This is a great way to show that Stable Diffusion doesn't copy.
Stable Attribution
81–90 of 365 posts
Re: Stable Attribution
#82I 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…
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.
Re: Stable Attribution
#83This is a great website, but not in the way the authors intended. Based on some of the examples they explicitly provided, it is clear to me Stable Diffusion creates novel art. Here's a random example https://www.stableattribution.com/?image=a2666aee-0a1a-411b-... I will admit this is a nice tool for verifying the creations of SD aren't pure copies, so I think it will be useful for a time. But as AI-generated images s…
> Based on some of the examples they explicitly provided, it is clear to me Stable Diffusion creates novel art.
You're jumping to a conclusion that the data doesn't warrant, I suspect because it's a conclusion that suits you.
They're doing something like a "reverse image search" from an AI generated image over the original dataset and returning a few examples that have a high degree of similarity. There's no guarantee that the images they return are actually the ones combined to create the AI image. In fact their results are dubious - see Saurik's comment:
https://news.ycombinator.com/item?id=34671149
I don't have an opinion regarding the question of whether SD creates art or not. To be honest, as someone who enjoys art or kind-of-art in many forms, it's not important to me (although, of course, I can see why it is important to someone who makes a living from art or AI generated images).
However, this website doesn't add anything except noise to either side of the debate, from what I can see.
Re: Stable Attribution
#84This appears to be just looking for the nearest neighbors of the image in embedding space and calling those the source data. This by definition would find similar looking images, but it's not strictly correct to call it attribution. To some extent all of the training data is responsible for the result - as an example, the model is also learning from negative examples. The result here may feel satisfying, but it's ove…
Yeah, it seems like it'll just as happily 'attribute' human-made images as well, which calls the whole thing into question. If it's really showing the images that stable diffusion has 'stolen from', and it'll do the same for humans, does that not mean people are equally guilty?
Maybe Stability AI is playing 4D chess and made this website themselves as a sorta "false flag" to help demonstrate that what SD is doing is no different than what humans do, to help them win any legal battles.
Re: Stable Attribution
#85Ah, a nice visual proof that these AI systems are actually synthesizing images with a degree of inspiration from prior art similar to the way humans do.
Until you upload a human created image...
Re: Stable Attribution
#86Earlier quoted context omitted.
The core of your concern (& argument) seems to be the problem of existing business models becoming disrupted by this technology. But the point of good law isn’t to protect an established business model. If that were the case, we would have outlawed the loom because it displaced weavers, and the camera (sorry portrait painters) and the iPhone. (How many telegraph operators are left? None!) When an artist learns to dra…
Sure, it's disruptive and that's fine. The problem is that there's no mechanism to compensate the people who enable your new disruptive machine. As I said, humans learn but the phase humans do it still allows for people be compensated. I'm not anti-AI at all, I think its great and I think the artist who can leverage it can hugely benefit from it but it is not fair to just take something from people away.
So the parent post to yours said he’s taking piano lessons. Let’s suppose he becomes great. And let’s suppose he writes his own music. How is Taylor Swift supposed to get paid by him from his early lessons which have undoubtedly played a key role in not only his love for music but the song he writes today?
Re: Stable Attribution
#87I was taught to paint by instructors, and then refined my abilities by studying paintings of the old masters, right down to their brushwork and core techniques visible in the paintings to all who see them. Now I go and create a painting called Sunflowers. Does Van Gogh's estate own some of my work?
Does your work eclipse the master you studied? That's too bad for that one master but often they share in your fame. And each artist eventually fades, passing the torch to the next generation.
Have you studied all masters and eclipsed them, without acknowledging them so they can share in your fame? Will you use your untiring, undying skill to flood the market with your work so "artist" ceases to be a profession?
That's categorically new, and worth preventing.
Re: Stable Attribution
#88To actually accomplish something like this purports to be (the linked tool only searches for similar images and doesn't tell you anything about how information ended up inside the model), you could try removing individual images or sets of images from the same artist from the training dataset to see what outputs the resulting model would lose the ability to create. It would be expensive to do that for more than a few…
Are these models actually "stable" (heh)? Or would changing anything in the dataset result in a butterfly effect so to speak, thus a completely different output for the same prompt?
Re: Stable Attribution
#89I 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…
Unless there are imitation Kincades in the training set labeled with the name Kincade, I would expect the model to fail to produce anything relevant.
It’s a strange situation. Certainly a human painter is free to study copywritten works closely and then produce art in the style of the other artist, provided the resulting work is “in the style of” but does not copy a specific painting. So why is a human SD-artist not allowed to do the same with their preferred tool? Perhaps because we can draw a causal line (a very fuzzy one) between the original and the knock off? But wait… in the human painter case the same fuzzy line exists, it’s just through wet-ware not hardware.
Perhaps passing first into a LLM trained to generate good prompts but never output specific artists’ names could get close? Has someone tried this?
Re: Stable Attribution
#90Uploading works by real human artists gives you a batch of results that resemble a reference board (mood board, inspiration board, etc) the artist could have been looking at while creating their original work of art. Obviously it’s not the actual reference board, the only way to get that is to ask the artist yourself, but it sure looks like what you’d expect their reference board to look like. This site is grift, of…
The AI does NOT build or use reference boards for specific prompts. The only reference it has is the prompt itself, which gets distilled down into a list of 512 numbers, each one of which the AI associates with a particular image feature (or set of features). The only reference material it has is the training set. Most images are not actually retained in the model; but certain statistically significant or repeated im…
In a literal sense, no, it does not use reference boards. I was being glib, perhaps too glib. A less objectionable rephrasing might be “the AI is composing a bunch of visual features together into a coherent image; it’s cool that this tool can show you images in the training set where the AI might have learned those visual features from.” It may still be inaccurate to say “reference boards” at all, because the temporality is reversed: human artist has a reference board, then does some black box process in their brain to draw inspiration from them, then outputs the final art piece. The AI draws on all the training data to produce the final image and it’s only by analyzing the final image that you can reconstruct which images in the training set were important.
Mostly I was just tickled by the fact that you can now get something that looks like a reference board for the generated image. There are some parallels to the human process, but maybe there are not enough parallels or the parallels don’t run deep enough to make it sensible to call this “the AI is using a reference board”.