Isn’t AI art derivative work? If yes, they are infringing on copyrighted work.
Stable Attribution
221–230 of 365 posts
Re: Stable Attribution
#222As one of my best friends told me in 1971 (we were six!), every image and sound that we produce has already been produced somewhere else in the infinite universe.
The observable universe has only 10^80 atoms. A small image of 128x128 pixels has more variations than that.
Re: Stable Attribution
#223How does it even work? AFAIK SD works in a "convoluted" latent space that is a result of all the training data, it's not like it takes a few images and smashes them together to create a new one.
Re: Stable Attribution
#224Earlier quoted context omitted.
> So let's say, if an artist developed a particular style and someone wants to hire them for a business project like a game they can't feasibly just learn that style and use it so they hire the artist. Later other people catch on this style and develop over it. It only works because monetising through copying the style is not very feasible. I don't think copying an art style is that hard. Professional artists in your…
> hey haven't been in the past and they shouldn't be So what's your suggestion, free food and housing for the artistic types or mercy killings?
Nothing. Continue as we currently are where artistic style is not protected, but output is. Artists get work making art as they always have, but they're competing against AI that can pump out shit quality work very quickly. If you can't do better than that as an artist then you should find another line of work.
Re: Stable Attribution
#225I like this because they are trying to show how AI is a copyright laundry. I can see other commenters picking apart its method of heuristically guessing at source images from training data. That obviously won't be accurate, or a full picture, but I wonder if it would convince a judge. An interesting challenge for these heuristics would be to take the picture under test along with its prompt, retrain the model without…
Without retraining the model, you can often get a different image by generating it again or modifying the prompt slightly. Makes people wonder if changing the training set would have any bigger impact.
Re: Stable Attribution
#226I gave it a photo I had Stable Diffusion 1.4 generate from the prompt "avatar for saurik". If you dig through the CLIP database, you will find that the model was trained on a ridiculously large number of copies of my Twitter profile photo due to it being included when people screenshot popular tweets I've posted (which, notably, also means that it is rather low resolution). https://www.stableattribution.com/?image=e8…
This. They probably simply used an “image similarity” algorithm, of which many are readily available and do not require much computing power.
The credit at the bottom of the website for “Chroma”, a startup with no live product and hiring, suggests this could be a growth hack. Like “let’s ride the buzz of the moment with a barely useful tool quick to develop, hit front page of HN, and get some visibility.” Good for them, it worked, but yeah the product is probably bogus as you’ve demonstrated.
Re: Stable Attribution
#227From the beginning of using Stable Diffusion in local and cloud instances, I’ve been promoting SD to generate objects I know nobody has ever drawn before. “Airplane by Tesla”, “Taylor Swift flying in the clouds”, “Little girl riding on an ira descent unicorn and chasing butterflies in the clouds”, “Turkey as a Judge” etc. I highly encourage everyone to try doing that. The results are absolutely atrocious in the begin…
Sorry, but you're reading into noise. Anyone can reproduce an image anyone else made by only knowing the model checkpoint, positive and negative prompt, seed, sampler and sampling steps, &c &c they used. (Well, in principle, and usually in practice too. Interfaces might give different results now compared to a version from a few months ago because implementations of certain things changed, or if you use xformers then all your outputs are slightly non-deterministic, other exceptions that prove the rule like that.)
Some prompts I've come up with generate excellent and definitely novel results (without necessarily much work put into refining the prompt), others are extremely hard to get working well with hours of work even if I know it's something that isn't novel.
Re: Stable Attribution
#228Earlier quoted context omitted.
Am I seeing the same thing you are in those two images you linked to? The first one, generated by AI has you looking at the camera. The other one has you looking at an instrument. They don’t look much like each other to me, in terms of pose or anything. The first images suggested by Stable Attribution looks a lot more like the AI image to me, in terms of pose and everything.
I think you're missing the point. How does Stable Diffusion know "what does saurik look like?". The answer is of course that it's seen saurik's profile pic in training data. Stable Attribution is not showing that. As another comment[1] points out: > This appears to be just looking for the nearest neighbors of the image in embedding space and calling those the source data. Stylistically similar images are not the same…
Interesting. So it only shows images that were transformed / mixed to get the output, but does not show images used to learn how to transform / select them?
Sounds very much like a human would do it.
If I 'know' how to recognize saurik and I know how anime is supposed to look like, I can check my digital photo library for a picture of saurik and than use that picture as a template to draw an anime version of saurik. If someone later asked me what pictures I used the photo is the only one I'd present. Not the thousands of anime pictures I have seen teaching me what anime looks like, nor the picture my eyes took meeting saurik.
Re: Stable Attribution
#229Earlier quoted context omitted.
It is expected of any professional artist to have an online portfolio if they are serious about generating work. Scraping my portfolio that I put out because I want to generate revenue is a shitty thing to do. Also 'trained' is a complete misnomer. AI is fed images made by humans, labelled and tagged by humans, categorized by styles defined by humans, then plotted, copied, traced by a program written by humans. Along…
> Also 'trained' is a complete misnomer. This here shows that you are speaking without understanding what you are speaking about. AI is absolutely trained. It's a process that is quite literally inspired by the way we understood neurons to work in the 1970s. AI start with a big batch of random numbers. There's a big fancy scientific method used to adjust those numbers in order to cause the system to learn to do some…
I personally care very little for copyright or copycats. I have great disdain for those who would profit off the backs of the labor of others. Saying that art often involves little to no effort just shows how ignorant you are of the subject. I am not threatened by AI and frankly I don't see it as competition, it's not really that good. Besides that the majority of my art is three dimensional. I am just saddened by how it will be misused to disrespect the effort and labor of the artists that it is feeding off of. No matter how complex AI might be, it is not sentient and it relies on human work and direction and is therefore not actually creating.
Re: Stable Attribution
#230Yeah, it's bullshit, but digging into a specific point from their FAQ:
> Usually, the image the model creates doesn’t exist in its training data - it’s new - but because of the training process, the most influential images are the most visually similar ones, especially in the details.
Would be cool if this were true, but I don't think it is, because the prompt you used and the captions on the training images are being completely ignored. If two different words tend to be used in captions for very visually similar images, and you use just one of those words in your inference prompt, I'm pretty sure the images that were captioned with the word you used are much more "influential" on your output than the images that were captioned with the word you didn't use. (Like, "equestrian" vs "mountie" or "cowboy" or something.)