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

Stable Diffusion 2.0

stability.ai

Post reply on HN
Print view View original

471–480 of 519 posts

Re: Stable Diffusion 2.0

#471

Post by tweetle_beetle »

Applejinx wrote: post #364
acadapter wrote: post #235

Earlier quoted context omitted.

Human artists derive their inspiration and styles from a large set of copyrighted works, but they are free to produce new art despite of that. Art would have developed much slower and be much poorer if, for example, Impressionism or Cubism had been entangled in long ownership confrontations in courts. Then there's the fact that humanity has been able to develop and share art and literary works for thousands of years…

That is a very apropos reference. If you're familiar with Cubism, you know that there's Picasso, and then there's Braque. The one is an art celebrity beyond almost any other, and the other isn't. But they developed Cubism in parallel. There were periods where their work was almost indistinguishable. "Houses at l'Estaque", the trope namer for Cubism thanks to the remarks of a critic, was in fact by Braque. You can gen…

> You can generate infinite recognizable Basquiat from an AI, but is it Basquiat? No, of course not, because Basquiat's style operates within the context of a specific individual human making a point about expectations and the interface between his race and his artistic boldness and audacity as experienced by his wealthy audience.

I'm not sure how I feel about this - I agree with the conclusion, but not the reasoning. For me, AI-generated Basquiat is not Basquiat simply because he had no ownership or agency in the process of its creation.

It feels like an overly romantic notion that art requires specific historical/cultural context at the moment of its creation to be valid.

If I could hypothetically pay Basquiat $100 to put his own work into a stable diffusion model that created a Basquiat-esque work, that's still a Basquiat. If I could pay him to draw a circle with a pencil, that's his work - and if I used it in an AI model, then it's not.

It's about who held the paintbrush, or who delegated holding the paintbrush, not a retrospectively applied critical theory.

Re: Stable Diffusion 2.0

#472

Post by feelandcoffee »

moron4hire wrote: post #116
joshspankit wrote: post #68

Earlier quoted context omitted.

Porn has driven many tech advances. I predict that models trained on specific porn genres will appear as soon as training a good model is doable for under $5000. They’ll get here much quicker if we get video to that mark first.

> Porn has driven many tech advances. This is an urban myth.

Yes and now. Yeah the VHS VS Beta situation was exaggerated, but you'll be surprised on how much on Netflix, and youtube UI tricks were stolen from innovation made in adult sites.

I'll even say that the high bandwidth push in the public was highly related to that. Even HTML5 video players, adult websites were faster to implement it than big streaming websites that still used flash or similar tech.

Re: Stable Diffusion 2.0

#473

Post by astrange »

kmeisthax wrote: post #413
juliendorra wrote: post #375

Earlier quoted context omitted.

My bet is that big corporations won’t risk suing anyone over a supposed copyright on generated images,as there is a good chance that a court ends up stating that all AI generated images are in fact public domain (no author, not from the original intent and idea of a human) You can already see the quite strange and toned down language they use on their sites. (And for some the revealing reversal from we licence to you…

So, the US Copyright Office will already refuse to issue a copyright for text-prompt-generated AI art, at least if you try a stunt like naming the artist to be the AI program itself. However, even if an image is not copyrightable, it can still infringe copyright. For example, mechanical reproductions of images are not copyrightable in the US[0] - which is why you even can have public domain imagery on the web. Howeve…

> So, the US Copyright Office will already refuse to issue a copyright for text-prompt-generated AI art, at least if you try a stunt like naming the artist to be the AI program itself.

That’s because only humans can own copyrights. People can and have registered copyrights for Midjourney outputs.

Re: Stable Diffusion 2.0

#474

Post by astrange »

andrepd wrote: post #355
kikokikokiko wrote: post #313

Earlier quoted context omitted.

It's almost like "capitalism" isn't something that needs to be created and forced upon people, it's just the way a world where energy isn't free and can not be created from thin air works. Capitalism is just that, the realization that there's no free lunches and no UBIs are possible without some serious unintended consequences. I pirate everything I consume, but I would never be such an hypocrite to say that all copy…

That's one of the great victories of capitalism: somehow it has convinced people that a 300 year-old economic system originating in north-western Europe is as natural as the air we breathe, and as inevitable as gravity or any natural law.

Paying people to make art is older than “capitalism”. Capitalism is when you can own and trade capital, not when you pay people to do things.

Re: Stable Diffusion 2.0

#475

Post by astrange »

Xelynega wrote: post #412
bonoboTP wrote: post #324

Earlier quoted context omitted.

If you can't process/digest copyrighted content with algorithms/machine learning then Google Search (the whole thing, not just Image Search) is dead. So no, it's not at all clear where the legal lines are drawn. There have been no court cases yet, regarding the training of ML models. People are trying to draw analogies from other types of cases, but this has not been tried in court yet. And then the answer will likel…

> If you can't process/digest copyrighted content with algorithms/machine learning then Google Search (the whole thing, not just Image Search) is dead. Not if Google honors the robots.txt like they say they do. Hosting content with a robots.txt saying "index me please" is essentially an implicit contract with Google for full access to your content in return for showing up in their search results. Hosting an image/cod…

LAION/StableDiffusion is already legal under the same exemptions as Google Image Search and does respect robots.txt. It was also created in Germany so US court cases wouldn’t apply to it.

Re: Stable Diffusion 2.0

#476

Post by astrange »

kmeisthax wrote: post #419
TeMPOraL wrote: post #258

Earlier quoted context omitted.

> Specifically, Wikimedia Commons images in the PD-Art-100 category, because the images will be public domain in the US and the labels CC-BY-SA. Doesn't the "BY" part of the license mean you have to provide attribution along with your models' output[0]? I feel you'll have the equivalent of Github Copilot problem: it might be prohibitive to correctly attribute each output, and listing the entire dataset in attribution…

If I was generating image labels I absolutely would need to worry about that. However, since we're only generating images alone, we don't need to worry about bits of the labels getting into the output images. The attribution requirement would absolutely apply to the model weights themselves, and if I ever get this thing to train at all I plan to have a script that extracts attribution data from the Wikimedia Commons…

> This is cumbersome, but possible.

This is not possible because the model is smaller than the input weights. Just as any new image it generates is something it made up, any attributions it generated would also be made up.

CLIP can provide “similarity” scores but those are based on an arbitrary definition of “similarity”. Diffusion models don’t make collages.

Re: Stable Diffusion 2.0

#477

Post by astrange »

in3d wrote: post #363

In addition to removing NSFW images from the training set, this 2.0 release apparently also removed commercial artist styles and celebrities [1]. While it should be possible to fine tune this model to create them anyway using DreamBooth or a similar approach, they clearly went for the safe route after taking some heat. 1. https://twitter.com/emostaque/status/1595731407095140352?s=4...

This is extremely misleading and you seem to have confused all the other replies.

StableDiffusion 1.0 used CLIP released by OpenAI. 2.0 uses a CLIP retrained from scratch by Stability.

We don’t know OpenAI’s dataset so don’t know what was in it or how to recreate it. Nothing was “removed”.

Re: Stable Diffusion 2.0

#478

Post by astrange »

siraben wrote: post #410
arez wrote: post #369

Earlier quoted context omitted.

does this mean that stuff like artstation and deviantart doesn't work anymore as prompts? That would be a huge change

Ran the model locally. Neither "trending on artstation" nor "Greg Rutowski" make any differences to the image anymore.[0] I suspect that people will find keywords that would improve the aesthetics further again, or that fine-tuning will also take place. [0] https://imgsli.com/MTM1ODQ5

“Prompting” and “keywords” are not an essential part of this technology. If you like tokens, make your own tokens with textual-inversion or image inputs.

Re: Stable Diffusion 2.0

#479

Post by astrange »

stavros wrote: post #322

It kind of annoys me that they removed NSFW images from the training set. Not because I want to generate porn (though some people do), but because I feel that they're foisting a puritan ethic on me. I don't consider the naked body inherently bad, and I don't like seeing new technology carry this (wrong, in my opinion) stigma. Then again, it's their model, they can do whatever they want with it, but it still leaves me…

It’s annoying when you get NSFW results when you didn’t ask for them, so it may be better to segregate them.
Post reply on HN