Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Stable Attribution

stableattribution.com

Post reply on HN
Print view View original

101–110 of 365 posts

Re: Stable Attribution

#101

Post by mrtksn »

bioemerl wrote: post #94
mrtksn wrote: post #75

Earlier quoted context omitted.

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.

I don't get the assumption that there should be. The machine was trained on publicly available hard that was already free. Why do people think they need to be compensated for something they put up online for free? They don't have the right to not allow people to learn from it, that's just never been a part of copyright.

They put it online for free for human consumption. Because the tech is very new, old concepts and laws don't cover it and that's not the point.

The assumption that there must be compensation comes from the capitalist society that we live in. Switching to Communism or something else can be a solution to not directly pay people who do works and still have them around.

Re: Stable Attribution

#102

Post by bioemerl »

esperent wrote: post #83
goldemerald wrote: post #8

This 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 guarante…

I have to be correcting you here, stable diffusion does not combine images.

Re: Stable Attribution

#103

Post by mrtksn »

codetrotter wrote: post #93
mrtksn wrote: post #78

Earlier quoted context omitted.

> 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?

> free food and housing for the artistic types Food and housing should be a human right, and it is only because of greed and fear that society allows someone to become homeless. Not only should we provide housing and food for the artists. We should do it for everyone. And then they can spend time doing what they want, and earn more money that way but never have to worry about housing or basic food for survival.

I guess you first should do your revolution, establish your new order where food and housing is a given right and later go after the work of the artist.

Re: Stable Attribution

#104

Post by saurik »

codetrotter wrote: post #82
saurik wrote: post #35

I 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.

The slight adjustment of where I'm looking is minor. The instrument is uncommon and honestly difficult to get stable diffusion to generate correctly at all; though, from my experience playing with this (I spent a lot of time trying to figure out why it knew who I was before discovering the CLIP database browser), I'm going to argue that the reason that hand is showing up in the position it is is because of my hand holding the violin there. Frankly, we might also as well start nitpicking that the suit-like thing being worn in the generated image is not a tuxedo and the generated person looks a tad bit rounded and has more hair ;P.

However, the key thing here is: do you really think "avatar for saurik" is going to come up with something out of the blue--out of all the numerous random images of people that exist and who have avatar/profile photos... people wearing lots of different clothing and in different orientations--where we can even be talking about such silly things as props and gaze direction? I will assert that would be ridiculous. Clearly seeing at least one photo of me (and AFAIK it was only trained on thousands of copies of that single photo) was absolutely crucial to the construction of this image, and yet this website isn't finding any such to show as it isn't really doing what it is claiming to do (and it isn't clear to me how it could without the original prompt).

From there, SD is upscaling from memory a lot and filling in a ton of details (as almost all of the copies of my photo it was trained on are very small, embedded in screenshots of tweets), but the cornerstone of that construction is clearly my Twitter profile photo... and then, once you do that, you can go back and attempt to rationalize "these were the photos that were most similar to the photo that we generated, and so I guess those were what the algorithm used to generate this image", but--at least in this case--it is pretty obvious that that isn't how this worked as there's no way you start with "avatar of saurik" and arbitrarily pluck an image that is this similar to the one photo of saurik you have.

Re: Stable Attribution

#105

Post by geuis »

I agree with several other commenters on this. I went through maybe 20 different images, and in every case there were no clearly identifiable ties back to the "sources". If anything, I'm more impressed at what SD is able to do.

However, I have definitely found at least a handful of generated images over the last few months that were almost 100% the same as the training image. I don't have the references handy, but it shouldn't be too hard to replicate. I was looking at different artists I liked on Artstation but that had few examples of their work. I then used a fairly standard prompt and only changed references to the artists I was testing out. In several of those instances, the generated images in SD were near 1-1 with one of the source images the AI was trained on.

Re: Stable Attribution

#106

Post by killjoywashere »

Retr0id wrote: post #96
codetrotter wrote: post #82

Earlier 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…

[flagged]

Re: Stable Attribution

#107

Post by astrange »

josephg wrote: post #65
mrtksn wrote: post #46

Earlier quoted context omitted.

The discussion over novelty is useless, all these legal structures like copyrights patents royalties and licenses are about creating business structures to allow artist or inventors be compensated. They were already imperfect in it and now suddenly a new technology drags their work into the wilderness with no stuctures for compensation. The images created by the AI are indeed novel but they feed on the work of people…

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…

> How many telegraph operators are left? None!

They're in the Navy, aren't they?

Re: Stable Attribution

#108

Post by astrange »

mrtksn wrote: post #101
bioemerl wrote: post #94

Earlier quoted context omitted.

I don't get the assumption that there should be. The machine was trained on publicly available hard that was already free. Why do people think they need to be compensated for something they put up online for free? They don't have the right to not allow people to learn from it, that's just never been a part of copyright.

They put it online for free for human consumption. Because the tech is very new, old concepts and laws don't cover it and that's not the point. The assumption that there must be compensation comes from the capitalist society that we live in. Switching to Communism or something else can be a solution to not directly pay people who do works and still have them around.

Capitalism isn't when you pay for things, it's when there's capital you can sell.

Re: Stable Attribution

#109

Post by pjgalbraith »

simonw wrote: post #51

Upload a photo you took to prove to yourself that this tool is misleading (if not straight up fraudulent), then downvote and move on. You can already run exactly this kind of image similarity search against the Stable Diffusion training set using existing tools - https://rom1504.github.io/clip-retrieval/?back=https%3A%2F%2... for example

It's actually just the exact same tool rebranded with a fancy landing page. The worst part is this "attribution tool" didn't even give attribution to the original author https://twitter.com/rom1504/status/1622381709424558081?s=20&...

Re: Stable Attribution

#110

Post by semicolon_storm »

esperent wrote: post #83
goldemerald wrote: post #8

This 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 guarante…

Until somebody comes out with a better way to trace back output images to training data, this is the best "data" we have so far.

Before this, there were anecdotal examples of SD outputting an image with some Shutterstock watermark or very similar to some artist's work, but the prompts also seemed highly specific or were asking for something in that artist's style.

This tool at least lets us start to trace back the average image, and so far it does seem SD is adding something novel to its outputs.

Post reply on HN