-
Video has already started
https://makeavideo.studio/
1. This is just research. It is also not clear how everything works there, it is quite possible that in the final video they use fragments of someone else's video, and this is a copyright infringement and no one will sell it on stocks.
2. There is no such thing in stock agencies and is not planned.
3. Everything on this site is cartoons, i.e. animation. Yes, perhaps those stockers who create animation or 3D rendering in 10 years will begin to feel competition in this segment.
4. I'm creating a live stock video and I don't see any threats.
5. Yes, it is quite possible that there will be many such sites, but these will not be stock agencies, and the content there will be extremely specific, it will definitely not be my buyers who will buy there. And how copyright issues will be resolved there is another question.
-
1. This is just research.
No, it's not. Actually it even already exists in basic form, like Meta's makeavideo or D-ID.
It is also not clear how everything works there, it is quite possible that in the final video they use fragments of someone else's video, and this is a copyright infringement and no one will sell it on stocks.
It's pretty clear actually, because that's how the whole AI generation works. If you had bothered reading any of the threads about AI generated images instead of commenting first, reading later, you'd know. That's the whole point of AI generated content: It LEARNS from other workand creates it's own content.
2. There is no such thing in stock agencies and is not planned.
You'd have said the same about photos half a year ago.
3. Everything on this site is cartoons, i.e. animation.
What is "this site"? We are talking about sites that create AI generated contet in general here and most of them can create photos.
Tell me, which one is a human made photo and which one was created by an AI?
(https://i.postimg.cc/3xpkwXQH/Untitled-1.jpg)
4. I'm creating a live stock video and I don't see any threats.
Someone could take your video, describe what he is seeing to the AI and it would recreate it's own version of it. Still not a thread?
5. Yes, it is quite possible that there will be many such sites, but these will not be stock agencies, and the content there will be extremely specific, it will definitely not be my buyers who will buy there.
Did you get the part where there are AIs that create images - photos, not just "cartoons" and stock agencies like Shutterstock are implementing selling them on their platform already? So these would be the exact same buyers this content is offered to.
I don't think AI images are a real competition to stock photographers yet, because for the most part I think the results are not good enough when it come sto more complex topics. But we'll get there some day. Videos will probably take more time. Maybe so long that it won't be a thread to current stock videographers in their lifetime. But one day.
-
Videos will probably take more time. Maybe so long that it won't be a thread to current stock videographers in their lifetime. But one day.
I agree with your conclusion. Everything else is of no interest to me. Arguing for the sake of arguing is pointless. When stocks start offering videos created by AI, then we’ll talk and see what a video competitor has appeared there.
-
Midjourney advancements in 6 months:
https://www.youtube.com/watch?v=d4lY2TjqNTs (https://www.youtube.com/watch?v=d4lY2TjqNTs)
-
It LEARNS from other workand creates it's own content.
It will still be necessary to check whether he creates his own content or takes other people's work as a basis. So, if he takes your photos as a basis, then the stock should still pay you for this. I'm not talking about the fact that the rules forbid creating content based on someone else's work, for such a ban and judge.
-
Midjourney advancements in 6 months:
https://www.youtube.com/watch?v=d4lY2TjqNTs (https://www.youtube.com/watch?v=d4lY2TjqNTs)
Drawings, cartoons, I don't see any threat. And I don't see any threat to the video at all. I can imagine how long it takes to fiddle with the program in order to describe what you need, to quickly buy a ready-made real photo. And what kind of software resources are involved, how much is it in terms of time, in terms of costs, I'm not talking about creating a video.
-
This made me chuckle...
Ewww...
-
Arguing for the sake of arguing is pointless.
Good advise that you should follow.
-
AI is also bad news for agencies, eventually stock image users will be able to download cheap versions of AI software and get the images they want without paying subscriptions. In the medium term, AI will not only kill the contributors but also the agencies
-
AI is also bad news for agencies, eventually stock image users will be able to download cheap versions of AI software and get the images they want without paying subscriptions. In the medium term, AI will not only kill the contributors but also the agencies
It will not kill and will not even create competition. I dealt with one program that converts HD to 4k and removes any noise from the video, but it needs a very powerful PC to work, and even on a powerful PC it takes a lot of time. As a result, the cost of a PC and electricity will block the profit.
-
AI is also bad news for agencies, eventually stock image users will be able to download cheap versions of AI software and get the images they want without paying subscriptions. In the medium term, AI will not only kill the contributors but also the agencies
It will not kill and will not even create competition. I dealt with one program that converts HD to 4k and removes any noise from the video, but it needs a very powerful PC to work, and even on a powerful PC it takes a lot of time. As a result, the cost of a PC and electricity will block the profit.
One can easily rent a cloud GPU at very cheap price.
-
AI is also bad news for agencies, eventually stock image users will be able to download cheap versions of AI software and get the images they want without paying subscriptions. In the medium term, AI will not only kill the contributors but also the agencies
It will not kill and will not even create competition. I dealt with one program that converts HD to 4k and removes any noise from the video, but it needs a very powerful PC to work, and even on a powerful PC it takes a lot of time. As a result, the cost of a PC and electricity will block the profit.
One can easily rent a cloud GPU at very cheap price.
ok, when you rent it and create something there, tell me.
8)
-
AI is also bad news for agencies, eventually stock image users will be able to download cheap versions of AI software and get the images they want without paying subscriptions. In the medium term, AI will not only kill the contributors but also the agencies
It will not kill and will not even create competition. I dealt with one program that converts HD to 4k and removes any noise from the video, but it needs a very powerful PC to work, and even on a powerful PC it takes a lot of time. As a result, the cost of a PC and electricity will block the profit.
One can easily rent a cloud GPU at very cheap price.
ok, when you rent it and create something there, tell me.
8)
He doesn't need to rent one and create something with it, as the majority of these AI image generators are all cloud based... so it doesn't matter what setup the end user has. If you'd looked into it and done even the slightest bit of research, rather than basing your opinion on incorrect information that you just made up (like you usually do), then you'd know that.
-
Tell me, which one is a human made photo and which one was created by an AI?
(https://i.postimg.cc/3xpkwXQH/Untitled-1.jpg)
One on the right is AI. That's my guess? How did I do?
-
Tell me, which one is a human made photo and which one was created by an AI?
(https://i.postimg.cc/3xpkwXQH/Untitled-1.jpg)
One on the right is AI. That's my guess? How did I do?
Left one is the AI generated image by DALL E. 😥
(https://i.postimg.cc/bJ2ZKw9P/Untitled-1.jpg)
-
One on the right is AI. That's my guess? How did I do?
Left one is the AI generated image by DALL E. 😥
(https://i.postimg.cc/bJ2ZKw9P/Untitled-1.jpg)
Nice job. The right one is soft and pixelated, that's why I made that choice. :) The AI version has some more even lighting. Of course the test is someone biased as you got to pick the bad real photo, but point made.
-
That's so exciting! They don't need photographers anymore.
-
That's so exciting! They don't need photographers anymore.
And buyers do not need stock agencies anymore ;)
-
Published today in a pro-Dalle-E online news article
Quote
Bad news for stock photo businesses
If you’re a stock photo business, DALL-E 2 might be your worst enemy. Stock photos already have a reputation as cheesy and inauthentic, but have been a necessary evil for content creators. That changes the moment DALL-E 2 becomes available for commercial use.
What justification would there be to pay for a stock photo license in a world where DALL-E 2 can create any image you want?
-
Published today in a pro-Dalle-E online news article
Quote
Bad news for stock photo businesses
If you’re a stock photo business, DALL-E 2 might be your worst enemy. Stock photos already have a reputation as cheesy and inauthentic, but have been a necessary evil for content creators. That changes the moment DALL-E 2 becomes available for commercial use.
What justification would there be to pay for a stock photo license in a world where DALL-E 2 can create any image you want?
DALL-E is available now for commercial use. All those illustrations and creations, are allowed to be licensed. What's going to be interesting in the future is, right for images that use portions of people or protected property, designs or specifics. Open AI “Users get full usage rights to commercialise the images they create with DALL-E, including the right to reprint, sell and merchandise,”
What is Fair use? I hope that sometime in the near future the courts will decide.
“There are real concerns with respect to the copyright of outputs from these models and unaddressed rights issues with respect to the imagery, the image metadata and those individuals contained within the imagery,” Getty Images CEO Craig Peters https://www.theverge.com/2022/9/21/23364696/getty-images-ai-ban-generated-artwork-illustration-copyright#:~:text=The%20creators%20of%20AI%20image%20generators%20say%20the,sites%2C%20and%20stock%20photo%20sites%20like%20Getty%20Images. (https://www.theverge.com/2022/9/21/23364696/getty-images-ai-ban-generated-artwork-illustration-copyright#:~:text=The%20creators%20of%20AI%20image%20generators%20say%20the,sites%2C%20and%20stock%20photo%20sites%20like%20Getty%20Images.)
Read this article which is looking at both sides. “I see people on both sides of this extremely confident in their positions, but the reality is nobody knows,” https://www.theverge.com/23444685/generative-ai-copyright-infringement-legal-fair-use-training-data (https://www.theverge.com/23444685/generative-ai-copyright-infringement-legal-fair-use-training-data)
What's interesting is that, lets say I create an image, using AI from one of the online services. If I don't have enough creative input and, the image is not created by a human's work, then it's not going to be protected. In the article they use Cat by Van Gogh as an example of what couldn't be protected. In the US, there is no copyright protection for works generated solely by a machine. However, it seems that copyright may be possible in cases where the creator can prove there was substantial human input.
What is substantial human input? What is a derivative, of substantial new design to change the image "enough" to make it a new work. Very subjective questions.
This is why I posted the Warhol case which is in progress now, that's examining what is fair use. They are both related.
None of this has to do with what's right or fair for artists, creatives or our interests, it's all about the legal side and could someone get sued for using something that AI created by scraping the web or using copyrighted images to train the AI?
-
Published today in a pro-Dalle-E online news article
Quote
Bad news for stock photo businesses
If you’re a stock photo business, DALL-E 2 might be your worst enemy. Stock photos already have a reputation as cheesy and inauthentic, but have been a necessary evil for content creators. That changes the moment DALL-E 2 becomes available for commercial use.
What justification would there be to pay for a stock photo license in a world where DALL-E 2 can create any image you want?
DALL-E is available now for commercial use. All those illustrations and creations, are allowed to be licensed. What's going to be interesting in the future is, right for images that use portions of people or protected property, designs or specifics. Open AI “Users get full usage rights to commercialise the images they create with DALL-E, including the right to reprint, sell and merchandise,”
What is Fair use? I hope that sometime in the near future the courts will decide.
“There are real concerns with respect to the copyright of outputs from these models and unaddressed rights issues with respect to the imagery, the image metadata and those individuals contained within the imagery,” Getty Images CEO Craig Peters https://www.theverge.com/2022/9/21/23364696/getty-images-ai-ban-generated-artwork-illustration-copyright#:~:text=The%20creators%20of%20AI%20image%20generators%20say%20the,sites%2C%20and%20stock%20photo%20sites%20like%20Getty%20Images. (https://www.theverge.com/2022/9/21/23364696/getty-images-ai-ban-generated-artwork-illustration-copyright#:~:text=The%20creators%20of%20AI%20image%20generators%20say%20the,sites%2C%20and%20stock%20photo%20sites%20like%20Getty%20Images.)
Read this article which is looking at both sides. “I see people on both sides of this extremely confident in their positions, but the reality is nobody knows,” https://www.theverge.com/23444685/generative-ai-copyright-infringement-legal-fair-use-training-data (https://www.theverge.com/23444685/generative-ai-copyright-infringement-legal-fair-use-training-data)
What's interesting is that, lets say I create an image, using AI from one of the online services. If I don't have enough creative input and, the image is not created by a human's work, then it's not going to be protected. In the article they use Cat by Van Gogh as an example of what couldn't be protected. In the US, there is no copyright protection for works generated solely by a machine. However, it seems that copyright may be possible in cases where the creator can prove there was substantial human input.
What is substantial human input? What is a derivative, of substantial new design to change the image "enough" to make it a new work. Very subjective questions.
This is why I posted the Warhol case which is in progress now, that's examining what is fair use. They are both related.
None of this has to do with what's right or fair for artists, creatives or our interests, it's all about the legal side and could someone get sued for using something that AI created by scraping the web or using copyrighted images to train the AI?
With many players coming into AI, the companies are now shifting their licenses to commercial.
This is dangerous and I don't see good future of image industry.
-
AI Learning means data is held, just as data is held in the human brain in terms of memory and learning as to what things look like.
The problem for AI data is that there are now laws that require data to only be held for a reasonable length of time, not indefinitely. I think this is why SS talks about being able to opt-out of future dataset refreshes that the AI uses. These datasets are created from stored imagery (ours).
Ultimately, if they let this continue, the software could put many artists and photographers out of business and in turn, drastically reduce the size of datasets available for the AI to... *cough* learn from. It feels like a short term gain process for the AI, which from my dealings with AI is not as fancy as what they like it to sound. It's basically a very large dataset with clever conditional programming. We used to use SaaS and other software to do "Machine Learning" within the financial industry!
-
Published today in a pro-Dalle-E online news article
Quote
Bad news for stock photo businesses
If you’re a stock photo business, DALL-E 2 might be your worst enemy. Stock photos already have a reputation as cheesy and inauthentic, but have been a necessary evil for content creators. That changes the moment DALL-E 2 becomes available for commercial use.
What justification would there be to pay for a stock photo license in a world where DALL-E 2 can create any image you want?
DALL-E is available now for commercial use. All those illustrations and creations, are allowed to be licensed. What's going to be interesting in the future is, right for images that use portions of people or protected property, designs or specifics. Open AI “Users get full usage rights to commercialise the images they create with DALL-E, including the right to reprint, sell and merchandise,”
What is Fair use? I hope that sometime in the near future the courts will decide.
“There are real concerns with respect to the copyright of outputs from these models and unaddressed rights issues with respect to the imagery, the image metadata and those individuals contained within the imagery,” Getty Images CEO Craig Peters https://www.theverge.com/2022/9/21/23364696/getty-images-ai-ban-generated-artwork-illustration-copyright#:~:text=The%20creators%20of%20AI%20image%20generators%20say%20the,sites%2C%20and%20stock%20photo%20sites%20like%20Getty%20Images. (https://www.theverge.com/2022/9/21/23364696/getty-images-ai-ban-generated-artwork-illustration-copyright#:~:text=The%20creators%20of%20AI%20image%20generators%20say%20the,sites%2C%20and%20stock%20photo%20sites%20like%20Getty%20Images.)
Read this article which is looking at both sides. “I see people on both sides of this extremely confident in their positions, but the reality is nobody knows,” https://www.theverge.com/23444685/generative-ai-copyright-infringement-legal-fair-use-training-data (https://www.theverge.com/23444685/generative-ai-copyright-infringement-legal-fair-use-training-data)
What's interesting is that, lets say I create an image, using AI from one of the online services. If I don't have enough creative input and, the image is not created by a human's work, then it's not going to be protected. In the article they use Cat by Van Gogh as an example of what couldn't be protected. In the US, there is no copyright protection for works generated solely by a machine. However, it seems that copyright may be possible in cases where the creator can prove there was substantial human input.
What is substantial human input? What is a derivative, of substantial new design to change the image "enough" to make it a new work. Very subjective questions.
This is why I posted the Warhol case which is in progress now, that's examining what is fair use. They are both related.
None of this has to do with what's right or fair for artists, creatives or our interests, it's all about the legal side and could someone get sued for using something that AI created by scraping the web or using copyrighted images to train the AI?
With many players coming into AI, the companies are now shifting their licenses to commercial.
This is dangerous and I don't see good future of image industry.
Well said in many less words.
-
Lets say I used to make $100 a month on a specific agency and now I make $10 a month there. And another the same, only it's now $5 a month. I averaged $80 RPD for some years on another, now I get $8.71 RPD with more images?
If you hang someone, and then shoot the corpse, does that make them more dead? Killing an already dead industry won't be making it any worse by AI entering the market. You can't stop progress or technology just because it doesn't fit our own goals or plans for the future.
(https://i.postimg.cc/CLxs22Vg/beatdeadhorse.gif)
"...grant me the serenity to accept the things I cannot change, the courage to change the things I can, and the wisdom to know the difference."
However if you are a supreme court justice, one of the nine people who could make a difference, and reading this, you could help protect the artists rights and interests. The rest of us 332 Million other people have almost no power to make a change. That's just in the USA.
-
AI images are just ugly
-
Lets say I used to make $100 a month on a specific agency and now I make $10 a month there. And another the same, only it's now $5 a month. I averaged $80 RPD for some years on another, now I get $8.71 RPD with more images?
If you hang someone, and then shoot the corpse, does that make them more dead? Killing an already dead industry won't be making it any worse by AI entering the market. You can't stop progress or technology just because it doesn't fit our own goals or plans for the future.
And let's say I used to make $100 a month there and now I make $1000? What then?
Microstock is not dead for everyone. Some people are still making decent money there, some even rely on it for their living.
No, we can't stop progressing trechnology that might destroy our livelihood. But it doesn't mean we have to like it or even cheer it on or keep silent about our disapproval.
-
AI images are just ugly
use a good prompt and the ugly will become beautiful.
-
Lets say I used to make $100 a month on a specific agency and now I make $10 a month there. And another the same, only it's now $5 a month. I averaged $80 RPD for some years on another, now I get $8.71 RPD with more images?
If you hang someone, and then shoot the corpse, does that make them more dead? Killing an already dead industry won't be making it any worse by AI entering the market. You can't stop progress or technology just because it doesn't fit our own goals or plans for the future.
And let's say I used to make $100 a month there and now I make $1000? What then?
Microstock is not dead for everyone. Some people are still making decent money there, some even rely on it for their living.
No, we can't stop progressing trechnology that might destroy our livelihood. But it doesn't mean we have to like it or even cheer it on or keep silent about our disapproval.
I know you're lookin' for a ruby in a mountain of rocks
But there ain't no Coupe de Ville
Hidin' at the bottom of a Cracker Jack box
Lets say your disapproval is useless and changes nothing. Then what?
-
I know you're lookin' for a ruby in a mountain of rocks
But there ain't no Coupe de Ville
Hidin' at the bottom of a Cracker Jack box
Lets say your disapproval is useless and changes nothing. Then what?
Don't understand the ruby and ville and jack stuff. Guess my English isn't good enough, I don't know what half of that is.
So, you are saying we are not supposed to talk about anything we don't like we can't change anything about? The Russian war? Explosing gas prices? Inflation? Soccer world cup in Katar?
Communication is a way to express our thoughts and feelings. It’s a basic human need that helps us connect and interact with others. It's helps us form our identity and perceive the world as we want others to see it. It helps us express our emotions and emotional expression is a key to our mental health. It helps relieve stress.
Through communication, we evolve as individuals in society. Through it we become informed and make well thought out decisions. It helps us develop our own ideas and express ourselves. It creates the foundation for understanding between people and helps us develop respect and empathy.
There are a million reasons why we talk about things, even though talking about them doesn't change anything about these things.
If you do not feel the need, then that's okay. But don't question other's peoples' motives for wanting to express their thoughts and feelings, regardless of whether it'S something positive or negative or something they can change or not.
-
AI images are just ugly
Hmm this is what my friend told me around 20 years ago about digital images.She works in photo lab... photo lab almost do not exist this days
-
Computers have been putting people out of business for a long. Machines have been putting people out of business for a long time. How many painters were put out of business by the camera?
The microstock business was created by digital cameras and computers. It put the old stock photo guys out of business.
How will all this play out? Will people still pay for the best images, and give SS a way to stay in business? Or will all images be free from now on?
What I most want to know is: How long before AI can make vectors?
-
...
The microstock business was created by digital cameras and computers. It put the old stock photo guys out of business.
no - many of us old stock guys (since 1976) made the transition. evolution in action
How will all this play out? Will people still pay for the best images...
why assume digital cameras will always produce 'better' than AI?
-
...
The microstock business was created by digital cameras and computers. It put the old stock photo guys out of business.
no - many of us old stock guys (since 1976) made the transition. evolution in action
How will all this play out? Will people still pay for the best images...
why assume digital cameras will always produce 'better' than AI?
Because I'm behind that camera and I'm real, not artificial? 8)
AI created images do have a place. I still see them doing some impossible things that real photos won't. Look at what CGI has done for movies. They also have AI screen writers to help with the script. This isn't an attack on photography and stock, the whole world is being advanced by AI assistance. Sure, that also means some people will not be needed, as computers fill in gaps and positions.
Robotics have taken over in manufacturing. Those real life workers have been replaced.
Biden said “Anybody who can go down 3,000 feet in a mine can sure as hell learn to program as well… Anybody who can throw coal into a furnace can learn how to program, for God’s sake!” :o So anyone who can push a button or edit a photo can learn some new tricks too? The Prez says so.
-
...
The microstock business was created by digital cameras and computers. It put the old stock photo guys out of business.
no - many of us old stock guys (since 1976) made the transition. evolution in action
How will all this play out? Will people still pay for the best images...
why assume digital cameras will always produce 'better' than AI?
Because I'm behind that camera and I'm real, not artificial? 8)
AI created images do have a place. I still see them doing some impossible things that real photos won't. Look at what CGI has done for movies. They also have AI screen writers to help with the script. This isn't an attack on photography and stock, the whole world is being advanced by AI assistance. Sure, that also means some people will not be needed, as computers fill in gaps and positions.
Robotics have taken over in manufacturing. Those real life workers have been replaced.
Biden said “Anybody who can go down 3,000 feet in a mine can sure as hell learn to program as well… Anybody who can throw coal into a furnace can learn how to program, for God’s sake!” :o So anyone who can push a button or edit a photo can learn some new tricks too? The Prez says so.
That's why presidents have the ultimate wisdom and we have not :) :) :)
-
Biden said “Anybody who can go down 3,000 feet in a mine can sure as hell learn to program as well… Anybody who can throw coal into a furnace can learn how to program, for God’s sake!” :o So anyone who can push a button or edit a photo can learn some new tricks too? The Prez says so.
That's why presidents have the ultimate wisdom and we have not :) :) :)
Yes, the current one and the last one.
Just amazing, as that's who's the figurehead that runs the country? Actually for anyone who has been in a club or on a board, the President presides and can't even make a motion. (Presidents don't write laws) He rules and is supposed to maintain control. "The chief administrative duty of the president is to represent the organization. The president signs all legal documents; supervises the employees and the activities of the organization; represents, or speaks for, the organization; and presides at meetings." That and commander in chief of the military.
-
So it all started now.
https://pixelvibe.com/
-
So it all started now.
https://pixelvibe.com/
Hey there 👋
Welcome to PixelVibe 🙌
We're building the world's best collection of AI stock photos and videos.
If you have any questions, just reply to this message.
Max
Yeah, please drop dead PixelVibe. I can't see any benefit of buying a license for an AI image over a real one, and I mean the ones they have?
-
Re: Artificial Intelligence killing the whole industry = Maybe Not Yet?
SSTK:
Why was my content rejected as Non-Licensable Content?
Content cannot be licensed due to legal restrictions
If your content was rejected as “Non-Licensable Content,” it is because we cannot license this content in our collection due to legal compliance restrictions. This type of restricted content cannot be published for either commercial or editorial use therefore it is considered “non-licensable.”
Restrictions could include, but are not limited to, the following subjects:
...
Appears to have been created with AI-generative technology
Why can’t I claim copyright to AI-generated content if I am the one who produced the query that generated the synthetic content?
Because AI content generation models leverage the IP of many artists and their content, AI-generated content ownership cannot be assigned to an individual. Per our Contributor Terms of Service (Sections 13d and 13f), contributors must have proven IP ownership of all content that is submitted. As such, AI-generated content should not be submitted to Shutterstock.
Getty / iStock:
Getty Images does not accept files created using AI generative models. There are open questions with respect to the copyright of outputs from these models and there are unaddressed rights issues with respect to the underlying imagery and metadata used to train these models. Please see https://contributors.gettyimages.com/article/9685 for more information.
AI Generated Content
Wednesday September 21, 2022
Effectively immediately, Getty Images will cease to accept all submissions created using AI generative models (e.g., Stable Diffusion, Dall-E 2, MidJourney, etc.) and prior submissions utilizing such models will be removed.
-
That just means we can't sell it. Several of the agencies have deals to put AI generators on the sites themselves, and I would think also add AI generated work to the collection.
-
Re: Artificial Intelligence killing the whole industry = Maybe Not Yet?
SSTK:
Why was my content rejected as Non-Licensable Content?
Content cannot be licensed due to legal restrictions
If your content was rejected as “Non-Licensable Content,” it is because we cannot license this content in our collection due to legal compliance restrictions. This type of restricted content cannot be published for either commercial or editorial use therefore it is considered “non-licensable.”
Restrictions could include, but are not limited to, the following subjects:
...
Appears to have been created with AI-generative technology
Why can’t I claim copyright to AI-generated content if I am the one who produced the query that generated the synthetic content?
Because AI content generation models leverage the IP of many artists and their content, AI-generated content ownership cannot be assigned to an individual. Per our Contributor Terms of Service (Sections 13d and 13f), contributors must have proven IP ownership of all content that is submitted. As such, AI-generated content should not be submitted to Shutterstock.
Getty / iStock:
Getty Images does not accept files created using AI generative models. There are open questions with respect to the copyright of outputs from these models and there are unaddressed rights issues with respect to the underlying imagery and metadata used to train these models. Please see https://contributors.gettyimages.com/article/9685 for more information.
AI Generated Content
Wednesday September 21, 2022
Effectively immediately, Getty Images will cease to accept all submissions created using AI generative models (e.g., Stable Diffusion, Dall-E 2, MidJourney, etc.) and prior submissions utilizing such models will be removed.
Doesn't matter, there are many portfolios smoothly submitting AI content. There is no way for agencies to track whether the content is AI or not. And even AI cannot tell difference between digitally created and digitally generated images.
-
Doesn't matter, there are many portfolios smoothly submitting AI content. There is no way for agencies to track whether the content is AI or not. And even AI cannot tell difference between digitally created and digitally generated images.
That's a fact, but at least there are some that are not allowing the flood.
That just means we can't sell it. Several of the agencies have deals to put AI generators on the sites themselves, and I would think also add AI generated work to the collection.
While also true, it seems a contradiction to the claimed reasons why we can't upload AI created images?
"Because AI content generation models leverage the IP of many artists and their content, AI-generated content ownership cannot be assigned to an individual. Per our Contributor Terms of Service (Sections 13d and 13f), contributors must have proven IP ownership of all content that is submitted. As such, AI-generated content should not be submitted to Shutterstock."
We'll have to wait and see how this turns out. But for the half empty, doomed people, with a perpetual black storm over their head, and who never stop finding what's wrong, their mind is made up, "Artificial Intelligence (is) killing the whole industry".
Nope, just killing our income from the industry. Just like my allusion that Microstock is already dead, that's really just for some artists. AI will replace some of us and make some of our images less valuable, but AI will not kill the whole industry.
-
Doesn't matter, there are many portfolios smoothly submitting AI content. There is no way for agencies to track whether the content is AI or not. And even AI cannot tell difference between digitally created and digitally generated images.
That's a fact, but at least there are some that are not allowing the flood.
That just means we can't sell it. Several of the agencies have deals to put AI generators on the sites themselves, and I would think also add AI generated work to the collection.
While also true, it seems a contradiction to the claimed reasons why we can't upload AI created images?
"Because AI content generation models leverage the IP of many artists and their content, AI-generated content ownership cannot be assigned to an individual. Per our Contributor Terms of Service (Sections 13d and 13f), contributors must have proven IP ownership of all content that is submitted. As such, AI-generated content should not be submitted to Shutterstock."
We'll have to wait and see how this turns out. But for the half empty, doomed people, with a perpetual black storm over their head, and who never stop finding what's wrong, their mind is made up, "Artificial Intelligence (is) killing the whole industry".
Nope, just killing our income from the industry. Just like my allusion that Microstock is already dead, that's really just for some artists. AI will replace some of us and make some of our images less valuable, but AI will not kill the whole industry.
Some agency deals mean the AI company will use the agency's collection to train the AI. I am sure terms will be updated soon to say we agree to it if we want to sell through the agency.
-
Doesn't matter, there are many portfolios smoothly submitting AI content. There is no way for agencies to track whether the content is AI or not. And even AI cannot tell difference between digitally created and digitally generated images.
That's a fact, but at least there are some that are not allowing the flood.
That just means we can't sell it. Several of the agencies have deals to put AI generators on the sites themselves, and I would think also add AI generated work to the collection.
While also true, it seems a contradiction to the claimed reasons why we can't upload AI created images?
"Because AI content generation models leverage the IP of many artists and their content, AI-generated content ownership cannot be assigned to an individual. Per our Contributor Terms of Service (Sections 13d and 13f), contributors must have proven IP ownership of all content that is submitted. As such, AI-generated content should not be submitted to Shutterstock."
We'll have to wait and see how this turns out. But for the half empty, doomed people, with a perpetual black storm over their head, and who never stop finding what's wrong, their mind is made up, "Artificial Intelligence (is) killing the whole industry".
Nope, just killing our income from the industry. Just like my allusion that Microstock is already dead, that's really just for some artists. AI will replace some of us and make some of our images less valuable, but AI will not kill the whole industry.
Some agency deals mean the AI company will use the agency's collection to train the AI. I am sure terms will be updated soon to say we agree to it if we want to sell through the agency.
Yes and that way, they own the images and control the output and eliminate us. All very possible.
This needs to be decided in the courts before anyone is going to go into Open AI big. I don't see how using all PD and scraped images or paying pennies to an agency for a selection, makes anything infringing? And back to the use argument, where we get paid for allowing our images to train AI, where do they send those pennies?
There's no money in that for us and no way to track use. There are better battles to be fought.
-
I do not think it has to be so bad as it seems. I think our role will change from artists to providers of training images. I tried to elaborate more about the topic at https://artmino.com/shutterstock-and-ai-is-it-a-really-bad-deal/ (https://artmino.com/shutterstock-and-ai-is-it-a-really-bad-deal/)
-
Clients won't even need agencies, today they can get a certain number of AI-produced images for free directly from the software creators, I won't say where so as not to give them free publicity. The company I work for is considering not renewing the subscription they get every year from an agency we all know, to generate and download the images they need for free directly from the mentioned website.
The days are counted both for the agencies and for the contributors.
-
Doesn't matter, there are many portfolios smoothly submitting AI content. There is no way for agencies to track whether the content is AI or not. And even AI cannot tell difference between digitally created and digitally generated images.
That's a fact, but at least there are some that are not allowing the flood.
No allowing on their terms sheet, but people are clever and are bypassing the same rule.
But I agree, the companies wants to restrict the same.
-
Clients won't even need agencies, today they can get a certain number of AI-produced images for free directly from the software creators, I won't say where so as not to give them free publicity. The company I work for is considering not renewing the subscription they get every year from an agency we all know, to generate and download the images they need for free directly from the mentioned website.
The days are counted both for the agencies and for the contributors.
The company you work for, must have pretty low standards for their image needs, if they can use images created by Open-AI or the rest. None I've ever seen, are good enough as stock, without editing and adjusting or filling in missing parts.
McDonald's is not putting any steak house out of business, but they both sell beef.
-
I do not think it has to be so bad as it seems. I think our role will change from artists to providers of training images. I tried to elaborate more about the topic at https://artmino.com/shutterstock-and-ai-is-it-a-really-bad-deal/ (https://artmino.com/shutterstock-and-ai-is-it-a-really-bad-deal/)
Just a hypothetical of your hypothetical. What if the training use is a one time payment or maybe we get nothing at all, for the training. But mostly who says we would be paid for every use of every image that was used to train the AI. Why?
And that's assuming that we get any image selected to be part of the dataset. 360 million images, no one will need to license all of them.
It's one use, from a giant, low cost, subscription, to train the AI. What if they paid us the dime standard, which is supposed to be the minimum. That's it. One dime, one use.
-
What if the training use is a one time payment or maybe we get nothing at all, for the training. But mostly who says we would be paid for every use of every image that was used to train the AI. Why?
And that's assuming that we get any image selected to be part of the dataset. 360 million images, no one will need to license all of them.
It's one use, from a giant, low cost, subscription, to train the AI. What if they paid us the dime standard, which is supposed to be the minimum. That's it. One dime, one use.
"But mostly who says we would be paid for every use of every image that was used to train the AI. Why?"
Shutterstock says that, citing: "Contributors whose content was used to train either model will be compensated for the role their IP played in the development of the original models, as well as through royalty payments tied to future generative licensing activity." or "Earnings from datasets and downloads of AI-generated content produced with integrated technology on our platform are pooled in a collective fund and will be distributed every 6 months." Why? It is obvious. All the other stock agencies are forbidding AI-generated images because they cannot say the training images were properly sourced and properly compensate them. SS can do that as it know the source and authors of the images. It provides them itself.
There are two different situations here. One is training the AI for other projects. This will be probably one time payment. The second one is AI generation based on our images. And this is "generative licensing activity" which should lead to royalty payments. I understand that we are going to be paid for every generaion of AI image where the AI was trained by our image.
"360 million images, no one will need to license all of them."
The quality of AI is extremely dependent on the size of training dataset. Extremely. It is not only about the quality of the algorithm but also about the quality (size) of dataset. How would you make better AI. You will put more data to that (in our case, more images). Of course, not all of them have to be chosen, but this is how the AI works. More data = usually better AI.
-
What if the training use is a one time payment or maybe we get nothing at all, for the training. But mostly who says we would be paid for every use of every image that was used to train the AI. Why?
And that's assuming that we get any image selected to be part of the dataset. 360 million images, no one will need to license all of them.
It's one use, from a giant, low cost, subscription, to train the AI. What if they paid us the dime standard, which is supposed to be the minimum. That's it. One dime, one use.
"But mostly who says we would be paid for every use of every image that was used to train the AI. Why?"
Shutterstock says that, citing: "Contributors whose content was used to train either model will be compensated for the role their IP played in the development of the original models, as well as through royalty payments tied to future generative licensing activity." or "Earnings from datasets and downloads of AI-generated content produced with integrated technology on our platform are pooled in a collective fund and will be distributed every 6 months." Why? It is obvious. All the other stock agencies are forbidding AI-generated images because they cannot say the training images were properly sourced and properly compensate them. SS can do that as it know the source and authors of the images. It provides them itself.
There are two different situations here. One is training the AI for other projects. This will be probably one time payment. The second one is AI generation based on our images. And this is "generative licensing activity" which should lead to royalty payments. I understand that we are going to be paid for every generaion of AI image where the AI was trained by our image.
"360 million images, no one will need to license all of them."
The quality of AI is extremely dependent on the size of training dataset. Extremely. It is not only about the quality of the algorithm but also about the quality (size) of dataset. How would you make better AI. You will put more data to that (in our case, more images). Of course, not all of them have to be chosen, but this is how the AI works. More data = usually better AI.
True and yes I read that when it was originally issued. I'm still skeptical about how much we will get. I don't know how this translates in money for anyone, from the first sets used? "as well as through royalty payments tied to future generative licensing activity" future generative licensing activity ?
Maybe you're right and that would be nice. This looks like something that honestly doesn't say much and in some ways is mixed, not specific. "Earnings from datasets and downloads of AI-generated content produced with integrated technology on our platform are pooled in a collective fund and will be distributed every 6 months."
Datasets and Downloads pooled and distributed. This is going to be pretty complicated. Let me just say on a very base level, every image used for the dataset is one kind of credit, and every download, using the AI is another.
I have 5000 images, that's 0.00001389 of the entire collection. Is that my fair share of the collective fund every six months. ;D
DALL-E2 charges 13c a credit, that's 13c an image. At 15% (my guess) that's going to be about 2 cents a download into the shared revenue. One could argue that with the volume of potential downloads, that could add up to a nice sum. Divided by active contributors? Size of portfolio? Quite a mystery how this will happen.
I won't say you're wrong, but from past experience, I'm not thinking this will be some kind of windfall for contributors.
-
I won't say you're wrong, but from past experience, I'm not thinking this will be some kind of windfall for contributors.
I do not expect it either. What I wanted to highlight is the fact that a contributor should be eligible for a commision every time when the image created with that topic is sold. I expect more stable income (not necessarily larger income though).
-
What I most want to know is: How long before AI can make vectors?
Faster than video and photo. A vector is just a conceptual drawing or diagram. It is easy for a computer to convert any drawing or photo into vector format. Yes, now perhaps such programs do not work very well, but this is a matter of a short time. The vector workers will go bankrupt first.
-
The company you work for, must have pretty low standards for their image needs, if they can use images created by Open-AI or the rest. None I've ever seen, are good enough as stock, without editing and adjusting or filling in missing parts.
McDonald's is not putting any steak house out of business, but they both sell beef.
[/quote]
I am pretty sure when McDonalds flood over the world from 1953 on, it took out tens of thousands restaurants especially steak houses. What you are talking about is that they NOW coexist, with a highly reduced number of steak houses.
-
McDonalds
McDonalds is not a popular restaurant in the US. Few people go there. There are many other chains where people go and where it tastes better. The quality that McDonalds offers is not suitable for Americans. Yes, McDonalds is popular in Europe, but not in the US.
-
McDonalds
McDonalds is not a popular restaurant in the US. Few people go there. There are many other chains where people go and where it tastes better. The quality that McDonalds offers is not suitable for Americans. Yes, McDonalds is popular in Europe, but not in the US.
you just have to look up the number 1 restaurant chain in the US. Good try though lol
-
McDonalds
McDonalds is not a popular restaurant in the US. Few people go there. There are many other chains where people go and where it tastes better. The quality that McDonalds offers is not suitable for Americans. Yes, McDonalds is popular in Europe, but not in the US.
you just have to look up the number 1 restaurant chain in the US. Good try though lol
Why should I look, I was there, I lived there, I saw everything with my own eyes. And I repeat, at McDonalds in the USA, food is much worse than in other similar restaurants.
-
You were in every store simultaneously, all day, every day? Unlikely. Anyway, I wouldn't class 8.71 billion dollars in revenue as 'not popular'.
-
McDonalds
McDonalds is not a popular restaurant in the US. Few people go there. There are many other chains where people go and where it tastes better. The quality that McDonalds offers is not suitable for Americans. Yes, McDonalds is popular in Europe, but not in the US.
you just have to look up the number 1 restaurant chain in the US. Good try though lol
Why should I look, I was there, I lived there, I saw everything with my own eyes. And I repeat, at McDonalds in the USA, food is much worse than in other similar restaurants.
OK, sure facts don't matter. For example that the chain that you described as unpopular is the number 1 restaurant chain in the US. But ramble on my dude.
-
McDonalds
McDonalds is not a popular restaurant in the US. Few people go there. There are many other chains where people go and where it tastes better. The quality that McDonalds offers is not suitable for Americans. Yes, McDonalds is popular in Europe, but not in the US.
you just have to look up the number 1 restaurant chain in the US. Good try though lol
Why should I look, I was there, I lived there, I saw everything with my own eyes. And I repeat, at McDonalds in the USA, food is much worse than in other similar restaurants.
And do you have to contribute anything to the real discussion here? You derailed it with hilariously wrong facts and your personal opinion about fast food... Good job.
-
I am pretty sure when McDonalds flood over the world from 1953 on, it took out tens of thousands restaurants especially steak houses. What you are talking about is that they NOW coexist, with a highly reduced number of steak houses.
Different markets. Sure the hamburger joints and cafes or lunch counters got mostly eliminated by fast food and drive through restaurants. But the good sit down restaurants didn't lose out to someplace where Mom's take the kids for a fast lunch or someone on the road, grabs something. Different quality and different markets.
I said:
The company you work for, must have pretty low standards for their image needs, if they can use images created by Open-AI or the rest. None I've ever seen, are good enough as stock, without editing and adjusting or filling in missing parts.
And the reasoning wasn't to insult your company, but to point out that AI images are not good enough yet, to replace agency subscriptions. Maybe for fast food, burgers and fries, but not for quality meals, steaks and baked potatoes? :) If someone has to work to fix and repair the AI images, that is not efficient use of time, and it will cost more to work that way.
-
McDonalds
McDonalds is not a popular restaurant in the US. Few people go there. There are many other chains where people go and where it tastes better. The quality that McDonalds offers is not suitable for Americans. Yes, McDonalds is popular in Europe, but not in the US.
you just have to look up the number 1 restaurant chain in the US. Good try though lol
Why should I look, I was there, I lived there, I saw everything with my own eyes. And I repeat, at McDonalds in the USA, food is much worse than in other similar restaurants.
OK, sure facts don't matter. For example that the chain that you described as unpopular is the number 1 restaurant chain in the US. But ramble on my dude.
"McDonald's has a consumer rating of 2.4 stars from 295 reviews indicating that most customers are generally dissatisfied with their purchases. Consumers complaining about McDonald's most frequently mention customer service, quarter pounder and ice cream problems."
https://www.sitejabber.com/reviews/mcdonalds.com#:~:text=McDonald's%20has%20a%20consumer%20rating,ranks%204th%20among%20Restaurants%20sites. (https://www.sitejabber.com/reviews/mcdonalds.com#:~:text=McDonald's%20has%20a%20consumer%20rating,ranks%204th%20among%20Restaurants%20sites.)
-
McDonalds
McDonalds is not a popular restaurant in the US. Few people go there. There are many other chains where people go and where it tastes better. The quality that McDonalds offers is not suitable for Americans. Yes, McDonalds is popular in Europe, but not in the US.
you just have to look up the number 1 restaurant chain in the US. Good try though lol
Why should I look, I was there, I lived there, I saw everything with my own eyes. And I repeat, at McDonalds in the USA, food is much worse than in other similar restaurants.
OK, sure facts don't matter. For example that the chain that you described as unpopular is the number 1 restaurant chain in the US. But ramble on my dude.
"McDonald's has a consumer rating of 2.4 stars from 295 reviews indicating that most customers are generally dissatisfied with their purchases. Consumers complaining about McDonald's most frequently mention customer service, quarter pounder and ice cream problems."
https://www.sitejabber.com/reviews/mcdonalds.com#:~:text=McDonald's%20has%20a%20consumer%20rating,ranks%204th%20among%20Restaurants%20sites. (https://www.sitejabber.com/reviews/mcdonalds.com#:~:text=McDonald's%20has%20a%20consumer%20rating,ranks%204th%20among%20Restaurants%20sites.)
Yes it's so unpopular that: McDonald's, the most successful fast food chain on Earth, also reigns supreme in the U.S., with $39.5 billion in overall sales last year.
Of course you may be on a different planet?
-
Of course you may be on a different planet?
That might solve the mystery of a lot of his statements on this forum.
-
It may say 2.4 out of 5, but did you notice that its says it's also ranked 4th out of all the restaurants on that site? And nobody was talking about their consumer rating anyway, you're just bringing it up as you've been called out, once again, for being wrong... so you're probably trying to save face. You said they weren't popular and few people go there, which is blatantly false no matter whether they have 5 stars, 2.4 stars or 0 stars.
-
I like McDonald's :P
-
I am pretty sure when McDonalds flood over the world from 1953 on, it took out tens of thousands restaurants especially steak houses. What you are talking about is that they NOW coexist, with a highly reduced number of steak houses.
Different markets. Sure the hamburger joints and cafes or lunch counters got mostly eliminated by fast food and drive through restaurants. But the good sit down restaurants didn't lose out to someplace where Mom's take the kids for a fast lunch or someone on the road, grabs something. Different quality and different markets.
I said:
The company you work for, must have pretty low standards for their image needs, if they can use images created by Open-AI or the rest. None I've ever seen, are good enough as stock, without editing and adjusting or filling in missing parts.
And the reasoning wasn't to insult your company, but to point out that AI images are not good enough yet, to replace agency subscriptions. Maybe for fast food, burgers and fries, but not for quality meals, steaks and baked potatoes? :) If someone has to work to fix and repair the AI images, that is not efficient use of time, and it will cost more to work that way.
Yeah different markets now, but the fast food market didn't existed before 53, so many opted for steakhouses for their meat cravings. But when McDonald's entered the market they had a cheaper and faster option and that killed a lot of business for the traditional restaurants.
Obviously they are different markets now because they both exist now. Ai didn't exist a few years ago but it does now and the progress they are making is breathtaking.
Did you check recently? Here's an Adobe link:
https://stock.adobe.com/search?k=AI+generated+woman&search_type=usertyped
It honestly gives me cold shivers seeing the artwork that comes out of the AI. Looking at the illustrations at least the machine is the superior steak to 99% humans already and faster and cheaper on top it.
-
... What I wanted to highlight is the fact that a contributor should be eligible for a commision every time when the image created with that topic is sold. ...
how would you decide from the generator phrase which images among millions were used in the training set? eg "penguin in a top hat walking on mars'
once training is done, no images are actually accessed during the creation of AI images
-
... What I wanted to highlight is the fact that a contributor should be eligible for a commision every time when the image created with that topic is sold. ...
how would you decide from the generator phrase which images among millions were used in the training set? eg "penguin in a top hat walking on mars'
once training is done, no images are actually accessed during the creation of AI images
Yeah we all get inspired, just because I took inspiration from photo x doesn't mean that my new work has to pay royalties to photo x. They obviously not gonna share royalties with us.
-
Did you check recently? Here's an Adobe link:
https://stock.adobe.com/search?k=AI+generated+woman&search_type=usertyped
It honestly gives me cold shivers seeing the artwork that comes out of the AI. Looking at the illustrations at least the machine is the superior steak to 99% humans already and faster and cheaper on top it.
By your link I found this video in the AI section. I strongly doubt that this video was created by AI.
https://stock.adobe.com/ua/video/4k-business-woman-putting-smartphone-on-wireless-charger/217765671?prev_url=detail
As for the drawings, they have nothing to do with photographers and videographers. But it's time for vector people to pack their bags for the exit.
-
... What I wanted to highlight is the fact that a contributor should be eligible for a commision every time when the image created with that topic is sold. ...
how would you decide from the generator phrase which images among millions were used in the training set? eg "penguin in a top hat walking on mars'
once training is done, no images are actually accessed during the creation of AI images
Yeah we all get inspired, just because I took inspiration from photo x doesn't mean that my new work has to pay royalties to photo x. They obviously not gonna share royalties with us.
AI isn't getting inspired. It doesn't think.
-
AI isn't getting inspired. It doesn't think.
The question is moot.
-
AI isn't getting inspired. It doesn't think.
The question is moot.
Like a cow?
-
AI isn't getting inspired. It doesn't think.
The question is moot.
That wasn't a question.
-
AI isn't getting inspired. It doesn't think.
The question is moot.
Like a cow?
What's with the cow. >:(
-
AI isn't getting inspired. It doesn't think.
The question is moot.
Like a cow?
What's with the cow. >:(
;D ;D ;D ;D
How to build a surreal dialogue ;D
-
AI isn't getting inspired. It doesn't think.
The question is moot.
Like a cow?
What's with the cow. >:(
It's like a cow's opinion. It doesn't matter. It's moo!
(Joey Tribbiani)
https://www.youtube.com/watch?v=fLwYpSCrlHU (https://www.youtube.com/watch?v=fLwYpSCrlHU)
-
AI isn't getting inspired. It doesn't think.
The question is moot.
Like a cow?
What's with the cow. >:(
It's like a cow's opinion. It doesn't matter. It's moo!
(Joey Tribbiani)
https://www.youtube.com/watch?v=fLwYpSCrlHU (https://www.youtube.com/watch?v=fLwYpSCrlHU)
This is the level of troll reasoning.
-
This is the level of troll reasoning.
No, bovine reasoning. Troll reasoning is interminable and more like "How do you cook thirteen Dwarves and a hobbit"
-
... What I wanted to highlight is the fact that a contributor should be eligible for a commision every time when the image created with that topic is sold. ...
how would you decide from the generator phrase which images among millions were used in the training set? eg "penguin in a top hat walking on mars'
once training is done, no images are actually accessed during the creation of AI images
That is a good question. You know what you have used for training each type of object (downloaded and fed to AI training system). I would assume it is going to be connected with keywords and training sets for them.
-
AI isn't getting inspired. It doesn't think.
The question is moot.
Like a cow?
What's with the cow. >:(
;D ;D ;D ;D
How to build a surreal dialogue ;D
Well you spotted that one right?
(https://i.postimg.cc/ZRzkv87Q/cowlogo.gif)
-
That is a good question. You know what you have used for training each type of object (downloaded and fed to AI training system). I would assume it is going to be connected with keywords and training sets for them.
ML doesnt train for specific objects. for generic ai generators we've been discussing, there's only 1 dataset and the original images are not stored
there are other ML apps that are much more specific (but not for art) - eg medical apps
-
This is the level of troll reasoning.
No, bovine reasoning. Troll reasoning is interminable and more like "How do you cook thirteen Dwarves and a hobbit"
Dude, you wrote complete nonsense. You have no idea about artificial intelligence, how it works and what its prospects are. You are nobody, and there is no way to call you. And all your arguments came down only to offending members of the forum. When there are no arguments, they start with an insult, it's about you.
-
Just seen this, could be useful for finding images that have been used to train AI. Not sure I would want to upload, unless it can use low res, or watermarked images.
https://haveibeentrained.com/
-
-
-
https://news.yahoo.com/ai-created-artwork-sparks-copyright-023727771.html?fr=yhssrp_catchall
In the news, still up for debate.
Just seen this, could be useful for finding images that have been used to train AI. Not sure I would want to upload, unless it can use low res, or watermarked images.
https://haveibeentrained.com/
That's what I was looking for this morning. LAION-5B, an open, publically available dataset of 5.8B image-text pairs and validate it by reproducing results of training state-of-the-art CLIP models of different scale.
https://laion.ai/blog/laion-5b/
"We distribute the metadata dataset (the parquet files) under the Creative Common CC-BY 4.0 license, which poses no particular restriction. The images are under their copyright."
-
https://news.yahoo.com/ai-created-artwork-sparks-copyright-023727771.html?fr=yhssrp_catchall
In the news, still up for debate.
Just seen this, could be useful for finding images that have been used to train AI. Not sure I would want to upload, unless it can use low res, or watermarked images.
https://haveibeentrained.com/
That's what I was looking for this morning. LAION-5B, an open, publically available dataset of 5.8B image-text pairs and validate it by reproducing results of training state-of-the-art CLIP models of different scale.
https://laion.ai/blog/laion-5b/
"We distribute the metadata dataset (the parquet files) under the Creative Common CC-BY 4.0 license, which poses no particular restriction. The images are under their copyright."
completely false - CC license specifically says credit must be given to the creator among SEVERAL other restrictions
AND images they use need to be under CC license themselves (unlikely for billions of images) or similar where owner grants such permission while retaining the copyright
"Adapted Material means material subject to Copyright and Similar Rights that is derived from or based upon the Licensed Material and in which the Licensed Material is translated, altered, arranged, transformed, or otherwise modified in a manner requiring permission under the Copyright and Similar Rights held by the Licensor. For purposes of this Public License, where the Licensed Material is a musical work, performance, or sound recording, Adapted Material is always produced where the Licensed Material is synched in timed relation with a moving image."
https://creativecommons.org/licenses/by/4.0/legalcode (https://creativecommons.org/licenses/by/4.0/legalcode)
finally they haven't made any changes, just made a compilation.
and they are required to credit the licensor for each image:
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
Attribution.
If You Share the Licensed Material (including in modified form), You must:
retain the following if it is supplied by the Licensor with the Licensed Material:
identification of the creator(s) of the Licensed Material and any others designated to receive attribution, in any reasonable manner requested by the Licensor (including by pseudonym if designated)
- a copyright notice;
- a notice that refers to this Public License;
- a notice that refers to the disclaimer of warranties;
- a URI or hyperlink to the Licensed Material to the extent reasonably practicable;
- indicate if You modified the Licensed Material and retain an indication of any previous modifications;
- indicate the License
listed Material is licensed under this Public License, and include the text of, or the URI or hyperlink to, this Public License.[/color]
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
-
McDonalds
McDonalds is not a popular restaurant in the US. Few people go there. There are many other chains where people go and where it tastes better. The quality that McDonalds offers is not suitable for Americans. Yes, McDonalds is popular in Europe, but not in the US.
you just have to look up the number 1 restaurant chain in the US. Good try though lol
Why should I look, I was there, I lived there, I saw everything with my own eyes. And I repeat, at McDonalds in the USA, food is much worse than in other similar restaurants.
In food, as well as many other areas of life, "popular" (which is quantifiable) doesn't equal "good" (which is subjective, at least to some extent), but rather the lowest common denominator.
The fact that I, or you, don't choose to eat there doesn't mean that many other people make the same choice.
-
Interesting, rather than a long quote, here's a link to the Creative Common CC-BY 4.0 license.
https://creativecommons.org/licenses/by/4.0/
completely false - CC license specifically says credit must be given to the creator among SEVERAL other restrictions
I think you have a point there? I don't use CC or offer them, so this is the first I've actually read anything about how this is allowed or not.
-
Interesting, rather than a long quote, here's a link to the Creative Common CC-BY 4.0 license.
https://creativecommons.org/licenses/by/4.0/
completely false - CC license specifically says credit must be given to the creator among SEVERAL other restrictions
i've contributed several images when editing wiki, but it's a bit of a hassle
I think you have a point there? I don't use CC or offer them, so this is the first I've actually read anything about how this is allowed or not.
-
Hello, everyone, Haven't been here for a while and was curious how the stock market was going. Like most of you I have had my mind blown by AI apps like Midjourney which seems to be improving at an incredible pace. A few days ago I tried ChatGPT, and although it doesn't have live access to the web or can create imagery yet, it more than blew my mind on its potential. As a designer I can realistically see my work being completed by an AI tool in the near future. And, I have already used it to write some copy for a product within a brochure thus eliminating the girl's job in the office who usually does that for me. And to be blunt, AI did a far better job than she or I could. Interesting times ahead I think. So my 2 cents to this topic is it would be foolish not to acknowledge there will be significant changes as AI becomes more powerful. How well we adapt is really unknown!
-
Hello, everyone, Haven't been here for a while and was curious how the stock market was going. Like most of you I have had my mind blown by AI apps like Midjourney which seems to be improving at an incredible pace. A few days ago I tried ChatGPT, and although it doesn't have live access to the web or can create imagery yet, it more than blew my mind on its potential. As a designer I can realistically see my work being completed by an AI tool in the near future. And, I have already used it to write some copy for a product within a brochure thus eliminating the girl's job in the office who usually does that for me. And to be blunt, AI did a far better job than she or I could. Interesting times ahead I think. So my 2 cents to this topic is it would be foolish not to acknowledge there will be significant changes as AI becomes more powerful. How well we adapt is really unknown!
“In a world filled with automated processes and grey machinery is there still a demand for contemporary ceramics? Absolutely! Should you purchase one of my ceramic pieces, know that the clay was dug, processed and hand-thrown on a pottery wheel by a human being.
Its hard work and so it should be. The reward to you, the consumer, is an object of beauty signed by its creator and something you may admire for a lifetime. And who knows? Your great-grandchildren might share your joy a hundred years from now!”
The link in your tagline takes me to this site. Is this yours? If it is then the level of hypocrisy here is truly mind numbing.
-
i've been using chatGPT for several weeks now & it's amazing in some areas- i've found a few factual errors but overall it's incredible - i've used it get descriptions for my blog. sometimes i can use it directly, others it breaks writer's block w a great first draft. I'm also working with it to write stories.
it also does poetry & limericks (sort of)- few laureates will be displaced, but greeting card writers should be looking for other jobs!
Ngorongoro Crater, a place of wonder
A true masterpiece, created by thunder
A natural wonder, for all to see
A treasure of the earth, for you and me
-
Hello, everyone, Haven't been here for a while and was curious how the stock market was going. Like most of you I have had my mind blown by AI apps like Midjourney which seems to be improving at an incredible pace. A few days ago I tried ChatGPT, and although it doesn't have live access to the web or can create imagery yet, it more than blew my mind on its potential. As a designer I can realistically see my work being completed by an AI tool in the near future. And, I have already used it to write some copy for a product within a brochure thus eliminating the girl's job in the office who usually does that for me. And to be blunt, AI did a far better job than she or I could. Interesting times ahead I think. So my 2 cents to this topic is it would be foolish not to acknowledge there will be significant changes as AI becomes more powerful. How well we adapt is really unknown!
“In a world filled with automated processes and grey machinery is there still a demand for contemporary ceramics? Absolutely! Should you purchase one of my ceramic pieces, know that the clay was dug, processed and hand-thrown on a pottery wheel by a human being.
Its hard work and so it should be. The reward to you, the consumer, is an object of beauty signed by its creator and something you may admire for a lifetime. And who knows? Your great-grandchildren might share your joy a hundred years from now!”
The link in your tagline takes me to this site. Is this yours? If it is then the level of hypocrisy here is truly mind numbing.
Yes, that's my website thou I haven't touched it in a long time - just building up something for retirement when I can focus better on ceramics. When I wrote that I wasn't even aware of AI technology apart from maybe seeing it in the movies. I do believe there will always be niche or specialised areas in any industry including stock. But, honestly, no one knows where this AI technology will go, so yes, even hand crafted ceramics could be automated using AI.
-
i've been using chatGPT for several weeks now & it's amazing in some areas- i've found a few factual errors but overall it's incredible - i've used it get descriptions for my blog. sometimes i can use it directly, others it breaks writer's block w a great first draft. I'm also working with it to write stories.
it also does poetry & limericks (sort of)- few laureates will be displaced, but greeting card writers should be looking for other jobs!
Ngorongoro Crater, a place of wonder
A true masterpiece, created by thunder
A natural wonder, for all to see
A treasure of the earth, for you and me
Yes, agree, its not perfect. I've been trying to get it to write some abstract graphic code in Processing but its never quite right and currently it can't access the web so isn't using the latest version of the app. Early days!
-
How would you like stock photography platforms to handle the uploading of AI-generated content?
Should there be a difference between completely-AI-generated content, and AI-assisted content in which there is substantial human work and editing involved?
If AI-generated content is allowed, should royalties and earnings of the AI-generated content be shared with human creators? If so, what share would be appropriate?
-
How would you like stock photography platforms to handle the uploading of AI-generated content?
Should there be a difference between completely-AI-generated content, and AI-assisted content in which there is substantial human work and editing involved?
If AI-generated content is allowed, should royalties and earnings of the AI-generated content be shared with human creators? If so, what share would be appropriate?
If I take a digital photo and edit in photoshop, that's my image. If I enter words and AI makes an image and I edit in illustrator, that's my image. Why should I share my earnings from either?
-
How would you like stock photography platforms to handle the uploading of AI-generated content?
Should there be a difference between completely-AI-generated content, and AI-assisted content in which there is substantial human work and editing involved?
If AI-generated content is allowed, should royalties and earnings of the AI-generated content be shared with human creators? If so, what share would be appropriate?
AI generation is a tool - just like the embedded AI in PS neural processing and others. So it should be treated exactly the same as any other submitted content
and how would you determine it's AI generated if the artist doesnt label it as such? I like AS approach which, for now, accepts it but requires it to be tagged appropriately
-
AI generation is a tool - just like the embedded AI in PS neural processing and others. So it should be treated exactly the same as any other submitted content
and how would you determine it's AI generated if the artist doesnt label it as such? I like AS approach which, for now, accepts it but requires it to be tagged appropriately
Totally agree. Adobe has the right approch, generative AI images are not "photography" of course but they can have a space with the appropriate tag and classification.
At the contrary, others told contributors that we can't submit AI content with no real reasons.
Legal issues will be solved. Probably these agencies are sure they could produce by themselves all the necessary images. In my opinion this is really short-sighted view, they will have trillions of similar images but never more really new ones, Let's see
-
Should there be a difference between completely-AI-generated content, and AI-assisted content in which there is substantial human work and editing involved?
Probably yes, there should be, but I can't see any way to do this... How could you ever see the difference? It's hard now, but I'm sure it will be impossible in very next future.
-
How would you like stock photography platforms to handle the uploading of AI-generated content?
Should there be a difference between completely-AI-generated content, and AI-assisted content in which there is substantial human work and editing involved?
If AI-generated content is allowed, should royalties and earnings of the AI-generated content be shared with human creators? If so, what share would be appropriate?
Canva has issues with it's regular/human created contributor content. I don't see how the large number of exports listed on my dashboard (a few thousand a month) is fairly compensated for with the extremely low payments I received. I read about the royalty pool and such but this seems way unbalanced and there is no transparency. I have written to support about the issue but no one seems to be able to talk about contributor payment. I signed up to be able license and sell my work, not give it away in mass quantities to people who download it then resell it on Etsy.
Jdwfoto
-
How would you like stock photography platforms to handle the uploading of AI-generated content?
Should there be a difference between completely-AI-generated content, and AI-assisted content in which there is substantial human work and editing involved?
If AI-generated content is allowed, should royalties and earnings of the AI-generated content be shared with human creators? If so, what share would be appropriate?
The Ai is a tool like photoshop. Or even a digital camera instead of painting with oil. Why should there be any difference in royalties?
Creators might save time using an ai or they might be able to explore more diverse concepts on a subject. But in the end it is a tool, built by humans for humans.
It is not alien that came to planet earth and brought itself with its own art and ideas.
There is nothing inside an ai that humans didn't put there.
-
There is nothing inside an ai that humans didn't put there.
Only that humans put stuff in there that they did not create, that did not belong to them, where they did not compensate the artists who created it financially and where the artists who created it did not agree to have their stuff put in there.
They programmed their AI and had it crawl google including microstock databases (thus why the early versions tried to create microstock watermarks in the images).
AIs trained with our stolen art. I can't wrap my head around how there really is any microstck artist who doesn't see how wrong this is and goes with the "This is just another tool" narrative.
And it's not a "tool". A tool is an aid to help you acomplish your work. Here the AI doens't help you with your work, it does the work.
-
Don‘t worry about all that.
The next generation of ais will all be very legally trained on OUR images.
Some agencies will ask for an opt in, others will just update their terms of service and tell you to pack up and leave if you don‘t like it.
Plus there is billions of visual content that no longer has any copyright, which includes some of the worlds greatest artwork.
In the same way ais will be trained in music, in writing, in software…
The legal part is probably the easiest to fix.
So you can decide to complain forever or change your job, or find an intelligent way to work with the new technology.
-
Complain about new technologies is not a new story for sure.
If you have few minutes, this article about the relationship between paintings and photography in late 1800 is useful to understand how things will go relying the past:
https://www.thecollector.com/how-photography-transformed-art/ (https://www.thecollector.com/how-photography-transformed-art/)
-
Any chance we could get more transparency on our existing Canva earnings first? I would love to know how my RPD has changed over the last year or so...
Doesn’t help with trust when Canva chose to hide our download numbers rather than address issues.
-
Don‘t worry about all that.
The next generation of ais will all be very legally trained on OUR images.
Some agencies will ask for an opt in, others will just update their terms of service and tell you to pack up and leave if you don‘t like it.
Plus there is billions of visual content that no longer has any copyright, which includes some of the worlds greatest artwork.
In the same way ais will be trained in music, in writing, in software…
The legal part is probably the easiest to fix.
So you can decide to complain forever or change your job, or find an intelligent way to work with the new technology.
Hi Cobalt,
I liked very much your post and think you are right as you say that AI is a tool - but it's a disquietingly clever one.
Your words started a disturbing chain of thought that I made into a post ( https://luisafumi-digitalart.com/blog/2022/12/20/food-for-thought/ (https://luisafumi-digitalart.com/blog/2022/12/20/food-for-thought/)).
Maybe it's just me, or maybe I've read too much Asimov... ;)
-
Hi gameover,
haven't we all read too much Asimov? Never thought I would see the science fiction of my childhood come to life, wether its tyrants and dictators that seem to use 1984 as a workbook or any other dystopian novel, including my favorite works by Philip K.Dick.
And didn't a space scientist just put out the disturbing theory, that the galaxy has very little intelligent life because at some point we all destroy ourselves through malevolent technology?
Overall I think people who work in art, often take their work too seriously. If you are a carpenter, you do not assume that every table you make should be an award winning conception. Software writers don't get prizes for endless sleepless nights.
Personally I think the ai is just showing us that what we glamorize as something extraordinary is a quite basic function of humans and biology in general.
And just like you can learn to understand how a cell works and then build software that emulates biochemical pathways, you can of course build software that mimics our creative process.
Creativity is a survival mechanism to handle problems.
So I am not worried about ai. As long as we have control of the electric plug...
@derby
love that article! Never really thought about how photography was the driver for abstract paintings. i just knew that it took more than 50 years to get photography accepted as an art form.
Will be interesting to see what happens with ai.
-
As long as we have control of the electric plug...
;D ;D ;D
-
I think it will never replace real photos. Especially editorial where reality and authenticity is needed.
That's what I think, real photos will never be replaced in a lot of areas. Even the AIs will need new photos to actualize their knowledge.
-
Still,
I am (and I will not speak for the rest) a photographer. Not some guy who enters words in a software program and then creates an image with it.
A subtle difference as to "it's just a tool that helps you".
-
Still,
I am (and I will not speak for the rest) a photographer. Not some guy who enters words in a software program and then creates an image with it.
A subtle difference as to "it's just a tool that helps you".
As a painter in 1890:
"Still,
I am (and I will not speak for the rest) a painter. Not some guy who push button in a mechanical machine and then creates an image with it.
A subtle difference as to "it's just a tool that helps you"
"
Sorry, nothing against you, I'm not trying to be sarcastic: just to remind that your exact words was used against the machine you're actually using, the camera
-
I liked very much your post and think you are right as you say that AI is a tool - but it's a disquietingly clever one.
Your words started a disturbing chain of thought that I made into a post ....
Maybe it's just me, or maybe I've read too much Asimov... ;)
check out https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/ (https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/)
-
I liked very much your post and think you are right as you say that AI is a tool - but it's a disquietingly clever one.
Your words started a disturbing chain of thought that I made into a post ....
Maybe it's just me, or maybe I've read too much Asimov... ;)
check out https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/ (https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/)
SF is OK, I like it a lot too. But here S<<F...
-
Still,
I am (and I will not speak for the rest) a photographer. Not some guy who enters words in a software program and then creates an image with it.
A subtle difference as to "it's just a tool that helps you".
As a painter in 1890:
"Still,
I am (and I will not speak for the rest) a painter. Not some guy who push button in a mechanical machine and then creates an image with it.
A subtle difference as to "it's just a tool that helps you"
"
Sorry, nothing against you, I'm not trying to be sarcastic: just to remind that your exact words was used against the machine you're actually using, the camera
But camera is creating photos, not paintings. It opened whole new world and replaced some areas of the old and very small world of paintings. Here AI wil create both "photos" and "paintings" or illustrations of any kind. It will not open new world in this very moment, just will replace most of the old one. Only editorial photos will survive and very specific areas of illustration - some conceptual and maybe humor (for some time).
So you can now happily generate hundreds of fantastic "paintings", even you are not painter but you get a tool to be a painter. But your only real skill is to see and correct mistakes that AI is doing so far. Half of human beings can do it. So you will soon compete with millions of other and cheaper human not-painters.
And the funny idea on the end - you are only tool to train AI to create images without mistakes. Happy generating!
-
I liked very much your post and think you are right as you say that AI is a tool - but it's a disquietingly clever one.
Your words started a disturbing chain of thought that I made into a post ....
Maybe it's just me, or maybe I've read too much Asimov... ;)
check out https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/ (https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/)
#1 unplug the computers?
His premise starts to get strange around this part "
AIs could recruit human allies, tele-operate robots and other military equipment, make money via research and quantitative trading, etc.
At a high level, I think we should be worried if a huge (competitive with world population) and rapidly growing set of highly skilled humans on another planet was trying to take down civilization just by using the Internet. So we should be worried about a large set of disembodied AIs as well.
"
They could tele-operate robots and military equipment, for what gain? What need is there for money if the AI controls everything? highly skilled humans on another planet Realy, now we are back to War of the Worlds kind of scenarios? Disembodied AI will be like alien invaders?
Could some AI network manipulate the entire human population? Whoever controls the network, controls the world.
Lets say all the "good" people in the world say, we won't create any AI that could take over. We won't create AI... How would they have the knowledge of how that AI works, when someone evil tries to build the system to take over the world? In other words, the best defense, is to understand the weapon that will be used to attack us. Maybe create something that can defeat it?
But I still say, if some AI network starts to self create, flip the switch, turn it off.
-
I liked very much your post and think you are right as you say that AI is a tool - but it's a disquietingly clever one.
Your words started a disturbing chain of thought that I made into a post ....
Maybe it's just me, or maybe I've read too much Asimov... ;)
check out https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/ (https://www.cold-takes.com/ai-could-defeat-all-of-us-combined/)
#1 unplug the computers?
His premise starts to get strange around this part "
AIs could recruit human allies, tele-operate robots and other military equipment, make money via research and quantitative trading, etc.
At a high level, I think we should be worried if a huge (competitive with world population) and rapidly growing set of highly skilled humans on another planet was trying to take down civilization just by using the Internet. So we should be worried about a large set of disembodied AIs as well.
"
They could tele-operate robots and military equipment, for what gain? What need is there for money if the AI controls everything? highly skilled humans on another planet Realy, now we are back to War of the Worlds kind of scenarios? Disembodied AI will be like alien invaders?
Could some AI network manipulate the entire human population? Whoever controls the network, controls the world.
Lets say all the "good" people in the world say, we won't create any AI that could take over. We won't create AI... How would they have the knowledge of how that AI works, when someone evil tries to build the system to take over the world? In other words, the best defense, is to understand the weapon that will be used to attack us. Maybe create something that can defeat it?
But I still say, if some AI network starts to self create, flip the switch, turn it off.
that post has been followed by more details & addresses the points you raise - esp'ly about whether 'good' companies should develop dangerous AI to counter those who don't care
https://www.cold-takes.com/ai-safety-seems-hard-to-measure/ (https://www.cold-takes.com/ai-safety-seems-hard-to-measure/)
overall summary & references
https://www.cold-takes.com/most-important-century/ (https://www.cold-takes.com/most-important-century/)
(https://cascoly.com/1-tfr/ai-prediction.jpg)
-
I am really curious to have the same conversation with all of you in a couple of years.
Right now there seem to be a lot of artist who jump on the trainwagon, seeing there is easy money for them to be made with AI generated images. So they claim it's "just a tool" for them and everything is fine and it's not basically the first step towards the end of human made art. Hey, that's just advanced technology, we have to go with the time and can't stop progress, right?
But I am curious to see what they think once they realize that this is not just a "tool" for them, but also for the customers.
How long will it take till the last customer has realized that instead of going to a microstick agency site or a self hosted photographer/artist site or even commissioning an artist/photographer for lots of money, all he needs to do is to go to midjourney, DALL-E or whatever other AI image generation sites are or will be out there and can just describe to the AI what he needs, instead of entering the words in a microstiock search bar or describing it to the artist? 1 year? 5 years? The way things are progressing why do you think the customer will even have a need for you as a traditional or digital artist or photographer in the future? Someone who needs an image will not need you as a "middle man" to describe stuff to the AI and re-sell what the AI creates for you, he will eventually just go to the AI site and describe what he needs to it himself. "AI picture describer" is not something I really see as a job to bring in money in the future.
And the whole problem goes much further than this. The next step after AI generated paintings and photos will be AI generated videos, AI generated stories, AI generated music. In a 100 years there won't be any artists left, because who ever will persuit art, if no one can live from it anymore, because an AI can do it faster and cheaper than you anyways. And that's incredibly sad, because humanity is basically killing off part of what makes it human. I am glad I will not live long enough to see that art-deprived mankind where human creativity has been snuffed out.
-
.
-
...
And the whole problem goes much further than this. The next step after AI generated paintings and photos will be AI generated videos, AI generated stories, AI generated music. In a 100 years there won't be any artists left, because who ever will persuit art, if no one can live from it anymore, because an AI can do it faster and cheaper than you anyways. And that's incredibly sad, because humanity is basically killing off part of what makes it human. I am glad I will not live long enough to see that art-deprived mankind where human creativity has been snuffed out.
yes, likely next steps - but what difference are you making by hiding your head in the sand while some of us see the future and are learning to deal with it. it's not a fast buck, it's facing reality.
if you've actually used an AI you'd realize that sending a phrase doesn't automatically create usable images without a good deal of post-processing. & buying from agencies will still be cheaper than paying salary & benefits to an in-house AI user.
-
yes, likely next steps - but what difference are you making by hiding your head in the sand while some of us see the future and are learning to deal with it. it's not a fast buck, it's facing reality.
if you've actually used an AI you'd realize that sending a phrase doesn't automatically create usable images without a good deal of post-processing. & buying from agencies will still be cheaper than paying salary & benefits to an in-house AI user.
Why do you think you are "learning to deal with it" in regards to the problem in my post, meaning, how are you learning to deal with the fact that in the future customers will enter their search terms in AI image generators instead of microstock sites and you won't be needed to do that for them?
Yes, I have tried AIs and I have realized that they are not producing satisfying results. That's why I am talking about the future. AIs are learning fast. If you have seen the video someone posted here of a comparison of how drastically midjourney results for the same description improved within just a couple of months (here: https://www.youtube.com/watch?v=d4lY2TjqNTs (https://www.youtube.com/watch?v=d4lY2TjqNTs) ), you must realize that your "post processing service" will not be needed in the future.
-
In 1977, I was working for IBM and we had all started using this word processor called Script. It was so much easier than sending stuff out to get typed.
After a couple of months, a memo comes down from management. Please stop using Script as the staff in the typing pool don't have enough work.
Well, word processors are still with us and typing pools have disappeared.
If the technology is decent, if it does the job and if people like it, then they will use it. All the wailing and gnashing of teeth isn't going to change that.
-
you must realize that your "post processing service" will not be needed in the future.
I am sorry but I have a different perspective. They will all be here in the future but probably in different manners.
I find interesting to have this tool available like any other in the past and i don't see a straight correlation to a dystopian/utopian future.
Of course AI changed the game but new services and new type of works will rise.
In past months i see more companies hiring creative people and setting their own creative/communication department instead of hiring an external company to do that. Mainly to deal with social media where you have to post a lot of content (nearly 20 different posts/day across platforms). Ai will really help here for sure. It will help to elaborate new concepts/ideas to be created, produced and distributed on same day. Microstock will still be there to help too since i don't see AI producing reality if you need it (news, documentaries, happenings, etc).
Wish you all a Merry Christmas!
-
yes, likely next steps - but what difference are you making by hiding your head in the sand while some of us see the future and are learning to deal with it. it's not a fast buck, it's facing reality.
if you've actually used an AI you'd realize that sending a phrase doesn't automatically create usable images without a good deal of post-processing. & buying from agencies will still be cheaper than paying salary & benefits to an in-house AI user.
Why do you think you are "learning to deal with it" in regards to the problem in my post, meaning, how are you learning to deal with the fact that in the future customers will enter their search terms in AI image generators instead of microstock sites and you won't be needed to do that for them?..,.
because it's not a 'fact' - just your improbable prediction - there's no reason to believe most customers will switch for reasons discussed here many times. they can buy images for pennies rather than pay the cost of an employee's time to create images
'dealing w it' = accepting it's coming (even faster by your estimates!) but your solution is to surrender w/o adjusting - just as many film photographers lost by refusing to adapt to digital. luddites are always on the wrong side of innovation & history
-
In 1977, I was working for IBM and we had all started using this word processor called Script. It was so much easier than sending stuff out to get typed.
After a couple of months, a memo comes down from management. Please stop using Script as the staff in the typing pool don't have enough work.
Well, word processors are still with us and typing pools have disappeared.
If the technology is decent, if it does the job and if people like it, then they will use it. All the wailing and gnashing of teeth isn't going to change that.
Those typists were eventually out of work and had to go learn to do something else. Artists and photographers today would be fools to think that's not going to happen to them. Most commercial artists and photographers (except those working in extremely niche segments that's not replicable by AI) are going to be out of a job in a few years. They're going to have to learn to make money some other way.
The argument isn't that "this Dall-E Chat GPT thing is evil and should be stopped" but that this thing is coming fast so you better have a backup plan in place in case it swallows all the income you generate with your work today.
-
Artists and photographers today would be fools to think that's not going to happen to them. Most commercial artists and photographers (except those working in extremely niche segments that's not replicable by AI) are going to be out of a job in a few years. They're going to have to learn to make money some other way.
I think it will happen to everybody and not just artists! AI generative like midjourney, Dall-e or Stable are a very small drop in the AI ocean. People in all areas are adapting AI as tool to improve performance. It's in Agriculture, industries, health, Finance, Economy, Banking, Security, weather, news, marketing, etc... do you think everybody will be out of job in a few years?
But let's stick to photography... Photoshop is implementing AI, Cameras are implementing AI to improve shooting, object recognition, Image stabilization, Shooting alone with no human in hazard environments, deep tracking, etc...
In that sense why companies of photography or Post production are developing and implementing AI in their products?
Following your logic no one will invest in development new AI cameras since we have Ai generative tools, right?
But that's not happening is it?
On the other hand, marketing is betting much more in User-generated content (tiktok, unboxing videos, real people reviews, travel vlogers, people doing tutorials) which is real and authentic. However marketing is relying on AI to analyze data from consumers...
Therefore like with computer in past, now...people are adapting and taking advantage to improve their work with AI. I don't think one will dilute the other. At least for now ;)
-
Customers can already use their mobile phone to fill most of their photography needs if they wanted to. The quality you can get from the high end models is incredibly.
And yet they still hire photographers for events and business portraits and still buy content from agencies.
The only real difference is that now they also need amateurish looking photos for social media content and especially on eyeem I was making good money providing exactly that until everything at eyeem stopped working.
It will be the same with ai. Customers buy it on agencies, because they simply don‘t have the time to produce the content themselves.
Large companies already employ designers, but even they usually buy from agencies. I am sure they will employ ais to speed up their workflow, but it will not replace them. It will simply give them more options.
-
Customers can already use their mobile phone to fill most of their photography needs if they wanted to. The quality you can get from the high end models is incredibly.
And yet they still hire photographers for events and business portraits and still buy content from agencies.
There's a big difference between "still hiring and buying" and "hiring and buying like they used to".
Do you think it's easier to make a living off photography and stock photography today than 10 years ago? It's precisely because it's far easier to take acceptable images today that there's a glut of images in the market and the agencies are racing to the bottom to scrape for ever lower demand. And with a glut of easily produceable AI images entering the market in the next few years, you're not just competing with millions of other humans but computers as well. I'll let you decide what that's going to do to the already saturated market.
-
So contributors are (not asked) just expected now to freely donate images and videos for the purpose of customers generating their own content which they can either use or go on and sell themselves?
If this is where it's heading I wonder how long the big contributors close their ports. Seems no use to create and upload for the benefit of everyone else except the contributor producing the content, often at cost. But then again, agencies seem to be getting their way with almost everything now and contributors aren't going anywhere.
Imagine traveling some distance to view a home for sale or rent.
"Oh this looks nothing like the photos I saw online?"
"Of course not! Those photos were made from AI"
"Heh???"
"It's progress... Welcome to the Big Brave New World of Fakeness Bull Sh!t"
-
„Imagine traveling some distance to view a home for sale or rent.
"Oh this looks nothing like the photos I saw online?"
"Of course not! Those photos were made from AI"
"Heh???"“
"It's progress... Welcome to the Big Brave New World of Fakeness Bull Sh!t"
That would be fraud and mean that that real estate agent will never get a home offered to be sold again. And you don‘t need an ai to create lies with photos…
Most people who I see complaining about ai have never used one.
It is a tool like photoshop and needs a lot of experience.
Which customer will waste his time playing around with various prompts until they get it right?
Much easier to just download a ready made file.
The advantage of ai is that it can make it a lot easier to create „impossible things“, i.e. images that would have taken a long time to create as composite of photos and illustrations.
If you go into the ai groups you will see that it is a very tiny percentage of people who create fantastic content. And they are usually professional 3d artists or professional illustrators.
But of course, if you are sure that ai destroys everything, then it would be prudent to get out of stock now and retrain into a new profession.
By the way all the business photographers I know are still extremely busy making money. But they simply know what they are doing. Even if they use a mobile phone, the quality they produces is lightyears better than what customers do themselves.
I am sure some artists will soon offer ai services as part of what they do. But they need to be able to create reliable results and at the moment that is still complicated.
But it will come.
It is your business, if for you it is all over, just leave and do something else. Others will see it as an intersting opportunity.
-
Which customer will waste his time playing around with various prompts until they get it right?
And you think customers enter search terms in a microstock search bar and get exactly what they want right on the first or even 50th page or even at all? Have you actually ever tried buying/finding images in microstock databases? Because i have and 90% of the time it's going through countless images that have irrelevant keywords and don't even show anything close to what you want.
Most will take the first image that pops up that is good enough and roughly serves the purpose for which they need it. Hardly any customers try around and browse the database "until they get it right", so why should it be different with AI generated images and the first results they get should not be close enough?
The few customers who take the effort to search in microstock databases for hours to find exactly what they want will also take the effort with AIs.
-
It is your business, if for you it is all over, just leave and do something else. Others will see it as an intersting opportunity.
Ai will affect all markets and definitelly the amount of money for artist and photographers will be lower. I don't want to be rude, but average photographers who get the "tool" to be "painters" instantly can see it as opportunity, but in future only people who are in some way different or exceptional will survive on the digital market.
And don't forget that the Ai is developing rapidly. If now there are some dificulties (fingers or so), few years from now it will be much easier to use with even better results.
-
„Imagine traveling some distance to view a home for sale or rent.
"Oh this looks nothing like the photos I saw online?"
"Of course not! Those photos were made from AI"
"Heh???"“
"It's progress... Welcome to the Big Brave New World of Fakeness Bull Sh!t"
That would be fraud and mean that that real estate agent will never get a home offered to be sold again. And you don‘t need an ai to create lies with photos…
Most people who I see complaining about ai have never used one.
It is a tool like photoshop and needs a lot of experience.
Which customer will waste his time playing around with various prompts until they get it right?
Much easier to just download a ready made file.
The advantage of ai is that it can make it a lot easier to create „impossible things“, i.e. images that would have taken a long time to create as composite of photos and illustrations.
If you go into the ai groups you will see that it is a very tiny percentage of people who create fantastic content. And they are usually professional 3d artists or professional illustrators.
But of course, if you are sure that ai destroys everything, then it would be prudent to get out of stock now and retrain into a new profession.
By the way all the business photographers I know are still extremely busy making money. But they simply know what they are doing. Even if they use a mobile phone, the quality they produces is lightyears better than what customers do themselves.
I am sure some artists will soon offer ai services as part of what they do. But they need to be able to create reliable results and at the moment that is still complicated.
But it will come.
It is your business, if for you it is all over, just leave and do something else. Others will see it as an intersting opportunity.
I do mainly aerial drone landmarks, landscapes and cityscapes video. So unless the AI boogeyman is coming to take over this market then I'm not going anywhere.
And if AI does take over this and similar content then you've got way bigger problems to concern yourself with than me and others complaining on these forums.
-
I am not worried at all.
On the contrary, I am quite excited about the possibilities that ai brings and will make an effort to learn how to use the new tool to my advantage.
I just see a lot of „the world is ending“ „the ai is coming for us“ everywhere and thought it might help discussions to offer a positive outlook.
-
I am not worried at all.
On the contrary, I am quite excited about the possibilities that ai brings and will make an effort to learn how to use the new tool to my advantage.
I just see a lot of „the world is ending“ „the ai is coming for us“ everywhere and thought it might help discussions to offer a positive outlook.
I'm fatalistic about it. If AI is good and meets a need then it will get used. However, in my time on this earth, I've seen technologies come and technologies go. I've seen industries change, job roles disappear and new ones get created. Nothing stays static, everything changes (except death and taxes). It's not the end of the world, it never is. Just need to roll with the punches.
-
I am not worried at all.
On the contrary, I am quite excited about the possibilities that ai brings and will make an effort to learn how to use the new tool to my advantage.
I just see a lot of „the world is ending“ „the ai is coming for us“ everywhere and thought it might help discussions to offer a positive outlook.
I'm fatalistic about it. If AI is good and meets a need then it will get used. However, in my time on this earth, I've seen technologies come and technologies go. I've seen industries change, job roles disappear and new ones get created. Nothing stays static, everything changes (except death and taxes). It's not the end of the world, it never is. Just need to roll with the punches.
You mean like when Digital Cameras took over for film cameras? :)
(https://img.discogs.com/dyfpJsiiY3vXjV8LIcqdoDERiPI=/fit-in/600x600/filters:strip_icc():format(jpeg):mode_rgb():quality(90)/discogs-images/R-10895596-1506177438-9907.jpeg.jpg)
Yes it was a good one.
(https://i.postimg.cc/6Q2gK8tb/frankenstein-nothing-to-fear.jpg)
-
If AI is good and meets a need then it will get used.
I couldn't agree more with you. Perhaps some people will be surprised but AI has helped during the pandemic:
1. Predicting outbreaks
Not many people realize, but it was actually an AI-automated system that first alerted the wider world to COVID-19.
2. Protecting the vulnerable
When you can predict something, you can prepare for it. That’s the goal of several AI researchers who are building models to protect vulnerable populations from COVID-19 and other viral diseases.
3. Contact tracing
The model helped identify close contacts faster, and even potential super spreaders and hot-spot suburbs.
4. Research and development
AWS has launched CORD-19 Search, built on the Allen Institute for AI’s open dataset of more than 128,000 research papers, to quickly allow scientists to look-up questions about COVID-19. AI is even help in the race for COVID vaccines and anti-viral drugs. In 2020, a UK company, BenevolentAI, used an AI drug discovery platform to figure out which compounds stood the best chance against COVID-19.
You can find a nice article about this here: https://online.rmit.edu.au/blog/4-ways-ai-has-helped-during-pandemic
-
...and will make an effort to learn how to use the new tool to my advantage...
I wouldn't bother. The interface will get more user friendly and the results better so fast even the minimal effort to learn how to use it now is time wasted. Just wait a couple of months and it will be a lot more intuitive. No point learning typesetting cast metal sorts when the wordprocessor will be invented before you can master it. AI will be able to do the post processing much better and faster than us soon enough.
-
Which customer will waste his time playing around with various prompts until they get it right?
And you think customers enter search terms in a microstock search bar and get exactly what they want right on the first or even 50th page or even at all? Have you actually ever tried buying/finding images in microstock databases? Because i have and 90% of the time it's going through countless images that have irrelevant keywords and don't even show anything close to what you want.
Most will take the first image that pops up that is good enough and roughly serves the purpose for which they need it. No customers try around and browse the database "until they get it right", so why should it be different with AI generated images and the first results they get should not be close enough?
Agree 100%. AI will be much quicker and easier than looking through pages of images. You can choose an image that is in the right direction and refine it further or instantly generate variants. Much easier than searching through 1000s of pre-created images.
-
...and will make an effort to learn how to use the new tool to my advantage...
I wouldn't bother. The interface will get more user friendly and the results better so fast even the minimal effort to learn how to use it now is time wasted. Just wait a couple of months and it will be a lot more intuitive. No point learning typesetting cast metal sorts when the wordprocessor will be invented before you can master it. AI will be able to do the post processing much better and faster than us soon enough.
thus becoming a self-fulfilling prophecy of doom. and those who adapt will at least have a chance rather than none at all. it's dancing among elephants - few will be Stieglitz or Ansel Adams, but niches are there to be exploited. Not every buyer will even have a specific need when they're looking to illustrate a concept
the wordprocessor didn't put all writers out of work, it streamlined the process.
oldtime programmers will remember the idea of desk checking - spending time checking & rechecking code for typos, logic errors,etc before submitting to be keypunched, then getting time on THE computer, only to have it spit out a vague "you've got errors" msg. Along came interactive compilers that displayed your errors, then suites that did large parts of design. downloadable drivers eliminated coding for each device; internet browsers replaced programming modem input/output; databases replaced the need to for coding the most efficient sorting algorithms ('bubble sort' anyone? 'hashing' algorithms? linked lists?) we had workarounds that did multi-tasking before windows, and modems & semi-hard disks were useful, but they were cumbersome & limited. each step eliminated some work/ers but those who swam with the flow had more interesting careers (and higher salaries). many computer consultants would not be able to find work if they had to constantly re-create the wheel.
now chat &others are starting to write code, but people will still be needed to design the app. (and current state of design needs more intelligence in general - with too many poorly designed apps being thrown untested into the wild with horrible design flaws)
-
AI is still fantastic. There will be no competition from him for the stock market. Yes, an additional tool, such as photoshop, for authors.
-
I am really curious to have the same conversation with all of you in a couple of years.
Right now there seem to be a lot of artist who jump on the trainwagon, seeing there is easy money for them to be made with AI generated images. So they claim it's "just a tool" for them and everything is fine and it's not basically the first step towards the end of human made art. Hey, that's just advanced technology, we have to go with the time and can't stop progress, right?
But I am curious to see what they think once they realize that this is not just a "tool" for them, but also for the customers.
How long will it take till the last customer has realized that instead of going to a microstick agency site or a self hosted photographer/artist site or even commissioning an artist/photographer for lots of money, all he needs to do is to go to midjourney, DALL-E or whatever other AI image generation sites are or will be out there and can just describe to the AI what he needs, instead of entering the words in a microstiock search bar or describing it to the artist? 1 year? 5 years? The way things are progressing why do you think the customer will even have a need for you as a traditional or digital artist or photographer in the future? Someone who needs an image will not need you as a "middle man" to describe stuff to the AI and re-sell what the AI creates for you, he will eventually just go to the AI site and describe what he needs to it himself. "AI picture describer" is not something I really see as a job to bring in money in the future.
And the whole problem goes much further than this. The next step after AI generated paintings and photos will be AI generated videos, AI generated stories, AI generated music. In a 100 years there won't be any artists left, because who ever will persuit art, if no one can live from it anymore, because an AI can do it faster and cheaper than you anyways. And that's incredibly sad, because humanity is basically killing off part of what makes it human. I am glad I will not live long enough to see that art-deprived mankind where human creativity has been snuffed out.
I don't agree, even until now customers were free to invest in their own tools (lets say cameras, or paint and brushes ) , invest even more time and learn how to use them and create professional level images. Is it really as simple as that ?
Even with AI, someone will not just be able to buy some credits and create something they need at the level of someone else who invested enormous time into that. Sure, serious hobbyist will be able to go really high in the quality of their work but they were able to do so in photography also.
The biggest problem that I see is in the actual amount of work someone is going to be able to produce in small amount of time when he finds his style which will have to be tricky to reproduce if that someone wants to stay recognizable. We are talking about the ability to create a full portfolio in couple of sleepless nights which until now it would takes years to create.
I'm sure there will be superstar AI artists with unique styles which will brand their work under their their name, earn based on social presence, more or less like in any form or art in the history.
Also I'm really against stuff that started to happen when people use at the end of their prompts "in style of artist name". In my opinion that's not only stealing the style, that's stealing the whole identity and brand that someone worked his butt for.
In case of machine learning I'm really not against that that much because there is not an artist in the history of the world that has not stolen part of his style or work from someone else. But when you mention that name to get more attention, or to build your style...that's a problem.
-
I just got an email from SS titled: Contributor earnings now reflect generative AI Here's the first paragraph of the email:
News for artist recognition in advanced technology worldwide, and news for Shutterstock contributors!
You will now accrue royalties when your IP is used in the training of AI-generative models or used for licensing of generative assets created using Shutterstock’s software. Contributing artists can view their earnings in their account in the Earnings Summary 'By month' tab as 'Contributor fund.'
-
LOL I get the joke.
(https://i.postimg.cc/6Q2gK8tb/frankenstein-nothing-to-fear.jpg)
-
I just got an email from SS titled: Contributor earnings now reflect generative AI Here's the first paragraph of the email:
News for artist recognition in advanced technology worldwide, and news for Shutterstock contributors!
You will now accrue royalties when your IP is used in the training of AI-generative models or used for licensing of generative assets created using Shutterstock’s software. Contributing artists can view their earnings in their account in the Earnings Summary 'By month' tab as 'Contributor fund.'
This is gonna be a few cents so they are able to reduce the likelihood of a successful lawsuit. And it is gonna be only for a few years until we are completely phased out.
-
I just got an email from SS titled: Contributor earnings now reflect generative AI Here's the first paragraph of the email:
News for artist recognition in advanced technology worldwide, and news for Shutterstock contributors!
You will now accrue royalties when your IP is used in the training of AI-generative models or used for licensing of generative assets created using Shutterstock’s software. Contributing artists can view their earnings in their account in the Earnings Summary 'By month' tab as 'Contributor fund.'
This is gonna be a few cents so they are able to reduce the likelihood of a successful lawsuit. And it is gonna be only for a few years until we are completely phased out.
this is what we've been saying all along - each artist is a tiny drop among 200 million images they can use for training
and the overhyped fears are just silly - why would they delete those 200 million images which are already highly placed on google? shift happens
assuming they used all 200 million, based on my numbers, the payout seems to be about .3 cents ($.003) /image. so someone w 10K images would get about $30 - does that correlate with what others have reported?
-
the TOS seem to let SS use images for training (and doesnt even require any payment)
By submitting any Content to Shutterstock, you grant to Shutterstock a worldwide, sublicensable, non-exclusive right and license to index, analyze, categorize, archive reproduce, prepare derivative works incorporating, publicly display, sell, advertise and market, any Content uploaded by you and accepted by Shutterstock for any reasonable business purpose, including but not limited to the distribution of your Content to Shutterstock customers, to optimize the performance and operation of Shuttestock’s platform and services, and to develop new features and products.
-
Yeah it's an obvious move to minimize potential legal damage.
-
I just got an email from SS titled: Contributor earnings now reflect generative AI Here's the first paragraph of the email:
News for artist recognition in advanced technology worldwide, and news for Shutterstock contributors!
You will now accrue royalties when your IP is used in the training of AI-generative models or used for licensing of generative assets created using Shutterstock’s software. Contributing artists can view their earnings in their account in the Earnings Summary 'By month' tab as 'Contributor fund.'
There are probably those on the forum who will not be allowed to use their work for AI training. :)))))))
-
I just got an email from SS titled: Contributor earnings now reflect generative AI Here's the first paragraph of the email:
News for artist recognition in advanced technology worldwide, and news for Shutterstock contributors!
You will now accrue royalties when your IP is used in the training of AI-generative models or used for licensing of generative assets created using Shutterstock’s software. Contributing artists can view their earnings in their account in the Earnings Summary 'By month' tab as 'Contributor fund.'
There are probably those on the forum who will not be allowed to use their work for AI training. :)))))))
I don't see why some "will not be allowed" to have their images used for AI training, but otherwise, I will not allow that, when given the option.
-
I just got an email from SS titled: Contributor earnings now reflect generative AI Here's the first paragraph of the email:
News for artist recognition in advanced technology worldwide, and news for Shutterstock contributors!
You will now accrue royalties when your IP is used in the training of AI-generative models or used for licensing of generative assets created using Shutterstock’s software. Contributing artists can view their earnings in their account in the Earnings Summary 'By month' tab as 'Contributor fund.'
...
, but otherwise, I will not allow that, when given the option.
problem is, you've already given them permission according to the TOS you agreed to. SS may choose to allow people to opt out but haven't done so yet
-
I just got an email from SS titled: Contributor earnings now reflect generative AI Here's the first paragraph of the email:
News for artist recognition in advanced technology worldwide, and news for Shutterstock contributors!
You will now accrue royalties when your IP is used in the training of AI-generative models or used for licensing of generative assets created using Shutterstock’s software. Contributing artists can view their earnings in their account in the Earnings Summary 'By month' tab as 'Contributor fund.'
...
, but otherwise, I will not allow that, when given the option.
problem is, you've already given them permission according to the TOS you agreed to. SS may choose to allow people to opt out but haven't done so yet
I understand that.
This is what SS specified in their FAQ:
Can I opt out of having my content included in future datasets / data deals?
Yes, in the coming months we will be adding an option in the contributor account settings that will allow you to opt out of having your content included in future datasets, also known as data deals.
-
I just got an email from SS titled: Contributor earnings now reflect generative AI Here's the first paragraph of the email:
News for artist recognition in advanced technology worldwide, and news for Shutterstock contributors!
You will now accrue royalties when your IP is used in the training of AI-generative models or used for licensing of generative assets created using Shutterstock’s software. Contributing artists can view their earnings in their account in the Earnings Summary 'By month' tab as 'Contributor fund.'
...
, but otherwise, I will not allow that, when given the option.
problem is, you've already given them permission according to the TOS you agreed to. SS may choose to allow people to opt out but haven't done so yet
I understand that.
This is what SS specified in their FAQ:
Can I opt out of having my content included in future datasets / data deals?
Yes, in the coming months we will be adding an option in the contributor account settings that will allow you to opt out of having your content included in future datasets, also known as data deals.
Translates to "when we are done processing your images you will be able to opt out"
-
I just got an email from SS titled: Contributor earnings now reflect generative AI Here's the first paragraph of the email:
News for artist recognition in advanced technology worldwide, and news for Shutterstock contributors!
You will now accrue royalties when your IP is used in the training of AI-generative models or used for licensing of generative assets created using Shutterstock’s software. Contributing artists can view their earnings in their account in the Earnings Summary 'By month' tab as 'Contributor fund.'
...
, but otherwise, I will not allow that, when given the option.
problem is, you've already given them permission according to the TOS you agreed to. SS may choose to allow people to opt out but haven't done so yet
I understand that.
This is what SS specified in their FAQ:
Can I opt out of having my content included in future datasets / data deals?
Yes, in the coming months we will be adding an option in the contributor account settings that will allow you to opt out of having your content included in future datasets, also known as data deals.
Translates to "when we are done processing your images you will be able to opt out"
I expect an exciting announcement coming soon, now that we are into the new year.
-
...the wordprocessor didn't put all writers out of work, it streamlined the process.
...
No but that wasn't what I was saying. It did put all typesetters out of work. We are the typesetters not the authors. AI isn’t going to stop at just the right level to make it possible for you to make saleable work with its help, it will shoot right by you.
-
...the wordprocessor didn't put all writers out of work, it streamlined the process.
...
No but that wasn't what I was saying. It did put all typesetters out of work. We are the typesetters not the authors. AI isn’t going to stop at just the right level to make it possible for you to make saleable work with its help, it will shoot right by you.
Typesetters were already put out of work when Linotype was invented, offset printing came in and lead slugs were history. Then we had galleys and paste up, which was replaced by machines. The word processor just replaced the typewriter as one machine made writing easier. Letterpress is dead except for special uses.
AI is going to replace some things and supplement others, but it's not going to replace individual artists or creativity.
ps I tried to point this out once before, but resistance to change is pretty strong and especially when backed with denial. Microstock is already dead, therefore AI can't kill it.
-
...the wordprocessor didn't put all writers out of work, it streamlined the process.
...
No but that wasn't what I was saying. It did put all typesetters out of work. We are the typesetters not the authors. AI isn’t going to stop at just the right level to make it possible for you to make saleable work with its help, it will shoot right by you.
Typesetters were already put out of work when offset printing came in. Letterpress is dead except for special uses. AI is going to replace some things and supplement others, but it's not going to replace individual artists or creativity.
ps I tried to point this out once before, but resistance to change is pretty strong and especially when backed with denial. Microstock is already dead, therefore AI can't kill it.
I am talking about us a stock image creators, not artists in general. Not sure what you mean by "Microstock is already dead" plenty of people have been doing fine so far.
-
...the wordprocessor didn't put all writers out of work, it streamlined the process.
...
No but that wasn't what I was saying. It did put all typesetters out of work. We are the typesetters not the authors. AI isn’t going to stop at just the right level to make it possible for you to make saleable work with its help, it will shoot right by you.
Typesetters were already put out of work when offset printing came in. Letterpress is dead except for special uses. AI is going to replace some things and supplement others, but it's not going to replace individual artists or creativity.
ps I tried to point this out once before, but resistance to change is pretty strong and especially when backed with denial. Microstock is already dead, therefore AI can't kill it.
I am taliking about us a stock image creators, not artists in general. Not sure what you mean by "Microstock is already dead" plenty of people have been doing fine so far.
And there's a heap of denial. Most people aren't, so don't use "plenty of people" which is the minority, as your supporting argument.
Some people still ride horses and drive wagons, some ride bicycles or use public transportation, and they are doing just fine without an automobile.
Microstock as a stable or reliable income or even side income, where someone can get in and make some extra money, is DEAD! We're going into over ten years of decline.
-
And there's a heap of denial. Most people aren't, so don't use "plenty of people" which is the minority, as your supporting argument.
Some people still ride horses and drive wagons, some ride bicycles or use public transportation, and they are doing just fine without an automobile.
Microstock as a stable or reliable income or even side income, where someone can get in and make some extra money, is DEAD! We're going into over ten years of decline.
Lol, you think riding a bike or using public transport is like having a horse and cart? The more advanced countries are the ones improving their public transport and putting bike lanes everywhere. Never mind.
It’s only ever a minority that are successful in business in any field. By “plenty of people” I mean as many people as you can expect to make a business work in any field.
So far it has been possible to increase income year on year since the early 2000s, and people have managed to do that. I am not the best at what I do and have managed it. People who haven’t been able to succeed have been saying what you’re saying since 2010 at least. I thought you were “what happened to taking responsibility for your own actions/ failings” guy?
-
And there's a heap of denial. Most people aren't, so don't use "plenty of people" which is the minority, as your supporting argument.
Some people still ride horses and drive wagons, some ride bicycles or use public transportation, and they are doing just fine without an automobile.
Microstock as a stable or reliable income or even side income, where someone can get in and make some extra money, is DEAD! We're going into over ten years of decline.
Lol, you think riding a bike or using public transport is like having a horse and cart? The more advanced countries are the ones improving their public transport and putting bike lanes everywhere. Never mind.
It’s only ever a minority that are successful in business in any field. By “plenty of people” I mean as many people as you can expect to make a business work in any field.
So far it has been possible to increase income year on year since the early 2000s, and people have managed to do that. I am not the best at what I do and have managed it. People who haven’t been able to succeed have been saying what you’re saying since 2010 at least. I thought you were “what happened to taking responsibility for your own actions/ failings” guy?
I'll try to make this easier for you to understand. Everyone doesn't own or drive a car. And they are doing just fine. Some people can't afford a car and they are also doing just fine. Plenty of people, that is. They never transitioned into what replaced the horse and buggy.
By saying Plenty of People, you would seem to mean most people. And the fact is, most people in microstock are not doing Just Fine. Most who used to be here and most who used to make supplemental income, have left, quit or moved to some other way of making money from their work.
What did I say about myself or personal responsibility? Where did that come from? I earn what I deserve, I'm not the one whining and complaining endlessly on the forum about how bad things are, or how we should get more, or how the market is dead. I'm just pointing out that people are not doing just fine.
And oh yes, Microstock is dead from the perspective of making money for someone, investing their time on equipment, making images, working to produce new images, paying models, or traveling, and also licensing the software. For most people Microstock is dead and AI is not going to kill it, because the business and trend that was beneficial for artists, is already over.
I stopped following this, but yes, you're correct, things have been going downhill since at the least 2012
(https://i.postimg.cc/cHpLzk3H/msg_earnings_poll_2012-2020_1000px.jpg)
Looks like plenty of people are not doing just fine with Microstock, like they once did.
(https://i.imgflip.com/1i775j.jpg)
ps Adobe continues to rise since they took over Fotolia. That's what I'd call doing just fine.
-
I'll try to make this easier for you to understand. Everyone doesn't own or drive a car. And they are doing just fine. Some people can't afford a car and they are also doing just fine. Plenty of people, that is. They never transitioned into what replaced the horse and buggy.
.
not that it really matters, but
https://edc.nyc/article/new-yorkers-and-their-cars
-
I'll try to make this easier for you to understand. Everyone doesn't own or drive a car. And they are doing just fine. Some people can't afford a car and they are also doing just fine. Plenty of people, that is. They never transitioned into what replaced the horse and buggy.
.
not that it really matters, but
https://edc.nyc/article/new-yorkers-and-their-cars
San Francisco is very car free also. https://sf.streetsblog.org/2014/08/15/car-free-households-are-booming-in-san-francisco/
-
I just got an email from SS titled: Contributor earnings now reflect generative AI Here's the first paragraph of the email:
News for artist recognition in advanced technology worldwide, and news for Shutterstock contributors!
You will now accrue royalties when your IP is used in the training of AI-generative models or used for licensing of generative assets created using Shutterstock’s software. Contributing artists can view their earnings in their account in the Earnings Summary 'By month' tab as 'Contributor fund.'
...
, but otherwise, I will not allow that, when given the option.
problem is, you've already given them permission according to the TOS you agreed to. SS may choose to allow people to opt out but haven't done so yet
I understand that.
This is what SS specified in their FAQ:
Can I opt out of having my content included in future datasets / data deals?
Yes, in the coming months we will be adding an option in the contributor account settings that will allow you to opt out of having your content included in future datasets, also known as data deals.
Translates to "when we are done processing your images you will be able to opt out"
I don't care what stock does with my photos, let your intellect learn. I think that this will only add ads in Google for my work or increase the rating on the stock. Very often I look for some of my old works, and then for some reason they are sold. On the one hand, events are not related, and on the other hand, money comes to me.
I don’t understand those people who are going to refuse to have their intellect learn from their work, these people are either very greedy or narrow-minded.
-
I'll try to make this easier for you to understand. Everyone doesn't own or drive a car. And they are doing just fine. Some people can't afford a car and they are also doing just fine. Plenty of people, that is. They never transitioned into what replaced the horse and buggy.
.
not that it really matters, but
https://edc.nyc/article/new-yorkers-and-their-cars
San Francisco is very car free also. https://sf.streetsblog.org/2014/08/15/car-free-households-are-booming-in-san-francisco/
How do the majority of people who made income from microstock in 2012 do ten years later?
-
...
By saying Plenty of People, you would seem to mean most people...
You thought I believed most people who have tried/ are doing microstock are successful at it? Lol
You’ve been here long enough to know there are almost no professionals who do this full time left on this forum. Much fewer than there used to be. Honestly I am not surprised. So I am not particularly bothered by what the chart says (even if it does seem to show SS and AS making more in 2019 than in 2013 so where’s the “We're going into over ten years of decline”?).
My weekly rank has moved very little on Adobestock over the last 10 years. I keep making more overall each year so I have to assume there are the same number of people doing better than me (all those ranked above me). The specific faces may have changed but the total number of people doing well seems to be similar.
-
How do the majority of people who made income from microstock in 2012 do ten years later?
Made me curious. About 55% up rolling 12 month total for November 2012 vs November 2022
-
How do the majority of people who made income from microstock in 2012 do ten years later?
Made me curious. About 55% up rolling 12 month total for November 2012 vs November 2022
Do not forget that the dollar inflates. What was the inflation rate in 10 years? Here, downvote it.
-
How do the majority of people who made income from microstock in 2012 do ten years later?
down about 10% since 2012, but next 5 years increased over 2012 by 50%
-
How do the majority of people who made income from microstock in 2012 do ten years later?
Made me curious. About 55% up rolling 12 month total for November 2012 vs November 2022
Do not forget that the dollar inflates. What was the inflation rate in 10 years? Here, downvote it.
An average of just under 2.5% a year. You know there's no downvote feature, right?
-
Do not forget that the dollar inflates. What was the inflation rate in 10 years? Here, downvote it.
There are calculators all over the interent but I went ahead and did it for you. Something over 20% increase adjusted. Of course the last year has been crazy for inflation compared to previous years.
-
In 10 years the microstock business as we know it will not exist, 90% of the regular clients of the agencies will stop buying subscriptions and will generate their own images using artificial intelligence programs. What is going to happen in the future is that little by little the sales of microstock will disappear and many people will give up and dedicate themselves to something else. One after another the agencies will disappear or declare bankruptcy.
-
In 10 years the microstock business as we know it will not exist, 90% of the regular clients of the agencies will stop buying subscriptions and will generate their own images using artificial intelligence programs. What is going to happen in the future is that little by little the sales of microstock will disappear and many people will give up and dedicate themselves to something else. One after another the agencies will disappear or declare bankruptcy.
I think ten years is optimistic
-
... to keep the point, my last post: Food for thought
https://luisafumi-digitalart.com/blog/2022/12/20/food-for-thought/ (https://luisafumi-digitalart.com/blog/2022/12/20/food-for-thought/)
(https://luisafumi-digitalart.com/blog/wp-content/uploads/2022/12/brain2.jpg)
... and more to come
-
https://www.freepik.com/author/dembaxx (https://www.freepik.com/author/dembaxx) here's a portfolio made entirely with AI tools. Far down to the oldest "creations", the images look like crap. But the newer ones are increasingly better. Have a look at the captions and keywords, for a good laugh.
-
In 10 years the microstock business as we know it will not exist, 90% of the regular clients of the agencies will stop buying subscriptions and will generate their own images using artificial intelligence programs. What is going to happen in the future is that little by little the sales of microstock will disappear and many people will give up and dedicate themselves to something else. One after another the agencies will disappear or declare bankruptcy.
I think ten years is optimistic
or wishful thinking - the agencies are adapting to new technologies, while many here are whinging rather than exploring how they can move with the times - again - dancing with elephants
-
... to keep the point, my last post: Food for thought
https://luisafumi-digitalart.com/blog/2022/12/20/food-for-thought/ (https://luisafumi-digitalart.com/blog/2022/12/20/food-for-thought/)
(https://luisafumi-digitalart.com/blog/wp-content/uploads/2022/12/brain2.jpg)
... and more to come
intriguing post! a great series of blogs about future of AI at https://www.cold-takes.com/most-important-century/ (https://www.cold-takes.com/most-important-century/)
-
...
By saying Plenty of People, you would seem to mean most people...
You thought I believed most people who have tried/ are doing microstock are successful at it? Lol
You’ve been here long enough to know there are almost no professionals who do this full time left on this forum. Much fewer than there used to be. Honestly I am not surprised. So I am not particularly bothered by what the chart says (even if it does seem to show SS and AS making more in 2019 than in 2013 so where’s the “We're going into over ten years of decline”?).
My weekly rank has moved very little on Adobestock over the last 10 years. I keep making more overall each year so I have to assume there are the same number of people doing better than me (all those ranked above me). The specific faces may have changed but the total number of people doing well seems to be similar.
Maybe I misunderstood your position. Yes, people who are busy making money and working, don't spend a lot of time on the forum. I'm a perfect example of that. Obviously, a hobbyist.
While I appreciate your correct humor, I'll say, most people who work hard and are smart and pay attention to the market and do high quality work, are successful. It's not easy money.
I did something by accident and my Adobe rank keeps climbing, nearly every week. Not the weekly, I don't care, but my Lifetime. Some kind of minor miracle. Of course when I started back, when Adobe bought them, that means I was pretty much living at the bottom of the cesspool, and there was nowhere to go but up?
WILM got me interested in watching that, I never did until the last few months. It moves up 500 every now and then, so the whole lifetime is in tiers. I'm probably just passing people who stopped uploading in 2012? ;D
-
What is the image size and resolution like on some of these AI generators? I one better than the other when it comes to that? DALLE vs Midjourney vs ??
-
What is the image size and resolution like on some of these AI generators? I one better than the other when it comes to that? DALLE vs Midjourney vs ??
No experience with Midjourney I'm not sure how to get in or do anything, so I just took a pass. Maybe someone can share the details?
DALL-E2 1024 x 1024 PNG with a little color sample bar in the lower right. I don't know if it's just me, but the lines in illustrations are not sharp and will get "quality" rejections at most places. People who know more than I do, say, 4x with Topaz Gigapixel AI or some other Topaz, edit and reduce to Microstock size.
I believe them, but I'm not spending $?? or full price $99.99 to make AI images that will sell for fractions of a dollar. If I thought I could get 400 DLs in a year from AI (1,000 on SSTK) images, I could justify that? 👍
-
What is the image size and resolution like on some of these AI generators? I one better than the other when it comes to that? DALLE vs Midjourney vs ??
Hi, you got plenty more AI generators but in my opinion the 3 Big at the moment are Dalle, Midjourney and stable diffusion. Also there's a buzz about Playground Ai but i never tried. I am currently using Midjourney subscription and free SD 2.1. via Github/colab.
In terms of Size/ resolution:
1) Dalle- 1024x1024
2) Midjourney v4 : upscale 1024X1024, beta scale 2048x2048 but you loose detail in 2nd
(you can improve detail directly in Prompt using arguments like ultra detail, super detailed, Photorealistic, etc... and request best quality which costs 2 times more)
3a)"Outdated" Disco diffusion / Stable Diffusion 1.5 : 1668x768 with colab pro+
3b)Stable diffusion 2.1 : 768x 768 or 1280x720 (sometimes errors in 2nd)
For both you can increase detail and sharp changing some parameters (example: 25 steps basic, 350 steps more detail, also you consume more power and time)
Note: After... you can upscale with AI tools but you got better results depending the type of image if it is photo realistic, cartoons/anime, 3d render etc...Sometimes it's better to combine 2/3 AI upscale tools but this depends really on the image itself and of course trial error process.
-
One AI I had not heard about before, Lexica art, built on stable diffusion and returning high end images, check the pricing though. You can begin to understand the 'game changing' talk about this new technology.
https://lexica.art/
-
One AI I had not heard about before, Lexica art, built on stable diffusion and returning high end images, check the pricing though. You can begin to understand the 'game changing' talk about this new technology.
https://lexica.art/
Thanks for sharing that, I had not heard about this one as well. Seeing how fast AIs improve I have been feeling a bit depressed about my microstock future lately, thinking I'd be jobless sooner than I had thought, but this is actually making me feel a bit more optimistic again that it might still take a while till I will be completely replaceable. As always I have been checking my direct competition and the results you get when searching for example for "French Bulldog" are a huge contrast to the amazing images this site shows you on the first page.
(https://lexica-serve-encoded-images2.sharif.workers.dev/md/13663c64-b808-483a-9664-044b0f2993bb) (https://lexica-serve-encoded-images2.sharif.workers.dev/md/0cf5b53d-0cdd-40c9-ac1c-d0eeaa7a5dac) (https://lexica-serve-encoded-images2.sharif.workers.dev/md/0ac66557-ea6e-4522-8a52-61bbc03ff15e) (https://lexica-serve-encoded-images2.sharif.workers.dev/md/87524412-1369-4f30-bd9c-efcfcfeae2b9) (https://lexica-serve-encoded-images2.sharif.workers.dev/md/701c6516-1369-4d28-83f4-d9a7d2f5b31b) (https://lexica-serve-encoded-images2.sharif.workers.dev/md/7270fbee-94a7-4702-9785-40d2907538bb) (https://lexica-serve-encoded-images2.sharif.workers.dev/md/07aef89f-36f5-4643-b81d-5a5b4b8cb2fa) (https://lexica-serve-encoded-images2.sharif.workers.dev/md/e2e4bd21-29f1-4172-bd03-5e5fd20eac70)
Not all of the results are as bizzare, but at least among the photorealistic results, none really looks right.
Eventually AI will get there and I will be out of an income, but with any luck I still have some time.
-
Tony Northrup says AI will eventually replace 95% of stock photography.
https://www.youtube.com/watch?v=8VRbt8GufeY (https://www.youtube.com/watch?v=8VRbt8GufeY)
I think he's half right. Editorial will remain and video will endure. When the technology is perfected synthesized photo realistic images will work for many users. AI replacing cameras is much like drum machines replacing drums. Cameras and drums will live on.. but making money with them will get harder.
-
Tony Northrup says AI will eventually replace 95% of stock photography.
https://www.youtube.com/watch?v=8VRbt8GufeY (https://www.youtube.com/watch?v=8VRbt8GufeY)...
income from existing portfolios will continue - SS would need almost 4 BILLION AI images to form 95% of their offering (assuming zero new images sent in)
the biggest factor will be how many abandon stock altogether, which should remain small for some time
-
Finn,
I only use lexica to find themes and some useful guides to my prompts that i like. I think Stable Diffusion can be more powerful with trained models or with image references.
I agree, eventually AI will get there... but it has been quite a speed race. I am using my memory here so it may not be precise but in 2022 we had:
-Disco diffusion v3, v4; Stable Diffusion 1.1,1.2,1.3,1.4,1.5,2 and 2.1;
-Midjourney v2,v3,v4a,v4b
I just tried with a simple text prompt of "french bulldog sit in XVII century Throne" and use some technical arguments without image reference (see images). Probably i could tune a little better but the result is ok for at least showing concept to a client before photo shooting. AI is still struggling to learn the teeth, feet and hands since there's still lack of knowledge of anatomy and right positions of any animal.
To be honest i don't know how much time AI will need but it's getting better everyday since it learns concepts, styles and references 24/7.
-
Finn,
I only use lexica to find themes and some useful guides to my prompts that i like. I think Stable Diffusion can be more powerful with trained models or with image references.
I agree, eventually AI will get there... but it has been quite a speed race. I am using my memory here so it may not be precise but in 2022 we had:
-Disco diffusion v3, v4; Stable Diffusion 1.1,1.2,1.3,1.4,1.5,2 and 2.1;
-Midjourney v2,v3,v4a,v4b
I just tried with a simple text prompt of "french bulldog sit in XVII century Throne" and use some technical arguments without image reference (see images). Probably i could tune a little better but the result is ok for at least showing concept to a client before photo shooting. AI is still struggling to learn the teeth, feet and hands since there's still lack of knowledge of anatomy and right positions of any animal.
To be honest i don't know how much time AI will need but it's getting better everyday since it learns concepts, styles and references 24/7.
Yes, these look great, but they look like paintings to me, not like real photos, which was what I was talking about (sorry if I didn't get that across correctly. It was what I meant by "photorealistic", but maybe I used the wrong word). In regards of paintings AI is - sadly - already kicking ass. I feel so sorry for painting artists, even though I know as a photographer I will be in the same boat soon. I have seen some mind blowing AI generated French Bulldog paintings on Adobe. But when it comes to photos it's still struggling, at least for now.
-
I'll try to make this easier for you to understand. Everyone doesn't own or drive a car. And they are doing just fine. Some people can't afford a car and they are also doing just fine. Plenty of people, that is. They never transitioned into what replaced the horse and buggy.
.
not that it really matters, but
https://edc.nyc/article/new-yorkers-and-their-cars
San Francisco is very car free also. https://sf.streetsblog.org/2014/08/15/car-free-households-are-booming-in-san-francisco/
How do the majority of people who made income from microstock in 2012 do ten years later?
70% drop in income from what I made in 2012.
-
So who is allowing AI Generated art submissions? I think Adobe Stock and Dreamtime are. Others?
-
So who is allowing AI Generated art submissions? I think Adobe Stock and Dreamtime are. Others?
I'd say all agencies allow it expect the ones who have officially stated that they don't. So that would be only Shutterstock/Bigstock, though they do their own AI thing and iStock/Getty, but I think they limited it to only no AI generated images with models? Unless I misunderstood their mail.
In the end it doesn't matter all that much. A rule only makes sense when you can enforce is. It's becoming harde to tell whether an image has been drawn or AI generated by the day, so how are reviewers to tell...?
-
I'll try to make this easier for you to understand. Everyone doesn't own or drive a car. And they are doing just fine. Some people can't afford a car and they are also doing just fine. Plenty of people, that is. They never transitioned into what replaced the horse and buggy.
.
10X
not that it really matters, but
https://edc.nyc/article/new-yorkers-and-their-cars
San Francisco is very car free also. https://sf.streetsblog.org/2014/08/15/car-free-households-are-booming-in-san-francisco/
How do the majority of people who made income from microstock in 2012 do ten years later?
-
AI friend or foe?, on my blog
A very brief history of art (part 1 of 5)
https://luisafumi-digitalart.com/blog/2023/01/05/ai-friend-or-foe/ (https://luisafumi-digitalart.com/blog/2023/01/05/ai-friend-or-foe/)
(https://luisafumi-digitalart.com/blog/wp-content/uploads/2023/01/POTTERY-s.jpg)
Enjoy
-
AI friend or foe?, on my blog
A very brief history of art (part 1 of 5)
https://luisafumi-digitalart.com/blog/2023/01/05/ai-friend-or-foe/ (https://luisafumi-digitalart.com/blog/2023/01/05/ai-friend-or-foe/)
Enjoy
I'd like to point out a more modern version which I'll assume everyone here understands.
Digital Cameras and I shouldn't have to write more than those two words.
But I need to include, computer drawn illustrations using a tablet . No paint, pens, pencils, ink, or chalk or anything.
AI will not kill art or individual creations.
-
AI friend or foe?, on my blog
A very brief history of art (part 1 of 5)
https://luisafumi-digitalart.com/blog/2023/01/05/ai-friend-or-foe/ (https://luisafumi-digitalart.com/blog/2023/01/05/ai-friend-or-foe/)
Enjoy
I'd like to point out a more modern version which I'll assume everyone here understands.
Digital Cameras and I shouldn't have to write more than those two words.
But I need to include, computer drawn illustrations using a tablet . No paint, pens, pencils, ink, or chalk or anything.
AI will not kill art or individual creations.
I still can't wrap my hand around how some people really think AI art will "just" change traditional art like digital camera mostly replaced cameras that capture images on photographic film or are like tablets that are just an additional medium to drawing on paper or canvas. Those are two completely different things.
These were technoligical advancements that helped you in your task. AI does the art for you. It's not a tool that helps an artist, it's a replacement.
A more correct comparison in advancement in technology would be for example a telephone and switchboard operators. Technology advanced, it was able to do their job, so they were replaced by technology. No one needs a telephone or switchboard operator these days because of "authentic" or "nostalgic" reasons. Technology can do it faster, better and cheaper than humans - You're out of your job.
I am not saying AI will replace all art, but it will certainly cause a decrease in artists when they have a harder time to make a living from art (which was already difficult before AI art!) as AI is cheaper and microstock photography and drawings are the easiest replaced by AIs and the first to go.
-
Generative AI will kill the business of illustrators as we know it in less than 6 months, specially the ones who make their living from stock illustrations. Stock photography will last maybe one more year. Most agencies will go out of business.
-
Generative AI will kill the business of illustrators as we know it in less than 6 months, specially the ones who make their living from stock illustrations. Stock photography will last maybe one more year. Most agencies will go out of business.
any luddites willing to put real $ behind their apocalyptic predictions?
-
These were technoligical advancements that helped you in your task. AI does the art for you. It's not a tool that helps an artist, it's a replacement.
Gameover explains some points with "AI friend or foe?", on her blog with a very brief history of art.
She calls our attention to the word ‘artificial’ with comes from the greek philosopher Aristotle in his Rhetoric: artificiality (the quality of being made or produced by human beings rather than occurring naturally.) - very nice! ;)
AI is a tool (1) and cannot do "the Art for you" (2).
1) It's hard in a post to explain in detail such issue regarding onto-technologies of the body but let me try to put it in this way: AI is an extension of your body not a replacement. In the same way that you don't replace your hand with a brush, you use a brush to paint. The brush doesn't paint by itself - you need a human to do it. In AI generator you need to type and work with a prompt: sort of digital code that machine can process your request.
Henry Ward Beecher once wrote, “A tool is but the extension of a man’s hand, and a machine is but a complex tool.” This fits here in line of scientific research into “embodiment”. But there's “disembodiment” in AI too. Which basically means that AI feeds on the output to become more efficient- it collects the data of your image to improve future Artworks. So AI is a Tool with “embodiment” and “disembodiment”features.
2) AI cannot do "art" for Humans. Art is a representation or presentation of an idea in a shape/form. AI doesn't have ideas of its own, Humans do. Therefore AI cannot do Art but can be extremely efficient in drawing, playing music, etc. Best alternative is that AI it's a performer conducted by an artist. A tool to improve your Artwork just like photoshop is using with mouse and clicks interface instead of a Prompt.
A more correct comparison in advancement in technology would be for example a telephone and switchboard operators.
In my opinion that is a bad comparison because switchboard operators don't create ideas like artists. The task/job was simple connecting cables. They were a kind of cogwheel in a communication system. New technologies made it faster, better and cheaper than humans. Now we all use a Smartphone with social media.
We don't have switchboard operators anymore but how much people you think have been hired in communication companies and social media (youtube, facebook, twitter, tiktok, instagram, whatsup, signal, etc) last 20 years?
None of social media companies existed before 2004 and according to google there are 142,282 people employed in the Social Networking Sites industry in the US as of 2023. Let's not forget about UGC creators which in fact creates everyday content and get paid to feed the channel by social media, ads or product reviews...so a lot jobs here too.
I am not saying AI will replace all art, but it will certainly cause a decrease in artists when they have a harder time to make a living from art (which was already difficult before AI art!) as AI is cheaper and microstock photography and drawings are the easiest replaced by AIs and the first to go.
Things are evolving so to expect this market not to change is to stand still in time. I do agree at some point with Gameover analysis where "plenty of ‘artists’ will inevitably lose their jobs as soon as their customers learn how to order a piece of art directly at the source, a skilled and most likely way cheaper AI."
I think artists that see potential of AI in their work will continue the path. I already see a lot of UGC creators with thousands of followers only doing AI too.
This week i was approached twice by NFT collectors that want to buy my AI artwork so this can be a new market too. Others will go more for news/events and street life photography (there will always be in demand since AI cannot produce reality). Companies of every kind are hiring people to deal with social media, specially creatives that can do all in one: illustrations/ Shoot photos/videos and editing them.
At the end eventually people will adapt to new reality.
-
..
In my opinion that is a bad comparison because switchboard operators don't create ideas like artists...
There are two things going on here. Art isn't going to die but jobs for commercial illustrators will (largely) as they aren’t the ones (for the most part) creating ideas. That’s the client/ art director, and they wont need the artist/ illustrator to execute those ideas any more.
-
These were technoligical advancements that helped you in your task. AI does the art for you. It's not a tool that helps an artist, it's a replacement.
Gameover explains some points with "AI friend or foe?", on her blog with a very brief history of art.
She calls our attention to the word ‘artificial’ with comes from the greek philosopher Aristotle in his Rhetoric: artificiality (the quality of being made or produced by human beings rather than occurring naturally.) - very nice! ;)
AI is a tool (1) and cannot do "the Art for you" (2).
1) It's hard in a post to explain in detail such issue regarding onto-technologies of the body but let me try to put it in this way: AI is an extension of your body not a replacement. In the same way that you don't replace your hand with a brush, you use a brush to paint. The brush doesn't paint by itself - you need a human to do it. In AI generator you need to type and work with a prompt: sort of digital code that machine can process your request.
Henry Ward Beecher once wrote, “A tool is but the extension of a man’s hand, and a machine is but a complex tool.” This fits here in line of scientific research into “embodiment”. But there's “disembodiment” in AI too. Which basically means that AI feeds on the output to become more efficient- it collects the data of your image to improve future Artworks. So AI is a Tool with “embodiment” and “disembodiment”features.
2) AI cannot do "art" for Humans. Art is a representation or presentation of an idea in a shape/form. AI doesn't have ideas of its own, Humans do. Therefore AI cannot do Art but can be extremely efficient in drawing, playing music, etc. Best alternative is that AI it's a performer conducted by an artist. A tool to improve your Artwork just like photoshop is using with mouse and clicks interface instead of a Prompt.
A more correct comparison in advancement in technology would be for example a telephone and switchboard operators.
In my opinion that is a bad comparison because switchboard operators don't create ideas like artists. The task/job was simple connecting cables. They were a kind of cogwheel in a communication system. New technologies made it faster, better and cheaper than humans. Now we all use a Smartphone with social media.
We don't have switchboard operators anymore but how much people you think have been hired in communication companies and social media (youtube, facebook, twitter, tiktok, instagram, whatsup, signal, etc) last 20 years?
None of social media companies existed before 2004 and according to google there are 142,282 people employed in the Social Networking Sites industry in the US as of 2023. Let's not forget about UGC creators which in fact creates everyday content and get paid to feed the channel by social media, ads or product reviews...so a lot jobs here too.
I am not saying AI will replace all art, but it will certainly cause a decrease in artists when they have a harder time to make a living from art (which was already difficult before AI art!) as AI is cheaper and microstock photography and drawings are the easiest replaced by AIs and the first to go.
Things are evolving so to expect this market not to change is to stand still in time. I do agree at some point with Gameover analysis where "plenty of ‘artists’ will inevitably lose their jobs as soon as their customers learn how to order a piece of art directly at the source, a skilled and most likely way cheaper AI."
I think artists that see potential of AI in their work will continue the path. I already see a lot of UGC creators with thousands of followers only doing AI too.
This week i was approached twice by NFT collectors that want to buy my AI artwork so this can be a new market too. Others will go more for news/events and street life photography (there will always be in demand since AI cannot produce reality). Companies of every kind are hiring people to deal with social media, specially creatives that can do all in one: illustrations/ Shoot photos/videos and editing them.
At the end eventually people will adapt to new reality.
excellent, well written 👏 👏
-
I am not saying AI will replace all art, but it will certainly cause a decrease in artists when they have a harder time to make a living from art (which was already difficult before AI art!) as AI is cheaper and microstock photography and drawings are the easiest replaced by AIs and the first to go.
I don't think AI will ever be able to replace editorial stock photography (which is a big chunk of how I make a living out of this) simply because no one can make up a prompt to see what I see in my neighbourhood or street or a protest or a rally and come up with an image that depicts the scene accurately. It's simply impossible to feed that data to a dall-e or whatever obscene thing that replaces it in the future. That will only happen if there are actual robots on the streets taking pictures and I think we're a wee bit away from that. But generic stock photography like an apple with a white background? Yeah that crap isn't going to sell so much.
-
AI friend or foe?, on my blog
A very brief history of art: growing up (part 2 of 5)
https://luisafumi-digitalart.com/blog/2023/01/11/ai-friend-or-foe-2-of-5/ (https://luisafumi-digitalart.com/blog/2023/01/11/ai-friend-or-foe-2-of-5/)
(https://luisafumi-digitalart.com/blog/wp-content/uploads/2023/01/gutenberg-s.jpg)
hope you like it
-
AI friend or foe?, on my blog
A very brief history of art: growing up (part 2 of 5)
https://luisafumi-digitalart.com/blog/2023/01/11/ai-friend-or-foe-2-of-5/ (https://luisafumi-digitalart.com/blog/2023/01/11/ai-friend-or-foe-2-of-5/)
(https://luisafumi-digitalart.com/blog/wp-content/uploads/2023/01/gutenberg-s.jpg)
hope you like it
another great post - your examples truly showing there's 'nothing new under the sun' (except everything)
“But where are the buggy-whip makers of yesteryear?”
— apologies to Francois Villon
-
AI friend or foe?, on my blog
A very brief history of art: growing up (part 2 of 5)
https://luisafumi-digitalart.com/blog/2023/01/11/ai-friend-or-foe-2-of-5/ (https://luisafumi-digitalart.com/blog/2023/01/11/ai-friend-or-foe-2-of-5/)
hope you like it
Your AI works are much better than what I get from DALL-E2. And I have read where other had to work at the descriptions, adjustment and created merged variations, until they got what they wanted. It isn't as if someone can say, make me a "photo quality image of a triple cheeseburger on a plain plate with a wood background" and they will have the perfect triple cheeseburger image for all time.
(https://i.postimg.cc/JhtPGdXf/cheeseburger-example.jpg)
And that was one of the better results.
And just like people don't need paint, brushes or canvas to make an image that looks like a painting, because they can do that on a computer or a tablet, people will not instantly, without any experience or ability, create a masterpiece, because some AI generated image, will just dump those out for every set of prompts.
Computers have made people more efficient, digital things have made us more productive for less money in less time. AI isn't autonomous. You need someone tell and directing the creation. AI created by a computer, can't be copyrighted. There's another argument against this science. But since the human directs it, much like someone sets their camera, even if it's auto exposure and auto WB and auto focus, there's a human pushing the button.
..
In my opinion that is a bad comparison because switchboard operators don't create ideas like artists...
There are two things going on here. Art isn't going to die but jobs for commercial illustrators will (largely) as they aren’t the ones (for the most part) creating ideas. That’s the client/ art director, and they wont need the artist/ illustrator to execute those ideas any more.
Ah, so professional photographers, who worked with film, bulky manual cameras, hand focusing and setting, and then in a dark room, and manually editing, and with enlargers, will be replaced by art directors/clients doing the work, executing the ideas. They won't need photographers anymore. ;D Because we have digital cameras and digital editors.
Generative AI will kill the business of illustrators as we know it in less than 6 months, specially the ones who make their living from stock illustrations. Stock photography will last maybe one more year. Most agencies will go out of business.
any luddites willing to put real $ behind their apocalyptic predictions?
I don't claim to know the future... but I don't think it's going to be as bad as some people are making things out to be. 6 months? Hardly.
We are witnessing another level in the evolution of creating images and art.
-
AI friend or foe?, on my blog
A very brief history of art: growing up (part 2 of 5)
https://luisafumi-digitalart.com/blog/2023/01/11/ai-friend-or-foe-2-of-5/ (https://luisafumi-digitalart.com/blog/2023/01/11/ai-friend-or-foe-2-of-5/)
(https://luisafumi-digitalart.com/blog/wp-content/uploads/2023/01/gutenberg-s.jpg)
hope you like it
Guttenberg is essential to understand where we came from and where we are going. It is at the moment when the reproducible invades the field formerly occupied by the aura, moment of its radical destruction, that aura can appear and become visible to the modern eye. You highlighted very well and in a concise way:
"yet surprisingly enough Gutenberg’s felony didn’t kill the literature at all; it just stripped off its aura of holy and arcane and focused it more on the contents than on the form."
I really liked the post!
-
..
In my opinion that is a bad comparison because switchboard operators don't create ideas like artists...
There are two things going on here. Art isn't going to die but jobs for commercial illustrators will (largely) as they aren’t the ones (for the most part) creating ideas. That’s the client/ art director, and they wont need the artist/ illustrator to execute those ideas any more.
Things will be different since AI causes disruption.
There is a book called "Human + machine : reimagining work in the age of AI" published in 2018 from Paul R. Daugherty, H. James Wilson. I'm not advertising it, but I personally like some of the visions or insights the book has.
AI is already or will be in every sector of business. I won't spoil the reading too but if there's repetition, replication or redundancy in the business its a clue that tasks/processes will change. One of the things that call my attention was the scalability of companies with AI and Personalization for AI in product and Service design. It means that many companies will make personalized ads to an individual or a small group of consumers instead of one for all.
Example: instead of one "coca-cola" video or 10 posters for publicity to all community there will be hundreds or thousands of them spread according the data of the consumer...
The increase of advertisements will be greater in quantity and will be more diverse too. This is already happening since there's UGC creators are making videos of product reviews, unbox, or ads to spread into is own community of followers.Who hasn't seen a video of a photographer reviewing a new camera on ytube yet?
note: btw there's also a chapter with Nike as example for designer and how they worked with AI.
-
Meta and Shutterstock will expand their business partnership, allowing the social media company to train its artificial intelligence and machine learning systems on Shutterstock’s collection of millions of images.
The two companies have announced what they categorize as a “significant partnership,” with the goal of bringing Meta’s artificial intelligence (AI) innovation to the forefront using the power of Shutterstock’s massive content library.
https://petapixel.com/2023/01/12/meta-will-use-shutterstocks-image-library-to-train-its-ai/
-
Does anyone know some good resources explaing how generative AI art works ?
I was wondering if the AI image is just a mosaic of tiny parts of other images, or does it "paint" a new image from scratch ? For instance let's say we have a prompt where the main subject is a cat. Is it possible that an eye or nose of that cat is just taken from some photograph in the internet ?
-
Just played with Dall E again. These engines are definitely not all created equal. Is Dall E abandonware now or what? Midjouney is sooo much better. And with Dall E I get the distinct impression that they always crop crucial parts of the image to force you to use more credits to extend the render.
-
Does anyone know some good resources explaing how generative AI art works ?
A good start would be looking up "neural networks".
I was wondering if the AI image is just a mosaic of tiny parts of other images, or does it "paint" a new image from scratch ? For instance let's say we have a prompt where the main subject is a cat. Is it possible that an eye or nose of that cat is just taken from some photograph in the internet ?
No, its derived from thousands of cat eyes (or whatever) used to build up a sort of 'concept' of cat's eye, and then drawing a new one accordingly. Which also accounts pretty well for the funny notion the AI seems to have of "hand" ::)
-
Just played with Dall E again. These engines are definitely not all created equal. Is Dall E abandonware now or what? Midjouney is sooo much better. And with Dall E I get the distinct impression that they always crop crucial parts of the image to force you to use more credits to extend the render.
Yes I said that a while back, about how DALL-E2 does unusual crops, too close, which cuts off parts of the image and someone here immediately disagreed.
I also see that it seems to add flaws and strange inclusions, which isn't impossible to fix, but I don't know why so many images have strange objects or imperfections? DALL-E2 is fun and at free 15 sets a month, I'm happy with the cartoonish illustrations that I get. Faces are often twisted, distorted and the eyes wonky, they look like a Picasso.
I hadn't considered extending the render as a way to repair the first images. Thanks for the reminder.
-
...
AI is already or will be in every sector of business. I won't spoil the reading too but if there's repetition, replication or redundancy in the business its a clue that tasks/processes will change. One of the things that call my attention was the scalability of companies with AI and Personalization for AI in product and Service design.
...
i could have used an AI when i did computer consulting - one company was sending out 12 copies of a particular report - after days of interviews I discovered only 2 recipients actually used the report -the others just filed it 'in case they needed it'. in another case i built a system to track rfid on freight cars to show that buyers were using the cars for free storage - costing my client millions. an Ai could have done the analysis directly. in either case i would have been freed to work on more interestig problems
-
Does anyone know some good resources explaing how generative AI art works ?
I was wondering if the AI image is just a mosaic of tiny parts of other images, or does it "paint" a new image from scratch ? For instance let's say we have a prompt where the main subject is a cat. Is it possible that an eye or nose of that cat is just taken from some photograph in the internet ?
some ML use mosaics, but not in th e way you describe -
anyone remember 'El Topo' - it was the Rocky Horror of its day? - this shows stills from a movie that doesn't exist & explains how the AI works
https://www.nytimes.com/interactive/2023/01/13/opinion/jodorowsky-dune-ai-tron.html (https://www.nytimes.com/interactive/2023/01/13/opinion/jodorowsky-dune-ai-tron.html)
many other references/explanations posted several times in this thread
-
..
I hadn't considered extending the render as a way to repair the first images. Thanks for the reminder.
i've had about 50% success doing that
-
AI: friend or foe? (3 of 5) on my blog
A very brief history of art: today
https://luisafumi-digitalart.com/blog/2023/01/13/ai-friend-or-foe-3-of-5/ (https://luisafumi-digitalart.com/blog/2023/01/13/ai-friend-or-foe-3-of-5/)
(https://luisafumi-digitalart.com/blog/wp-content/uploads/2023/01/future-l.jpg)
have fun :D
-
AI: friend or foe? (3 of 5) on my blog
A very brief history of art: today
https://luisafumi-digitalart.com/blog/2023/01/13/ai-friend-or-foe-3-of-5/ (https://luisafumi-digitalart.com/blog/2023/01/13/ai-friend-or-foe-3-of-5/)
have fun :D
OK so how does that table stand on those legs? :o But that's the kind of thing that AI creates that's lacking science or physical logic. Not just picking, I think the things you have shown are very well done and attractive. Wait, does the right hand chair only have three legs? Or is that 5 or 6 legs?
Yeah, people in some of mine only have three fingers and a thumb.
-
What is the image size and resolution like on some of these AI generators? I one better than the other when it comes to that? DALLE vs Midjourney vs ??
No experience with Midjourney I'm not sure how to get in or do anything, so I just took a pass. Maybe someone can share the details?
DALL-E2 1024 x 1024 PNG with a little color sample bar in the lower right. I don't know if it's just me, but the lines in illustrations are not sharp and will get "quality" rejections at most places. People who know more than I do, say, 4x with Topaz Gigapixel AI or some other Topaz, edit and reduce to Microstock size.
I believe them, but I'm not spending $?? or full price $99.99 to make AI images that will sell for fractions of a dollar. If I thought I could get 400 DLs in a year from AI (1,000 on SSTK) images, I could justify that? 👍
That $99,99 is a plan for a year?
-
What is the image size and resolution like on some of these AI generators? I one better than the other when it comes to that? DALLE vs Midjourney vs ??
No experience with Midjourney I'm not sure how to get in or do anything, so I just took a pass. Maybe someone can share the details?
DALL-E2 1024 x 1024 PNG with a little color sample bar in the lower right. I don't know if it's just me, but the lines in illustrations are not sharp and will get "quality" rejections at most places. People who know more than I do, say, 4x with Topaz Gigapixel AI or some other Topaz, edit and reduce to Microstock size.
I believe them, but I'm not spending $?? or full price $99.99 to make AI images that will sell for fractions of a dollar. If I thought I could get 400 DLs in a year from AI (1,000 on SSTK) images, I could justify that? 👍
That $99,99 is a plan for a year?
DALL-E2 is 15 images a month for free, you need a phone number to verify your registration. One account only, virtual numbers don't work. (Google Voice for example) For those who pay, 115 credits for $15 = free is fun, that's as far as I go.
Someone else who pays will have to give you the accurate facts about Midjourney or others. I see ads for some that start at $49 a month.
-
AI: friend or foe? (3 of 5) on my blog
A very brief history of art: today
https://luisafumi-digitalart.com/blog/2023/01/13/ai-friend-or-foe-3-of-5/ (https://luisafumi-digitalart.com/blog/2023/01/13/ai-friend-or-foe-3-of-5/)
(https://luisafumi-digitalart.com/blog/wp-content/uploads/2023/01/future-l.jpg)
have fun :D
keep 'em coming! welcome balanced approach to luddite negativity!
-
First lawsuits against AI: https://www.prnewswire.com/news-releases/class-action-filed-against-stability-ai-midjourney-and-deviantart-for-dmca-violations-right-of-publicity-violations-unlawful-competition-breach-of-tos-301721869.html
-
Getty too: https://www.theverge.com/2023/1/17/23558516/ai-art-copyright-stable-diffusion-getty-images-lawsuit
-
First lawsuits against AI: https://www.prnewswire.com/news-releases/class-action-filed-against-stability-ai-midjourney-and-deviantart-for-dmca-violations-right-of-publicity-violations-unlawful-competition-breach-of-tos-301721869.html (https://www.prnewswire.com/news-releases/class-action-filed-against-stability-ai-midjourney-and-deviantart-for-dmca-violations-right-of-publicity-violations-unlawful-competition-breach-of-tos-301721869.html)
Have you seen the source?
If you read here
https://www.theverge.com/2023/1/16/23557098/generative-ai-art-copyright-legal-lawsuit-stable-diffusion-midjourney-deviantart (https://www.theverge.com/2023/1/16/23557098/generative-ai-art-copyright-legal-lawsuit-stable-diffusion-midjourney-deviantart)
the law firm seems to have no idea how AI works ;D
-
First lawsuits against AI: https://www.prnewswire.com/news-releases/class-action-filed-against-stability-ai-midjourney-and-deviantart-for-dmca-violations-right-of-publicity-violations-unlawful-competition-breach-of-tos-301721869.html (https://www.prnewswire.com/news-releases/class-action-filed-against-stability-ai-midjourney-and-deviantart-for-dmca-violations-right-of-publicity-violations-unlawful-competition-breach-of-tos-301721869.html)
Have you seen the source?
If you read here
https://www.theverge.com/2023/1/16/23557098/generative-ai-art-copyright-legal-lawsuit-stable-diffusion-midjourney-deviantart (https://www.theverge.com/2023/1/16/23557098/generative-ai-art-copyright-legal-lawsuit-stable-diffusion-midjourney-deviantart)
the law firm seems to have no idea how AI works ;D
That's something court will decide.
-
First lawsuits against AI: https://www.prnewswire.com/news-releases/class-action-filed-against-stability-ai-midjourney-and-deviantart-for-dmca-violations-right-of-publicity-violations-unlawful-competition-breach-of-tos-301721869.html (https://www.prnewswire.com/news-releases/class-action-filed-against-stability-ai-midjourney-and-deviantart-for-dmca-violations-right-of-publicity-violations-unlawful-competition-breach-of-tos-301721869.html)
Have you seen the source?
If you read here
https://www.theverge.com/2023/1/16/23557098/generative-ai-art-copyright-legal-lawsuit-stable-diffusion-midjourney-deviantart (https://www.theverge.com/2023/1/16/23557098/generative-ai-art-copyright-legal-lawsuit-stable-diffusion-midjourney-deviantart)
the law firm has no idea how AI works ;D
Yeah weird. I would have gone for arguing that the AI company has made commercial use of images without a commercial licence or permission from the copyright owner (which they have, even if no storage or image retention is involved).
Whether storage of information obtained through studying people’s images counts as infringement is, I guess, more iffy. Surely there’s no doubt the “model” the AI has of what an object or person looks like is derived from the study of other people’s copyright work, regardless of the level of processing involved, hence “21st-century collage tool” (yes, I do understand the original image isn't used in its original form but it IS process into information to create the "new" work).
-
First lawsuits against AI: https://www.prnewswire.com/news-releases/class-action-filed-against-stability-ai-midjourney-and-deviantart-for-dmca-violations-right-of-publicity-violations-unlawful-competition-breach-of-tos-301721869.html (https://www.prnewswire.com/news-releases/class-action-filed-against-stability-ai-midjourney-and-deviantart-for-dmca-violations-right-of-publicity-violations-unlawful-competition-breach-of-tos-301721869.html)
Have you seen the source?
If you read here
https://www.theverge.com/2023/1/16/23557098/generative-ai-art-copyright-legal-lawsuit-stable-diffusion-midjourney-deviantart (https://www.theverge.com/2023/1/16/23557098/generative-ai-art-copyright-legal-lawsuit-stable-diffusion-midjourney-deviantart)
the law firm has no idea how AI works ;D
Yeah weird. I would have gone for arguing that the AI company has made commercial use of images without a commercial licence or permission from the copyright owner (which they have, even if no storage or image retention is involved).
Whether storage of information obtained through studying people’s images counts as infringement is, I guess, more iffy. Surely there’s no doubt the “model” the AI has of what an object or person looks like is derived from the study of other people’s copyright work, regardless of the level of processing involved, hence “21st-century collage tool” (yes, I do understand the original image isn't used in its original form but it IS process into information to create the "new" work).
we human make the same (in a smaller scale... ) but we call it inspiration or learning or whatever ;)
-
That will be a really interesting and great law war. Most of points are questionable.
Surely there’s no doubt the “model” the AI has of what an object or person looks like is derived from the study of other people’s copyright work, regardless of the level of processing involved, hence “21st-century collage tool” (yes, I do understand the original image isn't used in its original form but it IS process into information to create the "new" work).
This, for example, seems a description of the process that any artist do before creating his own art: the study of other people copyright works. And it's perfectly legit.
It seems to me that the only point really against AI is:
Does it really USE section (or pixels) of other copyrighted works? Are there in the AI generated images any "PART" of other copyrighted works?
In last weeks I was sure that the correct answer should be NO, THERE ARE'NT ANY PIXEL OF COPYRIGHTED WORKS IN GENERATIVE AI IMAGES
... but I read a lot about AI engines in these last weeks, and I have to say that it's not really so clear to define what AI "understand and recreate" and what, at the contrary, AI "copy, even only partly"
The legal war probably will need to clarify first of all this point. And, probably, the answer would not the same for ANY AI engine
-
we human make the same (in a smaller scale... ) but we call it inspiration or learning or whatever ;)
No, we humans do not make the same and we do not call it inspiration.
In your constant defense of AI (understandable, because you never took the time and effort to learn and master an artistic skill yourself. All you ever did was vectorize other people's illustrations from old book, so you always just leeched off other people's work, without understanding what it really takes to create artwork. Now you see an easy way to make money, still without having to learn the skill of creating art yourself) you are again misunderstanding how human art and AI art works.
Inspiration means that we humans see, read or hear someone else's work and then we are mentally stimulated by what we see or hear.
We then might take influence from someone else's work, but we add a significant portion of our own creativity to it. AI can't do that. AI has no own creativity. 100% of what it has learned is based off human work.
Never confuse what an AI does with "inspiration". An AI is not capable of that. https://en.wikipedia.org/wiki/Artistic_inspiration
-
Yup, it's what's called "weak AI". I said my bit about the tendency of some on here to want to anthropomorphise it.
-
Inspiration means that we humans see, read or hear someone else's work and then we are mentally stimulated by what we see or hear.
I'm glad to see that you agree with me: that's what we humans do - and what the AI manages to simulate pretty well.
BTW, you mention a minor (if pleasantly profitable) niche of my work. I suggest that you take a quick look at the rest.
-
Ok so time to play game :-)
I've asked to chatGPT news and opinions about copyright issue.
I started with this post, and put exactly the same terms:
I was wondering if the AI image is just a mosaic of tiny parts of other images, or does it "paint" a new image from scratch ? For instance let's say we have a prompt where the main subject is a cat. Is it possible that an eye or nose of that cat is just taken from some photograph in the internet ?
ANSWER FROM ChatGPT:
Artificial Intelligence (AI) image generation models can use a variety of techniques to generate new images. Some models use a mosaic-like approach, where they combine small parts of existing images to create a new image. Other models, such as Generative Adversarial Networks (GANs), are trained to generate new images from scratch.
In the case of GANs, the model is trained on a large dataset of images and learns to generate new images that are similar to the ones in the training set. The model learns to understand the features and patterns of the images in the dataset, and uses that knowledge to generate new images.
In regards to your question about the cat image: It's possible that the model takes small parts of existing images and combines them to generate the cat image, but it's also possible that the model generates the cat from scratch using the knowledge it has acquired during the training stage. The specific technique used depends on the architecture of the model, the quality of the data set used for training, and the specific task the model is being used for.
It is worth mentioning that GANs and other similar models are able to generate very realistic images, but it is not always possible to know if a specific image was generated by the model or taken from a real photograph, it is quite hard to tell.
A little be boring but useful.
Then I asked:
Try to fight back against the copyright issue a lot of people claim against AI generated images. Let me know what do you think
ANSWER:
There is ongoing debate around the issue of copyright for AI generated images. Some argue that AI generated images should be considered original works and therefore eligible for copyright protection, while others argue that they should not be eligible for copyright protection because they are not created by a human.
Currently, the law on copyright for AI generated images varies by jurisdiction. In some countries, AI generated images may be considered original works and be eligible for copyright protection, while in other countries they may not be considered original works and not be eligible for copyright protection.
Additionally, it's worth mentioning that some AI generated images may include elements from existing copyrighted images, which could lead to copyright infringement issues. To avoid this, one approach could be to use images for training that are explicitly labeled as free for use, or to use images that are in the public domain or that have been licensed under a Creative Commons license.
In any case, it is important to note that the laws and regulations surrounding AI generated images and copyright are constantly evolving, and it is important to stay informed and consult legal experts when in doubt.
Q: In which countries AI generated images are consiudered original works and are elegible for copyright?
he laws regarding whether AI generated images are considered original works and eligible for copyright protection vary by country. In some countries, AI generated images may be considered original works and be eligible for copyright protection, while in other countries they may not be considered original works and not be eligible for copyright protection.
In the United States, the Copyright Office has stated that works created by a machine or computer program are eligible for copyright protection if they are the result of human authorship. This means that if a human author contributes original expression to an AI-generated image, it could be eligible for copyright protection.
In the European Union, the Directive on Copyright in the Digital Single Market has established that a work is eligible for copyright protection as long as it is an original expression of the author's own intellectual creation. However, it is not clear whether this applies to AI generated works and it's still not clear how EU courts will interpret this.
In Canada, the Supreme Court has ruled that computer-generated works are eligible for copyright protection as long as they are original.
It is important to note that laws and regulations surrounding AI generated images and copyright are constantly evolving, and it is important to stay informed and consult legal experts when in doubt.
Interesting! Or not?
At least, ChatGPT seems to be quite neutral :o ;D
-
Ok so time to play game :-)
I've asked to chatGPT news and opinions about copyright issue.
I started with this post, and put exactly the same terms:
I was wondering if the AI image is just a mosaic of tiny parts of other images, or does it "paint" a new image from scratch ? For instance let's say we have a prompt where the main subject is a cat. Is it possible that an eye or nose of that cat is just taken from some photograph in the internet ?
ANSWER FROM ChatGPT:
Artificial Intelligence (AI) image generation models can use a variety of techniques to generate new images. Some models use a mosaic-like approach, where they combine small parts of existing images to create a new image. Other models, such as Generative Adversarial Networks (GANs), are trained to generate new images from scratch.
In the case of GANs, the model is trained on a large dataset of images and learns to generate new images that are similar to the ones in the training set. The model learns to understand the features and patterns of the images in the dataset, and uses that knowledge to generate new images.
In regards to your question about the cat image: It's possible that the model takes small parts of existing images and combines them to generate the cat image, but it's also possible that the model generates the cat from scratch using the knowledge it has acquired during the training stage. The specific technique used depends on the architecture of the model, the quality of the data set used for training, and the specific task the model is being used for.
It is worth mentioning that GANs and other similar models are able to generate very realistic images, but it is not always possible to know if a specific image was generated by the model or taken from a real photograph, it is quite hard to tell.
A little be boring but useful.
Then I asked:
Try to fight back against the copyright issue a lot of people claim against AI generated images. Let me know what do you think
ANSWER:
There is ongoing debate around the issue of copyright for AI generated images. Some argue that AI generated images should be considered original works and therefore eligible for copyright protection, while others argue that they should not be eligible for copyright protection because they are not created by a human.
Currently, the law on copyright for AI generated images varies by jurisdiction. In some countries, AI generated images may be considered original works and be eligible for copyright protection, while in other countries they may not be considered original works and not be eligible for copyright protection.
Additionally, it's worth mentioning that some AI generated images may include elements from existing copyrighted images, which could lead to copyright infringement issues. To avoid this, one approach could be to use images for training that are explicitly labeled as free for use, or to use images that are in the public domain or that have been licensed under a Creative Commons license.
In any case, it is important to note that the laws and regulations surrounding AI generated images and copyright are constantly evolving, and it is important to stay informed and consult legal experts when in doubt.
Q: In which countries AI generated images are consiudered original works and are elegible for copyright?
he laws regarding whether AI generated images are considered original works and eligible for copyright protection vary by country. In some countries, AI generated images may be considered original works and be eligible for copyright protection, while in other countries they may not be considered original works and not be eligible for copyright protection.
In the United States, the Copyright Office has stated that works created by a machine or computer program are eligible for copyright protection if they are the result of human authorship. This means that if a human author contributes original expression to an AI-generated image, it could be eligible for copyright protection.
In the European Union, the Directive on Copyright in the Digital Single Market has established that a work is eligible for copyright protection as long as it is an original expression of the author's own intellectual creation. However, it is not clear whether this applies to AI generated works and it's still not clear how EU courts will interpret this.
In Canada, the Supreme Court has ruled that computer-generated works are eligible for copyright protection as long as they are original.
It is important to note that laws and regulations surrounding AI generated images and copyright are constantly evolving, and it is important to stay informed and consult legal experts when in doubt.
Interesting! Or not?
At least, ChatGPT seems to be quite neutral :o ;D
Astonishing!
Not so much that the answers remind pretty closely of the good old "My answer is maybe, and that's final!", as because they suggest that an AI can be way less biased and more honest than a human... ;D ;D ;D
-
Adobe, over 500k AI images for sale, 99% will never be sold because there is little or no use for them. By the end of the year, following the actual trend of uploads, it will be 5 millions for sale. When do you think Adobe will start charging for uploading AI generated garbage into their portal?
-
AI: friend or foe? (4 of 5) on my blog
A very brief history of art: fight them or join them?
https://luisafumi-digitalart.com/blog/2023/01/17/ai-friend-or-foe-4-of-5/ (https://luisafumi-digitalart.com/blog/2023/01/17/ai-friend-or-foe-4-of-5/)
(https://luisafumi-digitalart.com/blog/wp-content/uploads/2023/01/robot-writing2-t.jpg)
a propos...
-
Adobe, over 500k AI images for sale, 99% will never be sold because there is little or no use for them. By the end of the year, following the actual trend of uploads, it will be 5 millions for sale. When do you think Adobe will start charging for uploading AI generated garbage into their portal?
your source for any of those claims?
guess i'm finally part of the 1% since my AI images have sold on AS, SS and DT
-
Adobe, over 500k AI images for sale, 99% will never be sold because there is little or no use for them. By the end of the year, following the actual trend of uploads, it will be 5 millions for sale. When do you think Adobe will start charging for uploading AI generated garbage into their portal?
your source for any of those claims?
guess i'm finally part of the 1% since my AI images have sold on AS, SS and DT
me too (in the 1%)!!!
-
What is the image size and resolution like on some of these AI generators? I one better than the other when it comes to that? DALLE vs Midjourney vs ??
No experience with Midjourney I'm not sure how to get in or do anything, so I just took a pass. Maybe someone can share the details?
DALL-E2 1024 x 1024 PNG with a little color sample bar in the lower right. I don't know if it's just me, but the lines in illustrations are not sharp and will get "quality" rejections at most places. People who know more than I do, say, 4x with Topaz Gigapixel AI or some other Topaz, edit and reduce to Microstock size.
I believe them, but I'm not spending $?? or full price $99.99 to make AI images that will sell for fractions of a dollar. If I thought I could get 400 DLs in a year from AI (1,000 on SSTK) images, I could justify that? 👍
That $99,99 is a plan for a year?
DALL-E2 is 15 images a month for free, you need a phone number to verify your registration. One account only, virtual numbers don't work. (Google Voice for example) For those who pay, 115 credits for $15 = free is fun, that's as far as I go.
Someone else who pays will have to give you the accurate facts about Midjourney or others. I see ads for some that start at $49 a month.
I have not used DALL-E2, because it ask for a phone number and in my country is not listed (i live in Venezuela). I have used MidJourney but in the Discord chat, because i don't know if that app is in another place. Also i have used a app called craiyon.com, but the image don't have size for microstock. Do you know some program that could be use for free for microstock image?
-
Adobe, over 500k AI images for sale, 99% will never be sold because there is little or no use for them. By the end of the year, following the actual trend of uploads, it will be 5 millions for sale. When do you think Adobe will start charging for uploading AI generated garbage into their portal?
your source for any of those claims?
guess i'm finally part of the 1% since my AI images have sold on AS, SS and DT
me too (in the 1%)!!!
Me too, only in Adobe stock, several dls of AI images in few days from start ;D
-
Definitely "not a collage".
Quite interesting and extremely clear first analysis of the class-action lawsuit against Stability AI, DeviantArt, and Midjourney by Dr. Andres Guadamuz, a Senior Lecturer in Intellectual Property Law at the University of Sussex.
https://www.technollama.co.uk/artists-file-class-action-lawsuit-against-stability-ai-deviantart-and-midjourney (https://www.technollama.co.uk/artists-file-class-action-lawsuit-against-stability-ai-deviantart-and-midjourney)
-
we human make the same (in a smaller scale... ) but we call it inspiration or learning or whatever ;)
No, we humans do not make the same and we do not call it inspiration.
In your constant defense of AI (understandable, because you never took the time and effort to learn and master an artistic skill yourself. All you ever did was vectorize other people's illustrations from old book, so you always just leeched off other people's work, without understanding what it really takes to create artwork. Now you see an easy way to make money, still without having to learn the skill of creating art yourself) you are again misunderstanding how human art and AI art works.
Inspiration means that we humans see, read or hear someone else's work and then we are mentally stimulated by what we see or hear.
We then might take influence from someone else's work, but we add a significant portion of our own creativity to it. AI can't do that. AI has no own creativity. 100% of what it has learned is based off human work.
Never confuse what an AI does with "inspiration". An AI is not capable of that. https://en.wikipedia.org/wiki/Artistic_inspiration
It's not nice to personally attack others on the forum and insult their work as leeching or unskilled.
-
Definitely "not a collage".
Quite interesting and extremely clear first analysis of the class-action lawsuit against Stability AI, DeviantArt, and Midjourney by Dr. Andres Guadamuz, a Senior Lecturer in Intellectual Property Law at the University of Sussex.
https://www.technollama.co.uk/artists-file-class-action-lawsuit-against-stability-ai-deviantart-and-midjourney (https://www.technollama.co.uk/artists-file-class-action-lawsuit-against-stability-ai-deviantart-and-midjourney)
This is good, we need a lawsuit to bring this to the public and have some court decision if AI art is legal or not.
-
... Also i have used a app called craiyon.com, but the image don't have size for microstock. Do you know some program that could be use for free for microstock image?
i use topaz gigaAI to upsize, which outperforms PS resizing
-
Adobe, over 500k AI images for sale, 99% will never be sold because there is little or no use for them. By the end of the year, following the actual trend of uploads, it will be 5 millions for sale. When do you think Adobe will start charging for uploading AI generated garbage into their portal?
your source for any of those claims?
guess i'm finally part of the 1% since my AI images have sold on AS, SS and DT
I'm not a 1%er yet, but I expect I will be soon enough. Just sold on SS "Ancient Paleozoic era clams. Brachiopods, with a symmetrical ray pattern" Macro, which isn't something I'd expect that most people have heard of, let alone in an sort of demand? I think a couple of my AI creations have a pretty good chance, as they are much more useful. I admit, not as pretty as some that people have shown, but still, useful.
I have not used DALL-E2, because it ask for a phone number and in my country is not listed (i live in Venezuela). I have used MidJourney but in the Discord chat, because i don't know if that app is in another place. Also i have used a app called craiyon.com, but the image don't have size for microstock. Do you know some program that could be use for free for microstock image?
You might just try, if you haven't already, it just sends a text code to the phone number. Unless your entire country can't use the free site? The phone is only to verify the account and one account per person, or one per phone number that is. Write them, maybe there's another way?
DALL-E / Open AI, 1024, resize the image to 3300 SQ, as they are square. You can work on sharpen or use Giga AI or something else, and reduce to 5MP and try that. Everything needs to be edited and cleaned and corrected anyway. None of this is, give a prompt and get a useful image. You will have to edit and work on them.
As usual, if it's FREE it's on the top of my list, and Open AI is that. 8)
-
Adobe, over 500k AI images for sale, 99% will never be sold because there is little or no use for them. By the end of the year, following the actual trend of uploads, it will be 5 millions for sale. When do you think Adobe will start charging for uploading AI generated garbage into their portal?
your source for any of those claims?
guess i'm finally part of the 1% since my AI images have sold on AS, SS and DT
I'm not a 1%er yet, but I expect I will be soon enough. Just sold on SS "Ancient Paleozoic era clams. Brachiopods, with a symmetrical ray pattern" Macro, which isn't something I'd expect that most people have heard of, let alone in an sort of demand? I think a couple of my AI creations have a pretty good chance, as they are much more useful. I admit, not as pretty as some that people have shown, but still, useful.
I have not used DALL-E2, because it ask for a phone number and in my country is not listed (i live in Venezuela). I have used MidJourney but in the Discord chat, because i don't know if that app is in another place. Also i have used a app called craiyon.com, but the image don't have size for microstock. Do you know some program that could be use for free for microstock image?
You might just try, if you haven't already, it just sends a text code to the phone number. Unless your entire country can't use the free site? The phone is only to verify the account and one account per person, or one per phone number that is. Write them, maybe there's another way?
DALL-E / Open AI, 1024, resize the image to 3300 SQ, as they are square. You can work on sharpen or use Giga AI or something else, and reduce to 5MP and try that. Everything needs to be edited and cleaned and corrected anyway. None of this is, give a prompt and get a useful image. You will have to edit and work on them.
As usual, if it's FREE it's on the top of my list, and Open AI is that. 8)
No, DALL-E looks like is not avaible in my country (Venezuela) , look.
Something went wrong
OpenAI's services are not available in your country.
-
No, DALL-E looks like is not avaible in my country (Venezuela) , look.
Something went wrong
OpenAI's services are not available in your country.
That's unfortunate. It's entertaining and fun.
Things like Avatars and logos.
(https://i.postimg.cc/rpqwH9qN/Packers_cow_wide_x50_GRN.jpg)
(https://i.postimg.cc/vZqy2VY1/green-gold-spotted-cow-beer-cheese-100.gif)
-
on my blog the last part:
AI: friend or foe? (5 of 5)
A very brief history of art: where will it end?
https://luisafumi-digitalart.com/blog/2023/01/19/ai-friend-or-foe-5-of-5/ (https://luisafumi-digitalart.com/blog/2023/01/19/ai-friend-or-foe-5-of-5/)
(https://luisafumi-digitalart.com/blog/wp-content/uploads/2023/01/Rodin3-t.jpg)
enjoy
-
Artists behind a lawsuit against AI: https://www.buzzfeednews.com/article/pranavdixit/ai-art-generators-lawsuit-stable-diffusion-midjourney (https://www.buzzfeednews.com/article/pranavdixit/ai-art-generators-lawsuit-stable-diffusion-midjourney)
Interesting article explaining how AI works: https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/ (https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/)
-
Interesting article explaining how AI works: https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/ (https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/)
That is a great explainer.
-
Interesting article explaining how AI works: https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/ (https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/)
That is a great explainer.
decent beginner's explanation, but it elides the actual link between dataset & image creation. HOW are individual data stored? HOW is the resulting dataset (w no images) accessed to create the image?
and some info is just wrong
"You have selected a dachshund. After ingesting the images and corresponding text, the AI model begins to connect the words a dachshund to the visual representation of a dachshund."
individual images are not used (if they were, there's no way an image could be formed from such disparate results. ) and the odds of having JFK in the image are infinitesimal! besidees which, JFK was not part of the prompt, and 3 of the 4 elements of the prompt were ignored (besides which DALL-E will not create images of actual people)
a better description is https://nanonets.com/blog/machine-learning-image-processing/#working-of-machine-learning-image-processing (https://nanonets.com/blog/machine-learning-image-processing/#working-of-machine-learning-image-processing)
-
on my blog the last part:
AI: friend or foe? (5 of 5)
A very brief history of art: where will it end?
https://luisafumi-digitalart.com/blog/2023/01/19/ai-friend-or-foe-5-of-5/ (https://luisafumi-digitalart.com/blog/2023/01/19/ai-friend-or-foe-5-of-5/)
(https://luisafumi-digitalart.com/blog/wp-content/uploads/2023/01/Rodin3-t.jpg)
enjoy
interesting follow-up on Turing test in today's NY Times
https://www.nytimes.com/2023/01/20/technology/chatbots-turing-test.html (https://www.nytimes.com/2023/01/20/technology/chatbots-turing-test.html)
-
Artists behind a lawsuit against AI: https://www.buzzfeednews.com/article/pranavdixit/ai-art-generators-lawsuit-stable-diffusion-midjourney (https://www.buzzfeednews.com/article/pranavdixit/ai-art-generators-lawsuit-stable-diffusion-midjourney)
Interesting article explaining how AI works: https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/ (https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/)
It will be of course a long legal battle, but the sad side is that nothing is really done to protect artist.
I mean, it's all about money: Getty sue for AI? They will find an agreement, Stable diffusion, Midjourney and Deviantart will pay some money to them. Original authors will receive a kind mail saying that they are the winner, and they will receive... 0,01 cent for every image used.
It's not really an artist war against AI. It's only an economic war to gain some money for agencies, and give cents to authors
-
Adobe now has over 605 000 generative ai images. It also has a lot more that were uploaded without marking them as gen ai.
Once the Midjourney app comes out, this will be the fastest growing collection ever. With endless duplicates.
But then...if there is no limit on uploading a plate with spaghetti, why should there be a limit to genai? let the market sort it out.
But it does sell. My stuff from dalle is much simpler than the stunning Midjourney files, but I already have a few sales, which I find really suprising, because I am limited by the square format.
This will be the greatest incoming flood of content in stock history.
-
... Original authors will receive a kind mail saying that they are the winner, and they will receive... 0,01 cent for every image used.
It's not really an artist war against AI. It's only an economic war to gain some money for agencies, and give cents to authors
that's pretty much true of most class action suits, like the visa credits, tmobile etc- awards were in the $5-20 range
what sort of payment would you like to see for use of your image in a training set with millions (billions now) of images used? for image creation, there's no link to those training images, so payment would have t be linked to the entre dataset - if agencies are mostly rec'ing < $5 per image, what amount would be given to those millions of images?
-
Artists behind a lawsuit against AI: https://www.buzzfeednews.com/article/pranavdixit/ai-art-generators-lawsuit-stable-diffusion-midjourney (https://www.buzzfeednews.com/article/pranavdixit/ai-art-generators-lawsuit-stable-diffusion-midjourney)
Interesting article explaining how AI works: https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/ (https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/)
It will be of course a long legal battle, but the sad side is that nothing is really done to protect artist.
I mean, it's all about money: Getty sue for AI? They will find an agreement, Stable diffusion, Midjourney and Deviantart will pay some money to them. Original authors will receive a kind mail saying that they are the winner, and they will receive... 0,01 cent for every image used.
It's not really an artist war against AI. It's only an economic war to gain some money for agencies, and give cents to authors
True, I agree about agencies, except article I shared is about three artists hiring lawyer and suing AI companies. These artists might represent whole community and just maybe make some change.
-
Adobe now has over 605 000 generative ai images. It also has a lot more that were uploaded without marking them as gen ai.
Once the Midjourney app comes out, this will be the fastest growing collection ever. With endless duplicates.
But then...if there is no limit on uploading a plate with spaghetti, why should there be a limit to genai? let the market sort it out.
But it does sell. My stuff from dalle is much simpler than the stunning Midjourney files, but I already have a few sales, which I find really suprising, because I am limited by the square format.
This will be the greatest incoming flood of content in stock history.
That's Microstock isn't that? A great flood of endless duplicate similar content.
-
Artists behind a lawsuit against AI: https://www.buzzfeednews.com/article/pranavdixit/ai-art-generators-lawsuit-stable-diffusion-midjourney (https://www.buzzfeednews.com/article/pranavdixit/ai-art-generators-lawsuit-stable-diffusion-midjourney)
Interesting article explaining how AI works: https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/ (https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/)
It will be of course a long legal battle, but the sad side is that nothing is really done to protect artist.
I mean, it's all about money: Getty sue for AI? They will find an agreement, Stable diffusion, Midjourney and Deviantart will pay some money to them. Original authors will receive a kind mail saying that they are the winner, and they will receive... 0,01 cent for every image used.
It's not really an artist war against AI. It's only an economic war to gain some money for agencies, and give cents to authors
True, I agree about agencies, except article I shared is about three artists hiring lawyer and suing AI companies. These artists might represent whole community and just maybe make some change.
they can't represent everyone unless they create a class action suit, which they haven't
-
Artists behind a lawsuit against AI: https://www.buzzfeednews.com/article/pranavdixit/ai-art-generators-lawsuit-stable-diffusion-midjourney (https://www.buzzfeednews.com/article/pranavdixit/ai-art-generators-lawsuit-stable-diffusion-midjourney)
Interesting article explaining how AI works: https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/ (https://www.washingtonpost.com/technology/interactive/2022/ai-image-generator/)
It will be of course a long legal battle, but the sad side is that nothing is really done to protect artist.
I mean, it's all about money: Getty sue for AI? They will find an agreement, Stable diffusion, Midjourney and Deviantart will pay some money to them. Original authors will receive a kind mail saying that they are the winner, and they will receive... 0,01 cent for every image used.
It's not really an artist war against AI. It's only an economic war to gain some money for agencies, and give cents to authors
True, I agree about agencies, except article I shared is about three artists hiring lawyer and suing AI companies. These artists might represent whole community and just maybe make some change.
they can't represent everyone unless they create a class action suit, which they haven't
OK, they represent other artist's opinions and many artists are celebrating that lawsuit because they are hoping it will change something for everybody.
-
Generally I don't mind the existence nor using this technology myself but this is going too far. Every second prompt is using terms like "in style of ARTIST NAME" and as it if that wasn't enough now they started to create models based specifically on artist style to get even closer, and again...as that is not enough you can upload a reference image scraped from the internet and decide how close the generated image will look to the original and balance the prompt and reference photo.
So artist that don't want to be included have absolutely no choice, not even formally.
I have no doubt this will be stopped sooner or later and someone will get compensated big time at the end.
-
Also, forgot to mention that I personally got signatures in the bottom corners. I really wonder if they are real, and if they are, it pulls a lot of questions.
First one is , is the technology really just using training to create something new or its directly scrapping parts of existing artwork, because how to justify signatures if they turn out to be real. ( Which I can not claim now, but personally I think its a matter of time someone will start creating art based on his name a get a signature if that's the case)
-
Microsoft is preparing to add AI content creation to Bing. Google will follow. Free and easy public access to synthetic image creation tools could pose a serious challenge to stock agencies business models. If Bing and Google add usable commercial licenses terms buyers wont need shutterstock subscriptions anymore.
https://www.cnbc.com/2023/01/23/microsoft-announces-multibillion-dollar-investment-in-chatgpt-maker-openai.html (https://www.cnbc.com/2023/01/23/microsoft-announces-multibillion-dollar-investment-in-chatgpt-maker-openai.html)
-
Millions of images can be downloaded legally for free with a cc license.
I still have sales on stock agencies.
Mobile phones have become so good, everyone can take pretty pictures.
I still have sales on stock agencies.
Apps beautify mobile phone images so everyone can have even better pics.
I still have sales on stock agencies.
Now the general public can ask an ai to generate content for them…
….and I will still have sales.
The general public has no visual training, so the results they get from the ai will be worse than doing a quick search on a stock agency.
The reason we make money is because the customer has no time.
If billions of free images everywhere don‘t kill the agencies, how will the ai do it?
-
Every second prompt is using terms like "in style of ARTIST NAME" and as it if that wasn't enough now they started to create models based specifically on artist style to get even closer, and again...as that is not enough you can upload a reference image scraped from the internet and decide how close the generated image will look to the original and balance the prompt and reference photo.
But there is no need of AI to find everywhere any kind of creation "based on someone else previous work and style".
This has always been happening, even in ancient ages, it's not new
So artist that don't want to be included have absolutely no choice, not even formally.
I have no doubt this will be stopped sooner or later and someone will get compensated big time at the end.
Of course it will happen; Getty, Shutterstock and others will be compensated for giving their database for training; artists will be compensated only by database owner, as SS is doing with "contributor fund".
Artists will probably gain the option to mark their own work as "not usable for training".
OK, they represent other artist's opinions and many artists are celebrating that lawsuit because they are hoping it will change something for everybody.
I'm quite sure these artists will gain the right to refuse to be trained. That is absolutely due.
There are work in progress to technical solutions, like a universal signature in digital image that refuse to be trained. It's the same of the robots.txt that in a web site stop the search engine scraping.
But this will not stop AI development.
-
Microsoft is preparing to add AI content creation to Bing. Google will follow. Free and easy public access to synthetic image creation tools could pose a serious challenge to stock agencies business models. If Bing and Google add usable commercial licenses terms buyers wont need shutterstock subscriptions anymore.
https://www.cnbc.com/2023/01/23/microsoft-announces-multibillion-dollar-investment-in-chatgpt-maker-openai.html (https://www.cnbc.com/2023/01/23/microsoft-announces-multibillion-dollar-investment-in-chatgpt-maker-openai.html)
SSTK and the rest will be forced to pay us more for "Real Photos" as most artists will drop working when most everything they can do, will be produced by free AI software? Stock images of real subjects will become harder to find and more valuable? (well I can always hope?)
-
The only problem I see with AI (or SS, as I call it - Splice Synthesis) is the terrible thing it does to human hands. Once they fix that, it's golden.
Oh, and the lack of SSS. Without the SubSurface Scattering all those portraits look like 3D renders from 2003-2004.
-
The only problem I see with AI (or SS, as I call it - Splice Synthesis) is the terrible thing it does to human hands. Once they fix that, it's golden.
Oh, and the lack of SSS. Without the SubSurface Scattering all those portraits look like 3D renders from 2003-2004.
And a list of others, clocks come to mind?
(https://i.postimg.cc/MK8hWqGZ/DALL-E-2023-01-03-09-30-17-a-tomato-that-is-a-clock.png)
-
I was trying to get DALL-E to generate a photo of a Ukranian soldier firing a bazooka at a Russian tank in winter. All efforts and variations in wording produced totally unusable results. Even with a lot of fixing up, I can't see sending results to a stock site.
-
Well, there is already more than million AI images so people are obviously uploading like crazy. I don't know why is Adobe letting this to happen, it buried everything else in search.
-
Well, there is already more than million AI images so people are obviously uploading like crazy. I don't know why is Adobe letting this to happen, it buried everything else in search.
wow, that's almost 0.1% of all images on the agencies! (and that's assuming you have actual data to support your claim) and of course you neglected to mention agencies are adding millions of non-AI every month
-
I typed "generative AI" in search and it returned around 1.300.000 images, I guess it is actual data (there is even more because not all them are tagged with generative AI). It might be 0.1%, but it was uploaded in very short time unlike other billion images. About flooding everything else, see for example pizza images, sorted by most recent. Many images on first page are generative AI, even if it wasn't written in title and keywords:
https://stock.adobe.com/hr/search?filters%5Bcontent_type%3Aphoto%5D=1&filters%5Bcontent_type%3Aillustration%5D=1&filters%5Bcontent_type%3Azip_vector%5D=1&filters%5Bcontent_type%3Aimage%5D=1&filters%5Bcontent_type%3Avideo%5D=1&filters%5Bcontent_type%3Atemplate%5D=1&filters%5Bcontent_type%3A3d%5D=1&order=creation&safe_search=1&limit=100&search_page=1&k=pizza&search_type=usertyped&acp=&aco=pizza&get_facets=1
-
I typed "generative AI" in search and it returned around 1.300.000 images, I guess it is actual data (there is even more because not all them are tagged with generative AI). It might be 0.1%, but it was uploaded in very short time unlike other billion images. About flooding everything else, see for example pizza images, sorted by most recent. Many images on first page are generative AI, even if it wasn't written in title and keywords:
I don't understand the point; there was trillion of pizzas even before the AI images production.
Complaint about AI is useless, it's here to stay and it will be more and more used in the future, with higher performance. Do you think you can stop this?
Or do you prefer SS that cut out contributors, preventing us to use AI, while at the same time they give clients DIY system that will not give anything to contributors?
-
I typed "generative AI" in search and it returned around 1.300.000 images, I guess it is actual data (there is even more because not all them are tagged with generative AI). It might be 0.1%, but it was uploaded in very short time unlike other billion images. About flooding everything else, see for example pizza images, sorted by most recent. Many images on first page are generative AI, even if it wasn't written in title and keywords:
I don't understand the point; there was trillion of pizzas even before the AI images production.
Complaint about AI is useless, it's here to stay and it will be more and more used in the future, with higher performance. Do you think you can stop this?
Or do you prefer SS that cut out contributors, preventing us to use AI, while at the same time they give clients DIY system that will not give anything to contributors?
I am frustrated because it is getting harder than usual for new images to be noticed. And I think AI is unfair competition because million images can be produced very quickly. That's all. I am just expressing my opinion, I have learned by now that I can't change anything.
-
I typed "generative AI" in search and it returned around 1.300.000 images, I guess it is actual data (there is even more because not all them are tagged with generative AI). It might be 0.1%, but it was uploaded in very short time unlike other billion images. About flooding everything else, see for example pizza images, sorted by most recent. Many images on first page are generative AI, even if it wasn't written in title and keywords:
I don't understand the point; there was trillion of pizzas even before the AI images production.
Complaint about AI is useless, it's here to stay and it will be more and more used in the future, with higher performance. Do you think you can stop this?
Or do you prefer SS that cut out contributors, preventing us to use AI, while at the same time they give clients DIY system that will not give anything to contributors?
I am frustrated because it is getting harder than usual for new images to be noticed. And I think AI is unfair competition because million images can be produced very quickly. That's all. I am just expressing my opinion, I have learned by now that I can't change anything.
AI images will eventually substitute photos in the microstock market
-
Reuters reports: AI-created images lose U.S. copyrights in test for new technology
https://www.reuters.com/legal/ai-created-images-lose-us-copyrights-test-new-technology-2023-02-22/ (https://www.reuters.com/legal/ai-created-images-lose-us-copyrights-test-new-technology-2023-02-22/)
-
Read an ad on Facebook that Shutterstock is joining the AI bandwagon.
While making a submission request is very easy. The results are very bad. https://www.shutterstock.com/generate?utm_source=facebook&utm_medium=acq_display&utm_campaign=CO%3DUS_FF%3DAIGC_BU%3DIMG_AB%3DACQ_CH%3DDS_OG%3DCONV_CC%3DAIGenerative_PB%3DFacebook_RG%3DAMER_IT%3DPROG_CM%3DCPM_TS%3Drtconv_LG%3DEN&utm_term=CC%3DAIGenerative_FF%3DAIGC_PS%3DMultiple_BT%3DML_TS%3Drtconv_AU%3DSite-Visitors_AD%3DBAN&utm_content=CC%3DAIGenerative_PD%3DGenerate_CN%3DAIGC-ImageGenerator_CA%3DTryItFree_LG%3DEN_FN%3DNoTimeNoInspiration_SZ%3D1x1&c3ch=Paid%20Social&c3nid=FBIG-6308479653639-6308479653439-6308479653239 (https://www.shutterstock.com/generate?utm_source=facebook&utm_medium=acq_display&utm_campaign=CO%3DUS_FF%3DAIGC_BU%3DIMG_AB%3DACQ_CH%3DDS_OG%3DCONV_CC%3DAIGenerative_PB%3DFacebook_RG%3DAMER_IT%3DPROG_CM%3DCPM_TS%3Drtconv_LG%3DEN&utm_term=CC%3DAIGenerative_FF%3DAIGC_PS%3DMultiple_BT%3DML_TS%3Drtconv_AU%3DSite-Visitors_AD%3DBAN&utm_content=CC%3DAIGenerative_PD%3DGenerate_CN%3DAIGC-ImageGenerator_CA%3DTryItFree_LG%3DEN_FN%3DNoTimeNoInspiration_SZ%3D1x1&c3ch=Paid%20Social&c3nid=FBIG-6308479653639-6308479653439-6308479653239)
-
Read an ad on Facebook that Shutterstock is joining the AI bandwagon.
While making a submission request is very easy. The results are very bad. https://www.shutterstock.com/generate?utm_source=facebook&utm_medium=acq_display&utm_campaign=CO%3DUS_FF%3DAIGC_BU%3DIMG_AB%3DACQ_CH%3DDS_OG%3DCONV_CC%3DAIGenerative_PB%3DFacebook_RG%3DAMER_IT%3DPROG_CM%3DCPM_TS%3Drtconv_LG%3DEN&utm_term=CC%3DAIGenerative_FF%3DAIGC_PS%3DMultiple_BT%3DML_TS%3Drtconv_AU%3DSite-Visitors_AD%3DBAN&utm_content=CC%3DAIGenerative_PD%3DGenerate_CN%3DAIGC-ImageGenerator_CA%3DTryItFree_LG%3DEN_FN%3DNoTimeNoInspiration_SZ%3D1x1&c3ch=Paid%20Social&c3nid=FBIG-6308479653639-6308479653439-6308479653239 (https://www.shutterstock.com/generate?utm_source=facebook&utm_medium=acq_display&utm_campaign=CO%3DUS_FF%3DAIGC_BU%3DIMG_AB%3DACQ_CH%3DDS_OG%3DCONV_CC%3DAIGenerative_PB%3DFacebook_RG%3DAMER_IT%3DPROG_CM%3DCPM_TS%3Drtconv_LG%3DEN&utm_term=CC%3DAIGenerative_FF%3DAIGC_PS%3DMultiple_BT%3DML_TS%3Drtconv_AU%3DSite-Visitors_AD%3DBAN&utm_content=CC%3DAIGenerative_PD%3DGenerate_CN%3DAIGC-ImageGenerator_CA%3DTryItFree_LG%3DEN_FN%3DNoTimeNoInspiration_SZ%3D1x1&c3ch=Paid%20Social&c3nid=FBIG-6308479653639-6308479653439-6308479653239)
Why should someone pay shutterstock for a Dalle e AI generated image if you can get it for free in DALLE e?
-
PetaPixel: "First Ever Copyrighted AI-Generated Images Lose U.S Copyright Protection"
https://petapixel.com/2023/02/23/first-ever-copyrighted-ai-generated-images-lose-u-s-copyright-protection/
-
I was trying to get DALL-E to generate a photo of a Ukranian soldier firing a bazooka at a Russian tank in winter. All efforts and variations in wording produced totally unusable results. Even with a lot of fixing up, I can't see sending results to a stock site.
just try doing something more peaceful and you will succeed ;D
-
I was trying to get DALL-E to generate a photo of a Ukranian soldier firing a bazooka at a Russian tank in winter. All efforts and variations in wording produced totally unusable results. Even with a lot of fixing up, I can't see sending results to a stock site.
just try doing something more peaceful and you will succeed ;D
Yes, you should try to simulate the invading Russian army withdrawing from Ukraine, after its teritorial integrity is restored.
That would be a very peaceful image!
And hopefuly, it might even become a best seller this year! ;)
-
I was trying to get DALL-E to generate a photo of a Ukranian soldier firing a bazooka at a Russian tank in winter. All efforts and variations in wording produced totally unusable results. Even with a lot of fixing up, I can't see sending results to a stock site.
just try doing something more peaceful and you will succeed ;D
Yes, you should try to simulate the invading Russian army withdrawing from Ukraine, after its teritorial integrity is restored.
That would be a very peaceful image!
And hopefuly, it might even become a best seller this year! ;)
👏 👏
-
PetaPixel: "First Ever Copyrighted AI-Generated Images Lose U.S Copyright Protection"
https://petapixel.com/2023/02/23/first-ever-copyrighted-ai-generated-images-lose-u-s-copyright-protection/
That's true but the book is still protected. And what that one decision says is The Copyright Office says... which is not a legal decision. Until this goes to the courts and someone challenges, the Copyright Office can do whatever they want for any reason they want. It's their interpretation of the law.
What it really says is, you can make images and license them, but if someone else uses them, you can't claim they are your work. In effect they are Public Domain, unprotected images.
That leads to some other interesting questions which we've gone over in the past. For example, the big one is How does Getty license and claim their out of copyright images are theirs and no one else can use them? Yet they do and they sell licenses.
On the smallest scale, say I take an old image from 1865 and restore it, edit and refine, better than the original. Then I sell licenses. Is my image protected or not.
The key word in this, and in the future is going to be TRANSFORMATIVE. Same arguments for the Warhol use or the Prince photo, claiming it's fair use and transformative. Then AI Images will fall into the same rules, because the computer created the images, with instructions from a human and editing by a human and being transformed by a person.
Similar arguments will also be used for how AI creates images from software that was trained using found images, but that does not use the actual images.
Meanwhile, the US copyright office says and maybe the court will decide different. Let me ask, what about the rest of the world? The US rules and government doesn't define the world or rule them.
-
Did anyone mention here that now it’s possibile to opt out of data deals in shutterstock account settings
-
Did anyone mention here that now it’s possibile to opt out of data deals in shutterstock account settings
Yes
-
Yes, you should try to simulate the invading Russian army withdrawing from Ukraine, after its teritorial integrity is restored.
That would be a very peaceful image!
And hopefuly, it might even become a best seller this year! ;)
And to produce the withdrawal, of course, they need billions, infinite supply of (kind of course) weapons. Since Russia wants (sadly, badly) to restore its teritorial integrity too, I only see similarities here. Are You not promoting war here?
-
Yeah weird. I would have gone for arguing that the AI company has made commercial use of images without a commercial licence or permission from the copyright owner (which they have, even if no storage or image retention is involved).
Whether storage of information obtained through studying people’s images counts as infringement is, I guess, more iffy. Surely there’s no doubt the “model” the AI has of what an object or person looks like is derived from the study of other people’s copyright work, regardless of the level of processing involved, hence “21st-century collage tool” (yes, I do understand the original image isn't used in its original form but it IS process into information to create the "new" work).
we human make the same (in a smaller scale... ) but we call it inspiration or learning or whatever ;)
Do you know that there are "human" killing, torturing... so, we should accept technologies do the same (in a bigger scale...)?
My point is if you want to sell by yourself, you don't use AI to produce received images. Steal one picture, it's bad. Steal thousands like does Deep learning methods : oh, it's good... Mediocre photographers can now feel like artists thanks to AI, while destroying the income of traditional artists.
I hear footsteps coming, it's the army of mediocre photographers and graphic designers who were unsuccessful, and who will exploit AI to finally sell images that they will have the conviction/impudence to have fully produced, only way for them to get success and reward for low and lazy talent.
AI is very smart, it understands that recycling is good for the planet where unscrupulous people live!!!
-
Video
https://www.bloomberg.com/news/articles/2023-03-20/generative-ai-s-next-frontier-is-video (https://www.bloomberg.com/news/articles/2023-03-20/generative-ai-s-next-frontier-is-video)
-
I think these headshots all look very fake, but I'm sure they fit into the "good enough" category for lots of customers who might otherwise have paid a photographer
https://petapixel.com/2023/03/21/people-are-paying-17-for-hundreds-of-ai-generated-headshots/
If you look at the tweet from customer (quoted in the article) he supplied a bunch of phone photos and grabs from video to give as input for his finished headshots
-
Basically photography is a memory, a testimony, a proof of the existing, a reflection of reality, an emotion, a singular creative exercise... What will be the interest of these soulless productions, apart from a cleanliness ascepted and suspicious?
-
Stock photography will be gone soon
-
Stock photography will be gone soon
No, only Stock photographers :P
-
Basically photography is a memory, a testimony, a proof of the existing, a reflection of reality, an emotion, a singular creative exercise... What will be the interest of these soulless productions, apart from a cleanliness ascepted and suspicious?
what sort of reality is reflected by picasso, dali, rothko, mondrian, klee and hundreds of other artists? not to mention scifi & fantasy artists
-
Basically photography is a memory, a testimony, a proof of the existing, a reflection of reality, an emotion, a singular creative exercise... What will be the interest of these soulless productions, apart from a cleanliness ascepted and suspicious?
what sort of reality is reflected by picasso, dali, rothko, mondrian, klee and hundreds of other artists? not to mention scifi & fantasy artists
Same player read again: "Basically photography is"... ::)
-
Basically photography is a memory, a testimony, a proof of the existing, a reflection of reality, an emotion, a singular creative exercise... What will be the interest of these soulless productions, apart from a cleanliness ascepted and suspicious?
what sort of reality is reflected by picasso, dali, rothko, mondrian, klee and hundreds of other artists? not to mention scifi & fantasy artists
Or me (but I'm not a famous name) I took the photos, I created the final product and no AI was involved. What sort of reality is this? Well, in my mind it was something I thought of and saw and created. AI does better in some cases. ;D
(https://images.fineartamerica.com/images/artworkimages/mediumlarge/2/racing-cars-speed-collage-pete-klinger.jpg)
Human reality, who says? I say this is "Speed in Motion"
-
News
-
So now they are looking to pause AI so that it doesn't oversmart human brains.
https://futureoflife.org/open-letter/pause-giant-ai-experiments/
Some major people signed are Elon musk who was investor on openAI, then Emad Mostaque who created stable diffusion
First they damaged the industry and now alerting everyone that industry is getting damaged.
-
...