Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models · HackerPapers discussions

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — mentioned by luqtas

Wed, 03 Jul 2024 01:20:45 GMT

what are the opinions on [0]? what's the scene for language rather than image? also what are the opinions on turning generative AI (that doesn't ask permission to creators) public domain? donation money that surpasses the cost of hosting the work to people/groups "creating" with AI, should be a violation of the license? are you allowed to play with the models in hardware made by for-profit entities, like Nvidia? [0] https://arxiv.org/abs/2212.03860

Paper and discussion history. A mention is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — mentioned by pksebben

Wed, 08 Feb 2023 02:34:35 GMT

is this (1) the lawsuit you're referring to? 'cause those images are not the same. Sports events are just easy to fake, because they're boring - all sports pictures look roughly the same. Edited to add: There's another lawsuit (a class action - 2), and after a little light reading, I came across section 5: 'Do diffusion models copy?', and my stomach jumped. What they're doing, to make a point at trial that stable diffusion copies images, is _training images into the model, then using that trained model to prove that stable diffusion is a compression algorithm_. This is a patent fabrication.…

Paper and discussion history. A mention is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — mentioned by space_fountain

Mon, 06 Feb 2023 17:57:37 GMT

I do want to clarify that I think stable diffusion and tools like it can engage in illegal copying. For example it will happily produce infringing images of logos and even somewhat random other images https://arxiv.org/pdf/2212.03860.pdf. It seems like it’s devoting an uneven amount of its weights to different images, but I remain unconvinced that’s all it can do, or at least anymore all it can do than for a human artist

Paper and discussion history. A mention is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — mentioned by rvz

Wed, 01 Feb 2023 13:14:23 GMT

Also another previous study that has Stable Diffusion (SD) emitting images in the training set [0] It is now clear that SD is treading on thin ice: training on watermarked and copyrighted images without their author's permission, then attempting to commercialize it even when the model emits images that resemble a high similarity of the original training data including watermarks or copyrighted images: (Mickey Mouse, Getty Images watermarks, Bloodborne art cover, etc). This weakens their fair use argument, especially with Getty Images also threatening to sue SD for the same reason. If OpenAI…

Paper and discussion history. A mention is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — mentioned by N1ckFG

Thu, 26 Jan 2023 19:01:02 GMT

Afaik theoretically you could reproduce any image in the training set using the full weights (not a fraction of them) and the correct prompt. In practice since this is an extremely lossy process, some or most of them aren't reproducible. For this specific case, I suspect it'll come down to whether somebody in the class can pass a test like this: https://arxiv.org/abs/2212.03860

Paper and discussion history. A mention is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — mentioned by ninjin

Sun, 22 Jan 2023 06:54:10 GMT

Honestly, can people stop speaking in absolutes regarding these systems? We (researchers and non-researchers alike) are gradually trying to comprehend exactly how much they generalise and memorise, but this is darn hard work and it is not our fault that several major tech giants decided to deploy and profit from these models long before the scientific and legal landscape was clear. Somepalli et al. (2022) [1] for example is a fairly strong argument against your statement above. [1]: https://arxiv.org/abs/2212.03860 The fact is that these systems are complex, new, and interesting. However, it…

Paper and discussion history. A mention is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — mentioned by karpierz

Sun, 15 Jan 2023 21:06:22 GMT

> Could you provide evidence of your last statement? I haven’t seen these models produce actual copies of any art (can’t imagine that’s an option in general). Here's a whole paper, complete with citations: https://arxiv.org/pdf/2212.03860.pdf > These models do not contain copies. One way to describe the data is they contain a statistical breakdown of the artwork, which is substantially different from a JPEG -> PNG conversion you mention. I don't understand the distinction you're making. What legally separates a "statistical breakdown" representation from a zip file representation, JPEG…

Paper and discussion history. A mention is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — mentioned by zowie_vd

Sat, 14 Jan 2023 17:43:03 GMT

> when doing paintovers on copyrighted images (VERY common) What are you talking about? I've been doing drawing and digital painting as a hobby for a long time and tracing is absolutely not "VERY common". I don't know anybody who has ever done this. > fan art where they paint trademarked characters (also VERY common) This is true in the sense that many artists do it (besides confusing trademark law and copyright law: the character designs are copyright-protected, trademarks protect brand names and logos). However, it is not fair use (as far as I'm aware at least, I'm not a lawyer). A…

Paper and discussion history. A mention is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — mentioned by realusername

Sat, 14 Jan 2023 08:55:14 GMT

> The actual issue is that Stable Diffusion does create derivatives of copyrighted works. Nothing points to that, in fact even in this website they had to lie on how stablediffusion actually works, maybe a sign that their argument isn't really solid enough. > [1] https://arxiv.org/pdf/2212.03860.pdf You realize those are considered defects of the model right? Sure, this model isn't perfect and will be improved.

Paper and discussion history. A mention is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — mentioned by IncRnd

Sat, 14 Jan 2023 08:51:13 GMT

There is no need for rhetorical games. The actual issue is that Stable Diffusion does create derivatives of copyrighted works. In some cases the produced images contain pixel level details from the originals. [1] [1] https://arxiv.org/pdf/2212.03860.pdf

Paper and discussion history. A mention is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — mentioned by space_fountain

Thu, 29 Dec 2022 05:50:18 GMT

From fact checking myself it is worth noting that stable diffusion will absolutely copy things in ways that would probably infringe a copyright (not a layer and not legal advice), but I found this paper interesting both because some of the examples it gives of clear copying don't look all that copied to me, and because some do and they find overall a relatively high rate of copying. 1.8% https://arxiv.org/abs/2212.03860. I believe this is still not peer reviewed.

Paper and discussion history. A mention is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — HN submission

Tue, 20 Dec 2022 20:54:20 GMT

Diffusion Art or Digital Forgery? Data Replication in Diffusion Models

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — HN submission

Tue, 13 Dec 2022 06:53:07 GMT

Investigating Data Replication in Diffusion Models

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models — HN submission

Fri, 09 Dec 2022 20:20:12 GMT

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.