The link to Adobe doesn't work.
Generative Ai content for Adobe, Helpdesk article on how and what to upload
https://helpx.adobe.com/stock/contributor/help/generative-ai-content.html (https://helpx.adobe.com/stock/contributor/help/generative-ai-content.html)
Article about generative ai on Dreamstime
https://www.dreamstime.com/blog/dreamstime-now-accepting-ai-generated-content-under-specific-terms-59030 (https://www.dreamstime.com/blog/dreamstime-now-accepting-ai-generated-content-under-specific-terms-59030)
In a different thread I read that pond5, alamy, mostphotos and 123rf are also accepting gen ai. But I haven‘t yet found an announcement.
Anyone have that?
very weird sorry, i will try to repair them all.
eta: hope they work now. thank you to everyone who alerted me.
I made my copy/paste via my ipad, maybe there is a problem there. works fine with my computer.
I've had AI images accepted by alamy - marked as AI
This makes me reluctant to invest time and money creating AI images:
No copyright protection for AI images, says US government
https://www.diyphotography.net/no-copyright-protection-for-ai-images-says-us-government/ (https://www.diyphotography.net/no-copyright-protection-for-ai-images-says-us-government/)
If you see only what you want to see and draw conclusions from that.
"This policy does not mean that
technological tools cannot be part of the
creative process. Authors have long
used such tools to create their works or
to recast, transform, or adapt their
expressive authorship. For example, a
visual artist who uses Adobe Photoshop
to edit an image remains the author of
the modified image,"
Is the final image transformative and making it a new work. Here's my point. I obtain an AI created image, using my prompts, from one of these computer driven systems. I open and edit it, and transform it, into a new work... it's now mine and I can copyright it.
If you see only what you want to see and draw conclusions from that.
"This policy does not mean that
technological tools cannot be part of the
creative process. Authors have long
used such tools to create their works or
to recast, transform, or adapt their
expressive authorship. For example, a
visual artist who uses Adobe Photoshop
to edit an image remains the author of
the modified image,"
Is the final image transformative and making it a new work. Here's my point. I obtain an AI created image, using my prompts, from one of these computer driven systems. I open and edit it, and transform it, into a new work... it's now mine and I can copyright it.
Same:
"If you see only what you want to see and draw conclusions from that."
That's very obvious not what is meant when they say "For example, a visual artist who uses Adobe Photoshop to edit an image remains the author of the modified image"
Because they say REMAIN. Which means you need to have owned copyright of the image before you edited it in the first place, so they are talking about editing your own human created artwork, not AI generated images. It does not mean that you become the copyright owner of an AI created image if you edit it in photoshop, because according to the US copyright office you were not the copyright owner of the unedited image, so you cannot "remain" the copyright owner by editing it.
If you see only what you want to see and draw conclusions from that.
"This policy does not mean that
technological tools cannot be part of the
creative process. Authors have long
used such tools to create their works or
to recast, transform, or adapt their
expressive authorship. For example, a
visual artist who uses Adobe Photoshop
to edit an image remains the author of
the modified image,"
Is the final image transformative and making it a new work. Here's my point. I obtain an AI created image, using my prompts, from one of these computer driven systems. I open and edit it, and transform it, into a new work... it's now mine and I can copyright it.
Same:
"If you see only what you want to see and draw conclusions from that."
That's very obvious not what is meant when they say "For example, a visual artist who uses Adobe Photoshop to edit an image remains the author of the modified image"
Because they say REMAIN. Which means you need to have owned copyright of the image before you edited it in the first place, so they are talking about editing your own human created artwork, not AI generated images. It does not mean that you become the copyright owner of an AI created image if you edit it in photoshop, because according to the US copyright office you were not the copyright owner of the unedited image, so you cannot "remain" the copyright owner by editing it.
If you see only what you want to see and draw conclusions from that.
"This policy does not mean that
technological tools cannot be part of the
creative process. Authors have long
used such tools to create their works or
to recast, transform, or adapt their
expressive authorship. For example, a
visual artist who uses Adobe Photoshop
to edit an image remains the author of
the modified image,"
Is the final image transformative and making it a new work. Here's my point. I obtain an AI created image, using my prompts, from one of these computer driven systems. I open and edit it, and transform it, into a new work... it's now mine and I can copyright it.
Same:
"If you see only what you want to see and draw conclusions from that."
That's very obvious not what is meant when they say "For example, a visual artist who uses Adobe Photoshop to edit an image remains the author of the modified image"
Because they say REMAIN. Which means you need to have owned copyright of the image before you edited it in the first place, so they are talking about editing your own human created artwork, not AI generated images. It does not mean that you become the copyright owner of an AI created image if you edit it in photoshop, because according to the US copyright office you were not the copyright owner of the unedited image, so you cannot "remain" the copyright owner by editing it.
Sorry you have twisted the meaning by picking out the word remain. They are saying you don't lose your rights by editing in Photoshop. I can take an AI image and become the owner of a new human created artwork by editing.
The legal part around do we have copyright will probably be discussed for years.
The safest route is probably to have a seed image to start from.
But if you are interested in creating ai content for stock you know from the get go that legally you are in murky waters.
If you see only what you want to see and draw conclusions from that.
"This policy does not mean that
technological tools cannot be part of the
creative process. Authors have long
used such tools to create their works or
to recast, transform, or adapt their
expressive authorship. For example, a
visual artist who uses Adobe Photoshop
to edit an image remains the author of
the modified image,"
Is the final image transformative and making it a new work. Here's my point. I obtain an AI created image, using my prompts, from one of these computer driven systems. I open and edit it, and transform it, into a new work... it's now mine and I can copyright it.
Same:
"If you see only what you want to see and draw conclusions from that."
That's very obvious not what is meant when they say "For example, a visual artist who uses Adobe Photoshop to edit an image remains the author of the modified image"
Because they say REMAIN. Which means you need to have owned copyright of the image before you edited it in the first place, so they are talking about editing your own human created artwork, not AI generated images. It does not mean that you become the copyright owner of an AI created image if you edit it in photoshop, because according to the US copyright office you were not the copyright owner of the unedited image, so you cannot "remain" the copyright owner by editing it.
Sorry you have twisted the meaning by picking out the word remain. They are saying you don't lose your rights by editing in Photoshop. I can take an AI image and become the owner of a new human created artwork by editing.
No, you have twisted the meaning by completely ignoring the word remain.
Yes, they are saying you don't lose your rights by editing in Photoshop. - The right to an image you had the copyrigfht to begin with, otherwise the word "remain" would be pointless in that sentence. You can't remain something you had not been before.
I am not sure how you can call that "twisting". I am not the one twisting anything, it's written there, exactly like this:
"a visual artist who uses Adobe Photoshop to edit an image remains the author of the modified image".
The word remain is there, I did not make that up.
If they were refering to AI generated images where, according to them, you do not have copyrigh, the sentence would be
"a visual artist who uses Adobe Photoshop to edit an image becomes the author of the modified image".
Two completely different things.
This makes me reluctant to invest time and money creating AI images:
No copyright protection for AI images, says US government
https://www.diyphotography.net/no-copyright-protection-for-ai-images-says-us-government/ (https://www.diyphotography.net/no-copyright-protection-for-ai-images-says-us-government/)
Adobe announces their own AI system.
Welcome Firefly!
https://blog.adobe.com/en/publish/2023/03/21/bringing-gen-ai-to-creative-cloud-adobe-firefly?fbclid=IwAR2tIv5tsSELTNHR0tqFcz2DrIMKrbAkjwN0u71NkOCg6Z7jCIngIFY8YNo
Of course the money is all that matters.There are microstockers who were able to produce quality images and did not had to wait for AI to achieve that.
Have you ever seen a photographer that felt guilty for putting portrait painters out of business?
New tech comes along and it is up to you to choose to whine and play victim or harvest the new possibilities and reinvent yourself.
I love ai and look forward to making more money.
Of course the money is all that matters.
Have you ever seen a photographer that felt guilty for putting portrait painters out of business?
New tech comes along and it is up to you to choose to whine and play victim or harvest the new possibilities and reinvent yourself.
I love ai and look forward to making more money.
There are microstockers who were able to produce quality images and did not had to wait for AI to achieve that.
They were happy about the money they made from their OWN work. And they knew they had to improve and work by themselves. And they did. And they evolved.
AI = easy money? lol, wait just a few months... These words will only be spoken by the fulfilled big mouths of the big agencies managers and shareholder ;D
Wait for the nexts "hey, we have good news!!!" :D
[...]natural selection moves alongSorry but nothing "natural" in AI...
[...]natural selection moves alongSorry but nothing "natural" in AI...
You all keep making the same arguments while completely confusing simple technology with AI. these are two completely different things. Technology itself was never a threat to humaity or creativity. AI can replace almost everything that makes humans human, espect for the biological part.
You all keep making the same arguments while completely confusing simple technology with AI. these are two completely different things. Technology itself was never a threat to humaity or creativity. AI can replace almost everything that makes humans human, espect for the biological part.
AWB, auto focus, auto exposure, auto ISO, programming, the only part a human has to do is push the button. No film, no processing, a digital photo can be edited down to pixels. Auto levels, color correction, sharpen or blur, much more including making parts that never existed, shadows and lighting. Digital images can replace almost everything that makes a human taking photo.
https://www.reuters.com/technology/musk-experts-urge-pause-training-ai-systems-that-can-outperform-gpt-4-2023-03-29/ (https://www.reuters.com/technology/musk-experts-urge-pause-training-ai-systems-that-can-outperform-gpt-4-2023-03-29/)
Maybe AI creators are slowly coming to their senses (or they are forced to think twice): "The letter, issued by the non-profit Future of Life Institute and signed by more than 1,000 people including Musk, called for a pause on advanced AI development until shared safety protocols for such designs were developed, implemented and audited by independent experts."
https://www.reuters.com/technology/musk-experts-urge-pause-training-ai-systems-that-can-outperform-gpt-4-2023-03-29/ (https://www.reuters.com/technology/musk-experts-urge-pause-training-ai-systems-that-can-outperform-gpt-4-2023-03-29/)
Maybe AI creators are slowly coming to their senses (or they are forced to think twice): "The letter, issued by the non-profit Future of Life Institute and signed by more than 1,000 people including Musk, called for a pause on advanced AI development until shared safety protocols for such designs were developed, implemented and audited by independent experts."
Will they "regulate" Chinese AI too? Which will gain leverage during the "pause"?
What AI would you rather submit to? English-speaking or Chinese-speaking? :P
It all is rather scary indeed :)
Frankly, I don't care much more for USA than China regarding this issue.
To be exact the checkbox says:For media submitted for Free License distribution:
"I allow users to use my media for free, even for commercial purposes, without further attribution or compensation to me"
I allow users to use my media for free, including for commercial purposes, without further attribution or fee to me.
midjourney temporarily halts free image trial
https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html (https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html)
midjourney temporarily halts free image trial
https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html (https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html)
Do not understand what the "AI-generated fake images that went viral" have to do with the free trial. It's not like the paid subscription will keep you from generating "fake images" - After all that's the whole point of midjourney.
sure....midjourney temporarily halts free image trial
https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html (https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html)
Do not understand what the "AI-generated fake images that went viral" have to do with the free trial. It's not like the paid subscription will keep you from generating "fake images" - After all that's the whole point of midjourney.
"There's an expert .. who says that if there is not an indefinite pause on AI development ... 'Literally everyone on Earth will die,'"
midjourney temporarily halts free image trial
https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html (https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html)
Do not understand what the "AI-generated fake images that went viral" have to do with the free trial. It's not like the paid subscription will keep you from generating "fake images" - After all that's the whole point of midjourney.
"There's an expert .. who says that if there is not an indefinite pause on AI development ... 'Literally everyone on Earth will die,'"
sure....midjourney temporarily halts free image trial
https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html (https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html)
Do not understand what the "AI-generated fake images that went viral" have to do with the free trial. It's not like the paid subscription will keep you from generating "fake images" - After all that's the whole point of midjourney.
"There's an expert .. who says that if there is not an indefinite pause on AI development ... 'Literally everyone on Earth will die,'"
and expert economists have predicted nine of the last 7 recessions
and a few 'expert' biologists refuse to accept evolution
and rightwing experts refuse to accept climate change
[an example of expert blunders/ignorance, not meant to start any debates on those topics]
Liberals invented Climate Change, talk about deniers of the facts. If a dire prediction doesn't go the way they want, they just change the model. That happens year after year, because the predictions haven't met the levels of doom that are claimed
midjourney temporarily halts free image trial
https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html (https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html)
Do not understand what the "AI-generated fake images that went viral" have to do with the free trial. It's not like the paid subscription will keep you from generating "fake images" - After all that's the whole point of midjourney.
"There's an expert .. who says that if there is not an indefinite pause on AI development ... 'Literally everyone on Earth will die,'"
Uhm, okay? I still do not understand what that has to do with Midjourney stopping their free trial?
midjourney temporarily halts free image trial
https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html (https://www.pcworld.com/article/1677533/midjourney-halts-free-trials-after-ai-photos-go-viral.html)
Even humor needs to make some sense. Like: What
Do not understand what the "AI-generated fake images that went viral" have to do with the free trial. It's not like the paid subscription will keep you from generating "fake images" - After all that's the whole point of midjourney.
"There's an expert .. who says that if there is not an indefinite pause on AI development ... 'Literally everyone on Earth will die,'"
Uhm, okay? I still do not understand what that has to do with Midjourney stopping their free trial?
Humor that's a shortage around here.
Could we perhaps move the climate change discussion/politics into a different thread?
I would like to continue using this thread for collecting useful links and articles about generative ai.
THANK YOU.
Could we perhaps move the climate change discussion/politics into a different thread?
I would like to continue using this thread for collecting useful links and articles about generative ai.
THANK YOU.
I would love for politics to not come up but when a grown ass man in the year of our Lord 2023 drops in the line "Liberals invented Climate Change" what the heck do you expect me to do.
This is why very few pros come here any more. It's turning into Facebook.
How can you go back to having adult/ professional conversation taking people seriously once you know the mental capacity of people you are talking to.
Arghhhhhhhhhhhhhhhhhhhhhhhhhhh
At least we wont have to worry about it soon, when AI has taken all our jobs or the planet becomes unlivable, which ever comes first.
sure....
and expert economists have predicted nine of the last 7 recessions
and a few 'expert' biologists refuse to accept evolution
and rightwing experts refuse to accept climate change
[an example of expert blunders/ignorance, not meant to start any debates on those topics]
Start at the source, not the reply? And attack issues not people, personally?
Start at the source, not the reply? And attack issues not people, personally?
Attack the issue that “liberals invented climate change”? LOL no, you're okay. I'll just go back to ignoring you.
Start at the source, not the reply? And attack issues not people, personally?
Attack the issue that “liberals invented climate change”? LOL no, you're okay. I'll just go back to ignoring you.
Please do, I'd appreciate not having to read your arrogant, egocentric and patronizing comments about the rest of us here.
Hello everyone,
generative ai is transforming our industry more drastically than the invention of the photocamera transformed art.
Allover the internet creatives are having very emotional discussions and reassessing their personal and business futures.
Is Ai an opportunity, a new tool? Is it the robot overlord that will replace us all? Is there nothing creative left for humanity to explore? Is this the end…?
etc…
Hope you find this thread useful.
Guys,
START YOUR OWN THREAD ON CLIMATE CHANGE. In Off topic.
Then you can keep slinging at each other as much as you like. We will get popcorn.
...really just shows how far behind these agencies are -- it ignores the real question of whether someone using a tool can be a creator/inventor (and of course, no artist is trying to patent their AI creations)
The Federal Circuit adopted a comparable stance for AI invention in the patent context in Thaler v. Vidal, Appeal No. 2021-2347 (Fed. Cir. Aug. 5, 2022). Writing for the court, Circuit Judge Stark proclaimed, “there is no ambiguity: the Patent Act requires that inventors must be natural persons; that is, human beings.”
My Bold...
...it ignores the real question of whether someone using a tool can be a creator/inventor
The Federal Circuit adopted a comparable stance for AI invention in the patent context in Thaler v. Vidal, Appeal No. 2021-2347 (Fed. Cir. Aug. 5, 2022). Writing for the court, Circuit Judge Stark proclaimed, “there is no ambiguity: the Patent Act requires that inventors must be natural persons; that is, human beings.”
My Bold...
it ignores the real question of whether someone using a tool can be a creator/inventor
No, it doesn't ignore the "real question". This question doesn't even arise.
Since with an AI image generator all you do is describe an image to the AI and the AI creates the image, not you, it is exacly the same as you going to an artist and commissioning him or her: You describe to him or her what you want, the artists paints or photographes the image. Are you the creator (and therfore by default the copyright holder) or the artist? No one would question the case here, so why should we with AI images? The creator is the one who creates the image, not the one who describes it.
...really just shows how far behind these agencies are -- it ignores the real question of whether someone using a tool can be a creator/inventor (and of course, no artist is trying to patent their AI creations)
The Federal Circuit adopted a comparable stance for AI invention in the patent context in Thaler v. Vidal, Appeal No. 2021-2347 (Fed. Cir. Aug. 5, 2022). Writing for the court, Circuit Judge Stark proclaimed, “there is no ambiguity: the Patent Act requires that inventors must be natural persons; that is, human beings.”
My Bold...
then something anyone creates with AI is also protected
...exactly
Which brings up the next complication. If something is automatically protected by copyright, by being created, then something anyone creates with AI is also protected. It just can't be registered.
complete nonsense - how many times have you produced a salable image that easily?then something anyone creates with AI is also protected
Only that no one can create anything with AI. All you can do is describe the image, the AI creates it.
Only that no one can create anything with AI. All you can do is describe the image, the AI creates it.exactly
This article actually champions the thoughtful use of AI, by someone in the industry, notwithstanding the title:
The Call to Halt ‘Dangerous’ AI Research Ignores a Simple Truth - Wired Magazine:
https://www.wired.com/story/the-call-to-halt-dangerous-ai-research-ignores-a-simple-truth/ (https://www.wired.com/story/the-call-to-halt-dangerous-ai-research-ignores-a-simple-truth/)
Edge’s AI image generator will be available to everyone as they offer Dall-e as a sidebar choice. Image Creator generates AI images based on your text. Powered by DALL-E
https://www.bing.com/images/create/make-a-picture-of-someone-with-their-hair-on-fire-/643002e35ed84c1aa58e497290ff82b7?id=EqfuN07OAySY3mlihdEUvw%3d%3d&view=detailv2&idpp=genimg&edgehub=1&lightschemeovr=1&FORM=GCRIDP&mode=overlay (https://www.bing.com/images/create/make-a-picture-of-someone-with-their-hair-on-fire-/643002e35ed84c1aa58e497290ff82b7?id=EqfuN07OAySY3mlihdEUvw%3d%3d&view=detailv2&idpp=genimg&edgehub=1&lightschemeovr=1&FORM=GCRIDP&mode=overlay)
Use of Creations. Subject to your compliance with this Agreement, the Microsoft Services Agreement, and our Content Policy, you may use Creations outside of the Online Services for any legal personal, non-commercial purpose.
(https://i.postimg.cc/tRSN2JDh/More-Free-AI.jpg)There is something I don't understand, why not green teeth? ::) ;D
(https://i.postimg.cc/tRSN2JDh/More-Free-AI.jpg)There is something I don't understand, why not green teeth? ::) ;D
Bit of a waste of time creating AI images until they can export files larger enough to be accepted by a stock agency
An article from earlier this week about a different type of copyrighted work being used for AI training, but with many of the same concerns as we've seen for photos/illustrations/videos:
https://arstechnica.com/information-technology/2023/04/streaming-services-urged-to-clamp-down-on-ai-generated-music/ (https://arstechnica.com/information-technology/2023/04/streaming-services-urged-to-clamp-down-on-ai-generated-music/)
"AI-generated songs have been popping up on streaming services, and UMG has been sending takedown requests “left and right,” said a person familiar with the matter. The company is asking streaming companies to cut off access to their music catalog for developers using it to train AI technology."
One big difference in the music business is that the individual artists are not on their own to pursue action or limit access - although music publishers and artists have certainly had all sorts of clashes over the years.
If you look at the paragraph about why Google hasn't yet released their music AI tool, it's clear (to me anyway) that it is entirely possible for AI generated results to be a "... direct replica of copyrighted work..." from the training data - from our works as much as musical works I would think.
A few more articles on the same topic
https://variety.com/2023/music/news/universal-music-streaming-services-block-ai-1235582612/ (https://variety.com/2023/music/news/universal-music-streaming-services-block-ai-1235582612/)
https://www.billboard.com/pro/universal-music-asks-spotify-apple-stop-ai-access-songs/ (https://www.billboard.com/pro/universal-music-asks-spotify-apple-stop-ai-access-songs/)
https://musically.com/2023/04/12/report-umg-wants-dsps-to-block-unlicensed-ai-training-scraping/ (https://musically.com/2023/04/12/report-umg-wants-dsps-to-block-unlicensed-ai-training-scraping/)
https://www.complex.com/music/universal-music-group-spotify-ai (https://www.complex.com/music/universal-music-group-spotify-ai)
https://gizmodo.com/ai-music-generator-umg-begs-spotify-apple-block-chatgpt-1850327300 (https://gizmodo.com/ai-music-generator-umg-begs-spotify-apple-block-chatgpt-1850327300)
...But instead of removing his images, Laion has sued Robert for damages for wanting to have his files removed…
The English translation says (emphasis mine) "We would also like to point out that our client can assert claims for damages in accordance with Section 97a (4) of the Copyright Act if unjustified copyright claims are made against her." So I think this is a thinly veiled threat designed to get rights holders to back off - they can assert those claims, but they haven't done so yet.
In this corner... Music!
Universal Music Group — with whom Drake signed a reported $400 million deal last October — has urged Spotify and Apple Music to block AI-generated music, as The Financial Times reported.
By contrast, Grimes has demonstrated openness to the technology, writing in a follow-up tweet: "I think it's cool to be fused w a machine and I like the idea of open sourcing all art and killing copyright."
Consider there are some people who are against all and any copyrights, they want everything to be free for all. I forgot about that segment.
Well, she has the right to do whatever she wants with her own voice.
In this corner... Music!
Universal Music Group — with whom Drake signed a reported $400 million deal last October — has urged Spotify and Apple Music to block AI-generated music, as The Financial Times reported.
By contrast, Grimes has demonstrated openness to the technology, writing in a follow-up tweet: "I think it's cool to be fused w a machine and I like the idea of open sourcing all art and killing copyright."
Consider there are some people who are against all and any copyrights, they want everything to be free for all. I forgot about that segment.
It's of course easy for an artist who owns millions (and is/was married and has children with the richest man in the world) to say that with absolutely no regards and no understanding of artists who actually depend on an income from their art to pay their bills.
Completely out of touch with reality.
Google has a new music ai.
Bring on the armchair. music composers..
https://www.freethink.com/robots-ai/ai-music-generator?fbclid=IwAR0P9IW3-GGcB9zgulbn-cZ-3d0SPPlFO3qyxh3CNPxCRYU-HAltRw63JLY (https://www.freethink.com/robots-ai/ai-music-generator?fbclid=IwAR0P9IW3-GGcB9zgulbn-cZ-3d0SPPlFO3qyxh3CNPxCRYU-HAltRw63JLY)
Article in English about Roberts court case
https://www.diyphotography.net/ai-used-photographers-photos-for-training-then-slapped-him-with-an-invoice/?fbclid=IwAR0KLn-h3XCdTqUEPtdsEZkGaAC4eMp4Nl2xzBT4fOIXaTuqrgQyiYRnvoI (https://www.diyphotography.net/ai-used-photographers-photos-for-training-then-slapped-him-with-an-invoice/?fbclid=IwAR0KLn-h3XCdTqUEPtdsEZkGaAC4eMp4Nl2xzBT4fOIXaTuqrgQyiYRnvoI)
"If the creator doesn’t like the result, she can refine the prompts — as Kashtanova did hundreds of times — until the image matches her intellectual conception. The more one uses prompts, the better one becomes at predicting the results. That’s why new jobs as prompt engineers have sprouted. Businesses seek the fruits of these creators’ “intellectual labor.”"
Here is a 34 year old writer who lost his income because of Chatgpt
https://www.reddit.com/r/ChatGPT/comments/139o1q6/lost_all_my_content_writing_contracts_feeling/ (https://www.reddit.com/r/ChatGPT/comments/139o1q6/lost_all_my_content_writing_contracts_feeling/)
This is a legal decision on what level of transformation constitutes fair use. As fair use is one of the arguments offered as to why generative AI images trained on copyrighted work is legally OK, I think it's worth adding to this list
https://petapixel.com/2023/05/18/supreme-court-rules-andy-warhols-prince-art-is-copyright-infringement/ (https://petapixel.com/2023/05/18/supreme-court-rules-andy-warhols-prince-art-is-copyright-infringement/)
https://www.hollywoodreporter.com/business/business-news/supreme-court-andy-warhol-prince-copyright-1235495647/ (https://www.hollywoodreporter.com/business/business-news/supreme-court-andy-warhol-prince-copyright-1235495647/)
https://www.billboard.com/pro/andy-warhol-prince-supreme-court-copyright-case-ruling/ (https://www.billboard.com/pro/andy-warhol-prince-supreme-court-copyright-case-ruling/)
https://www.cooley.com/news/insight/2023/2023-05-18-supreme-court-rules-andy-warhols-prince-portraits-not-fair-use (https://www.cooley.com/news/insight/2023/2023-05-18-supreme-court-rules-andy-warhols-prince-portraits-not-fair-use)
https://www.theguardian.com/artanddesign/2023/may/18/andy-warhol-copyright-prince-paintings-lawsuit (https://www.theguardian.com/artanddesign/2023/may/18/andy-warhol-copyright-prince-paintings-lawsuit)
https://variety.com/2023/music/news/andy-warhol-prince-images-supreme-court-copyright-1235617622/ (https://variety.com/2023/music/news/andy-warhol-prince-images-supreme-court-copyright-1235617622/)
i have wondered if it was written by Chatgtp as a prank, but thought there are too many mistakes....
nvidia and getty partner up for properly licensed ai creation
https://blogs.nvidia.com/blog/2023/03/21/generative-ai-getty-images/?ncid=so-face-193517&=&linkId=100000195758885&fbclid=IwAR0Ks1rGyjcfSGFPCMdunJGnmNhDrkzGaP71MJUmZvK6PYvxGfPmbNvHSCU#cid=gtcs23_so-face_en-us
i have wondered if it was written by Chatgtp as a prank, but thought there are too many mistakes....
you can ask chatGPT to include grammatical mistakes, misspellings.
this was done in an experiment to see if teachers could detect which essays were ai generated - the teachers failed!
i have wondered if it was written by Chatgtp as a prank, but thought there are too many mistakes....
you can ask chatGPT to include grammatical mistakes, misspellings.
this was done in an experiment to see if teachers could detect which essays were ai generated - the teachers failed!
OMG!
Never thought about that possibility!
Thank you to everyone who keeps posting useful links here.
As things develop this will be our own little documentary for future stock historians…
Just a follow up to my last post in this topic...Yes, but with all the ideas that the European parliament has, what impact will it make? Also this statement is way to vague. What actual laws do you think will come out of it? It will take years (if even something will get written black on white) and then it's already there and nothing can be done about it anymore. That will be the reality of it. Maybe they will fine some big American company or so by then (to collect some money) but everything will go on as usual.
The EU has come one-step closer to having the world's first law regulating Artificial Intelligence. The European Parliament voted today in favor to approve the AI Act. Next step, the talks will now begin with EU countries in the Council on the final form of the law. The aim is to reach an agreement by the end of this year.
From the series of measures, I highlight the following extracted from the news of the European Parliament:
"Generative AI, like ChatGPT, would have to comply with transparency requirements:
Disclosing that the content was generated by AI
Designing the model to prevent it from generating illegal content
Publishing summaries of copyrighted data used for training
Limited risk
Limited risk AI systems should comply with minimal transparency requirements that would allow users to make informed decisions. After interacting with the applications, the user can then decide whether they want to continue using it. Users should be made aware when they are interacting with AI. This includes AI systems that generate or manipulate image, audio or video content, for example deepfakes."
link to European parliament news: https://www.europarl.europa.eu/news/en/headlines/society/20230601STO93804/eu-ai-act-first-regulation-on-artificial-intelligence (https://www.europarl.europa.eu/news/en/headlines/society/20230601STO93804/eu-ai-act-first-regulation-on-artificial-intelligence)
Just a follow up to my last post in this topic...Yes, but with all the ideas that the European parliament has, what impact will it make? Also this statement is way to vague. What actual laws do you think will come out of it? It will take years (if even something will get written black on white) and then it's already there and nothing can be done about it anymore. That will be the reality of it. Maybe they will fine some big American company or so by then (to collect some money) but everything will go on as usual.
The EU has come one-step closer to having the world's first law regulating Artificial Intelligence. The European Parliament voted today in favor to approve the AI Act. Next step, the talks will now begin with EU countries in the Council on the final form of the law. The aim is to reach an agreement by the end of this year.
From the series of measures, I highlight the following extracted from the news of the European Parliament:
"Generative AI, like ChatGPT, would have to comply with transparency requirements:
Disclosing that the content was generated by AI
Designing the model to prevent it from generating illegal content
Publishing summaries of copyrighted data used for training
Limited risk
Limited risk AI systems should comply with minimal transparency requirements that would allow users to make informed decisions. After interacting with the applications, the user can then decide whether they want to continue using it. Users should be made aware when they are interacting with AI. This includes AI systems that generate or manipulate image, audio or video content, for example deepfakes."
link to European parliament news: https://www.europarl.europa.eu/news/en/headlines/society/20230601STO93804/eu-ai-act-first-regulation-on-artificial-intelligence (https://www.europarl.europa.eu/news/en/headlines/society/20230601STO93804/eu-ai-act-first-regulation-on-artificial-intelligence)
Yes, but with all the ideas that the European parliament has, what impact will it make?
It might, but will it come this far? Will then ChatGPT dissapear in the EU? I wonder.
Yes, but with all the ideas that the European parliament has, what impact will it make?
I posted a news article about this law already where it stated that for example GPT Chat has announced that if the law that the copyrighted source material that was used to train an AI has to be made public would pass, they would rather withdraw from the European market than do that, because they fear legal consequences. That would be a rather big impact, don't you think?
...
"Generative AI, like ChatGPT, would have to comply with transparency requirements:
...
Publishing summaries of copyrighted data used for training
... This includes AI systems that generate or manipulate image, audio or video content, for example deepfakes."
...
...
"Generative AI, like ChatGPT, would have to comply with transparency requirements:
...
Publishing summaries of copyrighted data used for training
... This includes AI systems that generate or manipulate image, audio or video content, for example deepfakes."
...
a good first start - I'm hope they consider:
how can those offering ai know what images were used when the systems don't provide that info & how would it be saved &H displayed? besides working thru agencies, artists offer their work on independent website's & POD sites such as FAA
...
"Generative AI, like ChatGPT, would have to comply with transparency requirements:
...
Publishing summaries of copyrighted data used for training
... This includes AI systems that generate or manipulate image, audio or video content, for example deepfakes."
...
a good first start - I'm hope they consider:
how can those offering ai know what images were used when the systems don't provide that info & how would it be saved &H displayed? besides working thru agencies, artists offer their work on independent website's & POD sites such as FAA
This is not a rule for microstock sites offering AI images for sale, this is a rule for companies that develope AI. They, so sites like ChatGTP or Midjourney or stable difusion would have to show which images they used to train their AI.
or Adobe firefly which is an ai art generator too...
This story shows how much extra work is generated when people try to follow up on made-up information (in this case a newspaper article that was never published because AI made it up). It's only a time saver if you don't care about accuracy
Midjourney is adding new features - zoom out. The comments are interesting as well as the article itselfI used it, here my first attempt: very entertaining ;D
https://arstechnica.com/information-technology/2023/06/stunning-midjourney-update-wows-ai-artists-with-camera-like-feature/
That looks like a useful feature.
https://www.newswire.ca/news-releases/shutterstock-offers-enterprise-customers-indemnification-for-ai-image-creation-856356568.html (https://www.newswire.ca/news-releases/shutterstock-offers-enterprise-customers-indemnification-for-ai-image-creation-856356568.html)Then they are very sure of their case or taking a huge gamble with their company. Interesting.
Shutterstock is offering Enterprise customers legal indemnification for AI generated content
"This is a critical advancement, not just for our platform, but for the industry as creatives and business professionals alike can use the AI content generated on our platform for any purpose, whether it's commercial or personal, without worrying about copyright infringement or ethical issues....We're excited to play a leading role in shaping how generative capabilities can be leveraged ethically, safely and in more creative ways than ever. We feel it's a crucial step towards protecting our customers and our artists."
That artists should be able to have their content removed from ai collection material should be the minimum that the courts establish as a new law.
This would of course extend to texts, music, software.
Then they will have to create a new ai version with legally licensed content. The way Adobe did with firefly.
This argument is like making a painting that looks like copyrighted work and saying, oh but I just looked at it on the ointernet, I never downloaded it.
same for music, oh I heard it somewhere, no idea when or where.
It does not help you.
They could however, simply make the ai producer responsible.
If you put out something for commercial use that looks like something that is copyright protected...then the ai scrapers could continue to scrape the entire internet.
Music, text and image producers would the have to keep looking for similars of their work and sue the way they do it now.
This solution would be what the agencies would love.
We will see what happens.
...
If you put out something for commercial use that looks like something that is copyright protected...then the ai scrapers could continue to scrape the entire internet.
Music, text and image producers would the have to keep looking for similars of their work and sue the way they do it now.
This solution would be what the agencies would love.
We will see what happens.
.... But I think artists should get money - A LOT of money for the damage that using their work has caused and that just "removing" one image from the training set once the damage has already been done is not helping.
The way they were promoting it was unfortunate.
https://www.lasco.ai/ (https://www.lasco.ai/)
Not sure how good the evaluations were (no idea who/what Insider Monkey is) but here's there take on the top 15 AI image generators (note that for the top 5 you have to follow a link, and then to get 4-3-2-1 you have to click "Next" links like a slide show. The site is littered with ads)I am not sure whoever wrote this really tried out all these Ai image generators, or at least tried them in a way to be able to make any judgement. For midjourney it says "While users cannot choose specific art style...". But of couse you can say what art style you want for the image to be in your pormots.
https://finance.yahoo.com/news/15-best-ai-image-generators-050331833.html
There is a very on point episode on black mirror that deals with this situation
https://www.imdb.com/title/tt20247352/?ref_=ttep_ep1 (https://www.imdb.com/title/tt20247352/?ref_=ttep_ep1)
There is a very on point episode on black mirror that deals with this situation
https://www.imdb.com/title/tt20247352/?ref_=ttep_ep1 (https://www.imdb.com/title/tt20247352/?ref_=ttep_ep1)
According to some reports, Adobe staff worried they are killing jobs of their own customers with AI:
https://www-benzinga-com.cdn.ampproject.org/c/s/www.benzinga.com/amp/content/33368787 (https://www-benzinga-com.cdn.ampproject.org/c/s/www.benzinga.com/amp/content/33368787)
According to some reports, Adobe staff worried they are killing jobs of their own customers with AI:
https://www-benzinga-com.cdn.ampproject.org/c/s/www.benzinga.com/amp/content/33368787 (https://www-benzinga-com.cdn.ampproject.org/c/s/www.benzinga.com/amp/content/33368787)
Here is the original articles with more details.
https://www.businessinsider.com/adobe-ai-firefly-kill-graphic-designer-jobs-cut-seat-sales-2023-7?utm_source=twitter&utm_medium=social&utm_campaign=business-sf&utm_source=headtopics&utm_medium=news&utm_campaign=2023-07-25 (https://www.businessinsider.com/adobe-ai-firefly-kill-graphic-designer-jobs-cut-seat-sales-2023-7?utm_source=twitter&utm_medium=social&utm_campaign=business-sf&utm_source=headtopics&utm_medium=news&utm_campaign=2023-07-25)
Some key notes:
"Adobe often sells cloud software subscriptions based on the number of seats, or licenses (...). A company with, say, 5 graphic designers in-house would buy five licenses. So if designers are getting laid off, demand for licenses might fall"
.... how some constributors still think AI was a good thing and they will still have a job in 10 years where all they do is enter prompts when not even the customers - the designers - are safe, is beyond me.
According to some reports, Adobe staff worried they are killing jobs of their own customers with AI:
https://www-benzinga-com.cdn.ampproject.org/c/s/www.benzinga.com/amp/content/33368787 (https://www-benzinga-com.cdn.ampproject.org/c/s/www.benzinga.com/amp/content/33368787)
Here is the original articles with more details.
https://www.businessinsider.com/adobe-ai-firefly-kill-graphic-designer-jobs-cut-seat-sales-2023-7?utm_source=twitter&utm_medium=social&utm_campaign=business-sf&utm_source=headtopics&utm_medium=news&utm_campaign=2023-07-25 (https://www.businessinsider.com/adobe-ai-firefly-kill-graphic-designer-jobs-cut-seat-sales-2023-7?utm_source=twitter&utm_medium=social&utm_campaign=business-sf&utm_source=headtopics&utm_medium=news&utm_campaign=2023-07-25)
Some key notes:
"Adobe often sells cloud software subscriptions based on the number of seats, or licenses (...). A company with, say, 5 graphic designers in-house would buy five licenses. So if designers are getting laid off, demand for licenses might fall"
.... how some constributors still think AI was a good thing and they will still have a job in 10 years where all they do is enter prompts when not even the customers - the designers - are safe, is beyond me.
That article is behind paywall. I think that people who did photo-manipulations are already affected most. Other designers - I don't know, maybe it can replace some simple work but not everything, AI would explode if it heard some of my clients requests. :) In my opinion, Canva destroyed designers much more than AI ever could.
NY Times article (paywall) about fake travel guides for sale on amazon. One book used as an example had an AI generated author photo - they pointed out the tell-tale signs.
https://www.nytimes.com/2023/08/05/travel/amazon-guidebooks-artificial-intelligence.html (https://www.nytimes.com/2023/08/05/travel/amazon-guidebooks-artificial-intelligence.html)
amazon should do better in weeding this print-on-demand fakery out, but the scale of the problem when there are bucketloads of these types of fakes being generated makes it hard even if you are being dilligent...
Professionally licensing content is the right way forward.
The technology will not disappear, but users should have the option to work with an ai where the producers are being compensated.
And then the market will find a new balance.
There was that article about the actress from Singapor who licensed her image for video advertising as an avatar.
Some will say how horrible, but she says it all depends on the details.
For musicians there will always be the revenue from live concerts, maybe including live streaming for those who cannot be there.
And of course many musicians or music writers will now write their songs and bring them to life with ai, with full control over everything.
Young people will grow up with all this technology at their fingertips. Who knows what they will create?
ai is just a tool. It will bring forth a new group of talent.
People are uploading AI images on Adobe with the names of the artists they copied included in the title...
That is just wrong. I am surprised Adobe does not have a warning system for famous artists names.
Is this not easy to implement?
Then people would just not mention the artist name in the title - They'd still use it for promting. Same difference.
Then people would just not mention the artist name in the title - They'd still use it for promting. Same difference.
Exactly, they will acknowledge that it’s wrong to use those names in titles and tags but won’t acknowledge that is wrong to copy all those artists.
Then people would just not mention the artist name in the title - They'd still use it for promting. Same difference.
Exactly, they will acknowledge that it’s wrong to use those names in titles and tags but won’t acknowledge that is wrong to copy all those artists.
And you think that human illustrators or photographers do not copy other artists?
And you think that human illustrators or photographers do not copy other artists?
"A federal judge on Friday upheld a finding from the U.S. Copyright Office that a piece of art created by AI is not open to protection."
https://www.hollywoodreporter.com/business/business-news/ai-works-not-copyrightable-studios-1235570316/ (https://www.hollywoodreporter.com/business/business-news/ai-works-not-copyrightable-studios-1235570316/)
Howell is the judge in the case.
"The question presented in the suit was whether a work generated solely by a computer falls under the protection of copyright law.
“In the absence of any human involvement in the creation of the work, the clear and straightforward answer is the one given by the Register: No,” Howell wrote.
U.S. copyright law, she underscored, “protects only works of human creation” and is “designed to adapt with the times.” There’s been a consistent understanding that human creativity is “at the core of copyrightability, even as that human creativity is channeled through new tools or into new media,” the ruling stated.
While cameras generated a mechanical reproduction of a scene, she explained that they do so only after a human develops a “mental conception” of the photo, which is a product of decisions like where the subject stands, arrangements and lighting, among other choices.
“Human involvement in, and ultimate creative control over, the work at issue was key to the conclusion that the new type of work fell within the bounds of copyright,” Howell wrote."
https://mashable.com/article/ai-art-copyright-debate (https://mashable.com/article/ai-art-copyright-debate)
https://www.theverge.com/2023/8/19/23838458/ai-generated-art-no-copyright-district-court (https://www.theverge.com/2023/8/19/23838458/ai-generated-art-no-copyright-district-court)
"Nobody really knows how things will shake out around US copyright law and artificial intelligence, but the court cases have been piling up. Sarah Silverman and two other authors filed suit against OpenAI and Meta earlier this year over their models’ data scraping practices, for instance, while another lawsuit by programmer and lawyer Matthew Butterick alleges that data scraping by Microsoft, GitHub, and OpenAI amounted to software piracy."
In a German article about what can artists do to protect themselves from ai, they mentioned „glaze“, a software that slightly changes your images and males them a lottle soft or fuzzy but renders them unusable for ai.
https://glaze.cs.uchicago.edu/ (https://glaze.cs.uchicago.edu/)
This is maybe something agencies could use to prevent the data scraping of our work without proper licensing of data sets.
And that we might use on our own websites.
Will try to learn more about this.
https://www.makeuseof.com/how-to-use-glaze-protect-art-from-ai/ (https://www.makeuseof.com/how-to-use-glaze-protect-art-from-ai/)
If this really works, then protecting images from ai abuse will be much easier than protecting written content.
How much risk does a contributor actually face when uploading generative AI content?
I recently uploaded some AI images (nothing special, more to test if they would be accepted), but not before I had read the terms of the respective AI generators to see if I could use the content for commercial purposes. Furthermore, I adhered to all the guidelines that Adobe Stock imposes on gen-AI content. However, I did use generators that are currently being addressed by Getty Images and are not from one of the "ethical" generators (such as Firefly presents itself, aside from the fact that you can't use it for commercial purposes due to its beta status anyway). So, I tried to "play by the rules" as far as they are currently clear and thus attempted to limit my risks. But how do you view this? Aside from the question of whether you are in favor of or against AI content for stock purposes.
You can check if a file was created using gen ai tools in this link.
https://verify.contentauthenticity.org/inspect
Seen this? Is it legit or a trap?
https://haveibeentrained.com/
Didn't LAION threaten to sue some dude that tried to have his images removed from the dataset?
Dall-e3 will allow artists to opt out
https://openai.com/dall-e-3
...When cameras first came out it was denied any creative value and photographers were not considered artists.
...
....
The judges should try themselves to create an image like that.
They would quickly understand how much work and how much human thinking goes into this.
....
The judges should try themselves to create an image like that.
They would quickly understand how much work and how much human thinking goes into this.
of course it's futile to hope for rational thinking by many US congressfolk & judges. their level of ignorance concerning science and technology is staggering consider evolution-, vaccine- & climate-deniers
admittedly it was a long time ago - there's former Senator Ted Stevens, chair of the Senate committee responsible for regulating the internet:
the Internet is not something that you just dump something on. It's not a big truck. It's a series of tubes. And if you don't understand, those tubes can be filled and if they are filled, when you put your message in, it gets in line and it's going to be delayed by anyone that puts into that tube enormous amounts of material, enormous amounts of material.
Why don't you create specific targeted sellable content with ai and then explain to me again how your mind was never involved doing that?
getty announces their ai generator
https://www.theverge.com/2023/9/25/23884679/getty-ai-generative-image-platform-launch (https://www.theverge.com/2023/9/25/23884679/getty-ai-generative-image-platform-launch)
How do you create with pushing a button on a camera?
How do you create with pushing a button on a camera?
I do not know about you, maybe you are only doing snapshost, but my microstock photos are more than just "pushing a button".
It can easily take me an hour just setting up backdrops and lighing equipment and arrange photo props for one photo. Then taking the actual photos and editing them can easily take me up to 30 minutes per photo as well.
Now I can get the same result in 5 seconds with Midjourney....
And I already told the story once about how everyone constantly wants me to take photos of ther wedding, their child, their pet, their anniversary and when I offer to just give them my camera, then suddenly it seems to be more than "pushing a button" after all and they tell me they just can't make the photos look and I have to do it. So my "pushing abutton" seems to be different then their "pushing a button" after all? I am so sick of my skill and effort in taking photos being downtalked whenever it suits someone, but when I tell people to just do it themselves it suddenly becomes an unieque skill only I seem to possess?
How do you create with pushing a button on a camera?
I do not know about you, maybe you are only doing snapshost, but my microstock photos are more than just "pushing a button".
It can easily take me an hour just setting up backdrops and lighing equipment and arrange photo props for one photo. Then taking the actual photos and editing them can easily take me up to 30 minutes per photo as well.
Now I can get the same result in 5 seconds with Midjourney....
And I already told the story once about how everyone constantly wants me to take photos of ther wedding, their child, their pet, their anniversary and when I offer to just give them my camera, then suddenly it seems to be more than "pushing a button" after all and they tell me they just can't make the photos look and I have to do it. So my "pushing abutton" seems to be different then their "pushing a button" after all? I am so sick of my skill and effort in taking photos being downtalked whenever it suits someone, but when I tell people to just do it themselves it suddenly becomes an unieque skill only I seem to possess?
Nightshade is a tool that performs a data poisoning attack against generative AI image models:
https://www.technologyreview.com/2023/10/23/1082189/data-poisoning-artists-fight-generative-ai/?utm_source=Twitter&utm_campaign=site_visitor.unpaid.engagement&utm_medium=tr_social (https://www.technologyreview.com/2023/10/23/1082189/data-poisoning-artists-fight-generative-ai/?utm_source=Twitter&utm_campaign=site_visitor.unpaid.engagement&utm_medium=tr_social)
Nightshade is a tool that performs a data poisoning attack against generative AI image models:Splendid! the best response instead of whining ...
https://www.technologyreview.com/2023/10/23/1082189/data-poisoning-artists-fight-generative-ai/?utm_source=Twitter&utm_campaign=site_visitor.unpaid.engagement&utm_medium=tr_social (https://www.technologyreview.com/2023/10/23/1082189/data-poisoning-artists-fight-generative-ai/?utm_source=Twitter&utm_campaign=site_visitor.unpaid.engagement&utm_medium=tr_social)
https://petapixel.com/2023/10/29/ai-and-me-how-image-generation-is-changing-my-role-as-a-photographer/
One photographer's perspective on use of genAI images, including composites where the "set" is genAI and the studio is used to shoot the model who will be photoshopped into the set.
You can still use Adobe firefly for free for a while.
But if you click on your account you can see your current credit allowance and usage.
https://discord.com/channels/1076190214369853510/1087560280982175784
https://petapixel.com/2023/11/05/genai-and-the-forced-evolution-of-photography-from-artifice-to-authenticity/ (https://petapixel.com/2023/11/05/genai-and-the-forced-evolution-of-photography-from-artifice-to-authenticity/)
I like the notion that "Photography is more than just an image—it’s our connection to the real world, to one another, and to moments that inform our decisions."
His twitter feed references this article
https://futurism.com/adobe-caught-selling-ai-generated-images-israel-palestine-violence (https://futurism.com/adobe-caught-selling-ai-generated-images-israel-palestine-violence)
I think the pseudo-editorial images have to be removed - like the 9/11 images that were allowed in and then removed a few months back.
The Futurism article doesn't mention Freepik, but their collection of over 30 million genAI images includes over 40k for a search for "gaza"
https://www.freepik.com/search?format=search&last_filter=query&last_value=gaza&query=gaza&type=ai (https://www.freepik.com/search?format=search&last_filter=query&last_value=gaza&query=gaza&type=ai)
And even Shutterstock's sad collection of DALL-E creations includes a couple (along with their standard note "Important information - This content was generated by an Artificial Intelligence (AI) system. Shutterstock does not review AI-generated content for compliance with Shutterstock’s content compliance standards. AI-generated"):
https://www.shutterstock.com/image-generated/gaza-city-palestine-2-children-playing-2384676855 (https://www.shutterstock.com/image-generated/gaza-city-palestine-2-children-playing-2384676855)
https://www.shutterstock.com/image-generated/outdoor-photo-gaza-city-palestine-2-2384676351 (https://www.shutterstock.com/image-generated/outdoor-photo-gaza-city-palestine-2-2384676351)
Supposedly it was today but AI ACT agreement in Europe is not reached yet.
This week France, Italy and Germany came with the idea of Self-regulation. In some cases self regulation can be interpreted as no regulation at all.
Chinese court declares that AI-generated image has copyright
https://www.technollama.co.uk/chinese-court-declares-that-ai-generated-image-has-copyright (https://www.technollama.co.uk/chinese-court-declares-that-ai-generated-image-has-copyright)
from uncle pete
https://www.msn.com/en-us/money/companies/ny-times-sues-openai-microsoft-for-infringing-copyrighted-works/ar-AA1m75sX?ocid=00000000&pc=U528&cvid=36cdc2530ee347549955a4670eb08328&ei=17 (https://www.msn.com/en-us/money/companies/ny-times-sues-openai-microsoft-for-infringing-copyrighted-works/ar-AA1m75sX?ocid=00000000&pc=U528&cvid=36cdc2530ee347549955a4670eb08328&ei=17)
NEW YORK (Reuters) - The New York Times sued OpenAI and Microsoft on Wednesday, accusing them of using millions of the newspaper's articles without permission to help train chatbots to provide information to readers.
The newspaper's complaint, filed in Manhattan federal court, accused OpenAI and Microsoft of trying to "free-ride on The Times's massive investment in its journalism" by using it to provide alternative means to deliver information to readers.
"There is nothing 'transformative' about using The Times's content without payment to create products that substitute for The Times and steal audiences away from it," the Times said.
The case is New York Times Co v Microsoft Corp et al, U.S. District Court, Southern District of New York, No. 23-11195.
I moved the thread to the new ai forum.
Interesting article co-written by a journalist and a law professor about where the fair use argument has succeeded - and failed - in prior cases. The key issue, IMO, is that things that might be fair use by an individual for personal use, or researchers for academic use are not so if done by a for-profit company for commercial use.
https://arstechnica.com/tech-policy/2024/02/why-the-new-york-times-might-win-its-copyright-lawsuit-against-openai/
After a discussion of why Google won its case about building a search engine for books, including that it was built to be unable to produce no more than snippets, the article says:
"Ultimately, the fate of these companies may depend on whether judges feel that the companies have made a good-faith effort to color inside the lines. If generative models never regurgitated copyrighted material, then defendants would have a compelling argument that it is transformative. The fact that the models occasionally produce near-perfect copies of other people’s creative work makes the case more complicated and could lead judges to view these companies more skeptically."
Google is now also playing in the AI league.
With the Gemini model Google is attacking at the forefront. Gemini is a multimodal model that can process text, images, video, music and other documents such as PDFs as inputs and generate corresponding outputs.
Google offers a cloud-based API platform for using and developing your own AI models, which can be created from the smaller Gema models.
Even some third-party open source models can be used.
In my opinion, Google created a strong overall package of AI models, API and cloud environment.
Despite the current problems I would assume that Google has a big chance to take the first place from Open AI in the long term.
https://blog.google/technology/developers/gemma-open-models/ (https://blog.google/technology/developers/gemma-open-models/)
https://deepmind.google/technologies/gemini/#introduction (https://deepmind.google/technologies/gemini/#introduction)
https://blog.google/products/ads-commerce/gemini-models-are-coming-to-performance-max/ (https://blog.google/products/ads-commerce/gemini-models-are-coming-to-performance-max/)
https://blog.google/technology/ai/google-labs-imagefx-textfx-generative-ai/ (https://blog.google/technology/ai/google-labs-imagefx-textfx-generative-ai/)
Free testing of Google's AI Image Generator: https://aitestkitchen.withgoogle.com/tools/image-fx (https://aitestkitchen.withgoogle.com/tools/image-fx)
Google is now also playing in the AI league.
With the Gemini model Google is attacking at the forefront. Gemini is a multimodal model that can process text, images, video, music and other documents such as PDFs as inputs and generate corresponding outputs.
Google offers a cloud-based API platform for using and developing your own AI models, which can be created from the smaller Gema models.
Even some third-party open source models can be used.
In my opinion, Google created a strong overall package of AI models, API and cloud environment.
Despite the current problems I would assume that Google has a big chance to take the first place from Open AI in the long term.
https://blog.google/technology/developers/gemma-open-models/ (https://blog.google/technology/developers/gemma-open-models/)
https://deepmind.google/technologies/gemini/#introduction (https://deepmind.google/technologies/gemini/#introduction)
https://blog.google/products/ads-commerce/gemini-models-are-coming-to-performance-max/ (https://blog.google/products/ads-commerce/gemini-models-are-coming-to-performance-max/)
https://blog.google/technology/ai/google-labs-imagefx-textfx-generative-ai/ (https://blog.google/technology/ai/google-labs-imagefx-textfx-generative-ai/)
Free testing of Google's AI Image Generator: https://aitestkitchen.withgoogle.com/tools/image-fx (https://aitestkitchen.withgoogle.com/tools/image-fx)
Being Woke and diverse has created the opposite of what an honest AI would do.
"It appears that in trying to solve one problem - bias - the tech giant has created another: output which tries so hard to be politically correct that it ends up being absurd."
"Gemini also generated German soldiers from World War Two, incorrectly featuring a black man and Asian woman."
https://www.bbc.com/news/technology-68412620 (https://www.bbc.com/news/technology-68412620)
Reverse Bias is still bias. While trying to compensate for what the AI got from general images, they have created a mockery.
"When the AI was asked to show a picture of a White person, Gemini said it could not fulfill the request because it "reinforces harmful stereotypes and generalizations about people based on their race." :o
https://petapixel.com/2024/03/07/recreating-iconic-photos-with-ai-image-generators/
None of the copies are great, but they're clearly more than "inspired by" the very famous images they were trained on.
GB200 Superchips deliver up to a 30x performance increase compared to the NVIDIA H100 Tensor Core GPU for large language model inference workloads.
It seems to me that only a very tiny percentage of this is being paid to artists.