Quote from: cascoly on March 22, 2023, 12:46

[...]natural selection moves along

Sorry but nothing "natural" in AI...

Also digital camera had nothing "natural" vs old analogue camera... at the time when digital was born

For the thesis that advertising for stock photography should bring something, no one here has yet provided proof - all just personal hypotheses and a question of faith.

Agree. Advertising bring absolutely nothing to single controbutor.
But in general terms adv can drive more new clients to a specific agency and, in general terms, can give a growth of sales (for everyone).

Why does adobe reject for quality issues when there's nothing wrong with the submitted photos even viewed at 100 percent? I spend time cloning out people in the picture and I think I've done a really good job. I'm actually a former designer trained in the 80s so I am mainly self-taught at editing. Is there anyone from adobe on here? The photo rejected is too big to attach here.
I had a 12 rejected last time and about 6 accepted. I never had this rate of rejection before so you would think I must be getting worse at this but I know that I'm not. I have less than 500 photos on there due to the rejections but they seem to be selling well for such a small number, especially this year

If you go to their discord chat server there is a channel for rejection explained

Interesting points. I wonder how this is different than submitting an editorial image as commercial, or an image without model release, which the agency lets slip through? Who's responsible for the error? The contributor for having made an incorrect submission, or the agency for letting it slip through and offering it with wrong license terms?

I always thought that the contributor was still responsible in such cases.

Good question!
In this case I would say the author is resposable, because he does not own the copyright.

But you're still not considering the other side, the use of image:
Following your example, if I should put for commercial use something like, let's say, a well known and famous car...
The legal problem would eventually rise only and when the image would be used for commercial.
In other words, it's not the image that break the rules, it's the use of it that could do

You're talking about something that has nothing to do with AI
It's called "sensitive use", and it's a well know issue, it's absolutely managed on agency side and has nothing to do with the content.

The "not allowed" list of DALL-E (and other engines) is made to prevent the creation of the content; at the contrary, the sensitive use of ANY content (AI generated or not) is an agency side problem

Quote from: Uncle Pete on March 01, 2023, 12:44

We are not responsible for the license terms

That's a strange view of things. You think because you are not the one who made the license terms you bear no responsibility?

Absolutely yes. The creator is resposible of content copyright, absolutely not of the terms of license given to the buyer.

Telling the person who wants to license images, that there are restrictions, is the duty of the agency.

This is absolutely correct, this is the truth, no way to say that's not the case!
My opinion, of course 

I have files that are waiting 5 days for inspection.
That wasn't situation before.
They were accepted/rejected in a 3 days time tops.

Anybody else ?

Ai generated images take much more time to be approved, up to ten days, while traditional photography review is quickly as usual for me, max a couple of days

All Midjourney have to do is to add this text to their End User License Agreement:

"By downloading this image you agree not to sell/distribute it through stock agencies."

If the customer doesn't agree, he/she simply won't be able to download the generated image.

Sorry but this is not a solution.
First, it's simply a gift for dozens of other engines that give commercial use. 
Second, it has already discussed, it's not so clear how to distinguish what you can and cannot do with your own images.
Someone gave examples with the restriction for the buyers who license content, but these are not relevant. These are restrictions for buyers, not for the copyright owner.

If it were simple as you said it would have already been done.

Force AI engine to pay the source IS the problem, not to lock the engine itself. AI is between us and obviously nothing will stop it to work

It depends on the company's Terms. Take for example the two biggest marketplaces for 3D models - Turbosquid and CGTrader.

Turbosquid doesn't allow images, generated from their models to be sold on stock markets, but CGTrader does.

Really? I didn't know this is possible, I'm curious and I'll take a look how they can exactly restrict commercial rights. Thanks for the info

Is this answer sufficient? Can I start uploading the generated files?

Reading the Adobe terms
is your responsability, submitting generative AI content, to own all the necessary rights.
So, it's up to you to consider (or not) enough the Wombo mail, no one else could answer you

From the FAQ: https://helpx.adobe.com/stock/contributor/help/generative-ai-content.html

Ensure you have the appropriate rights to submit.
You must have all the necessary rights to submit generative AI illustrations to Adobe Stock for licensing and use as described in our contributor terms (e.g., broad commercial use).  You must review the terms of any generative AI tools that you use to confirm that this is the case before you submit any AI-generated content.

Do: Read the terms and conditions for generative AI tools that you use to ensure that you have the right to license all generative AI content that you submit to Adobe Stock under the contributor terms. For example, you cannot submit any content if you are not permitted to license it for commercial purposes.

 
incredible

Artists behind a lawsuit against AI: 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/

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

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 

First part. LOL. 2 points re. that

    1. You know anyone can log into Midjouney and see exactly how "hard" it is in real time don�t you? (you get to see the prompts and the images produced in real time, highly recommend if you want to know how seriously to take these comments). Alternatively watch a YouTube video or two.

    2. You know we can still see older work in the portfolios of people claiming this is just a new tool in an �artists� toolbox? (and how they instantly made a quantum leap not only in craft but also in composition, artistic vision etc.)

These arguments are silly. The evidence is right there in the open, at least until Midjouney comes off a discord server and artists delete their older work so we don�t get to witness the process anymore.

I know I can copy prompts; but learning how to write a prompt to obtain your unique image it's completely different job.
Yes of course you can copy, and it's far from necessary to copy. You can also obtain hundred of nice images for (let's say) valentine's day with really simple inputs: copy prompts it's not an issue if you can have a good image only asking "valentine's day".

But: creating an original different work you are thinking about is completely different: it takes time and several inputs; and midjourney it's not free, and not cheap at all (you pay for a year more or less the same than Adobe creative cloud subscription).
When you finally have a good image (or series of), that's not enough: upscaling is a pain, takes more time, and once again it's not free, you have to pay software.
Finally you can do title and keyword.

Are you sure that so many people will  pay so much to obtain few money flooding agency with hundred of similar images? I don't think it will go this way.
In my opinion, at the beginning (now) there will be the flood; but soon many people will realize that earn money from AI it's not automatic, not fast, not easy.

EDIT: I would like to add an example from my real last days.
I went in a music studio to shoot musical instruments, interiors, details, various eqwuipment and so on... It takes three hours to produce about 100 good photos.
Then three hours more for post production, and I have 100 photos ready to go; total six hours of work.

100 good images with AI with same subject... it will take not less than three/four days of full immersion job in front of computer.  Of course I'm talking about GOOD images, not one hundred of random musical instruments.

(keywording is the same for both works so it doesn't matter)

This is what I mean when I say "it's hard to work on it"