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

351–360 of 519 posts

Re: Stable Diffusion 2.0

#351

Post by ksrm »

acadapter wrote: post #235
TaylorAlexander wrote: post #154

Earlier quoted context omitted.

Ah I am glad to see someone else talking about using public domain images! Honestly it baffles me that in all this discussion, I rarely see people discussing how to do this with appropriately licensed images. There are some pretty large datasets out there of public images, and doing so might even help encourage more people to contribute to open datasets. Also if the big ML companies HAD to use open images, they would…

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…

AI tools aren't people. We don't have to treat them the same.

Re: Stable Diffusion 2.0

#352

Post by FeepingCreature »

otabdeveloper4 wrote: post #350
FeepingCreature wrote: post #251

Earlier quoted context omitted.

The dataset, LAION-5B, is 240TB of already compressed data. (5 billion pairs of text to 512x512 image.) Uncompressed, LAION-5B would be 4PB, for a compression ratio into SD of ~780kx, or one byte per picture.

The point is that there's is no practical limit on compression. You don't need "AI" or anything besides very basic statistics to get astronomical compression ratios. (See: "zip bomb".) The only practical limit is the amount of information entropy in the source material, and if you're going to claim that internet pictures are particularly information-dense I'd need some evidence, because I don't believe you.

Correct, however "compression is equivalent to general intelligence" (http://prize.hutter1.net/hfaq.htm#compai ) and so in a sense, all learning is compression. In this case, SD applies a level of compression that is so high that the only way it can sustain information from its inputs is by capturing their underlying structure. This is a fundamentally deeper level of understanding than image codecs, which merely capture short-range visual features.

Re: Stable Diffusion 2.0

#353

Post by theCrowing »

klqwart wrote: post #348
thot_experiment wrote: post #285

Earlier quoted context omitted.

The problem is not that people aren't owning ideas hard enough, ideas shouldn't be ownable in this way, the problem is that we've created a system that's obsessed with scarcity and collecting rents. Being able to own and trade ideas a la copyright/patents helps people who can buy copyrights and patents stifle creativity more than it helps artists gather reward for their creation (though it does both). Human endeavor…

Perhaps no one wants "your art"? 99% of artists who produce something worthwhile very much care about money/copyright. The there still is the question of attribution, which 100% of real artists care about.

99%? You might have it in reverse because most art is not produced by "fulltime" artists. I would even go as far and say 99% of art is not produced to earn money.

Re: Stable Diffusion 2.0

#354

Post by swores »

ajuc wrote: post #325
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…

> It would be interesting to see if this technology can erode the copyright concept a bit Copyright law (especially in US) only ever changes in the direction that suits corporations. So - no. What I expect instead is artists being sued by a big tech company for copyright violations because that big tech company used the artist Public Domain image for training their copyrighted AI and as a result it created a copyrigh…

> Copyright law (especially in US) only ever changes in the direction that suits corporations. So - no.

There's certainly arguments to be made in this direction, for example corporations tending to have the most money they can afford to spend on lobbying to get their way, but the attitude of "it hasn't been good up 'til now so it definitely can't ever be good" is pretty defeatist and would imply that positive change is impossible in any area.

Re: Stable Diffusion 2.0

#355

Post by andrepd »

kikokikokiko wrote: post #313
hdjjhhvvhga wrote: post #296

Earlier quoted context omitted.

When I was younger, I also thought that way. I also felt that being artist has nothing to with money: a true artist will always create out of their internal need, not for money. Then came the brutal reality: creating high-quality artwork needs time. Some can be created after work, but not that much. Some forms of art require expensive instruments. Some, like filmmaking, require collaboration and coordination of many…

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.

Re: Stable Diffusion 2.0

#356

Post by charcircuit »

jeroenhd wrote: post #270
charcircuit wrote: post #87

I dislike how they call their model open source even though there are restrictions on how you can use the model. The ability to use code however you want and not have to worry about if all the code you are using is compatible with your use case is a key part of open source.

The code is open source, the model is a data file that the open source code operates on. It's similar to engine recreations for old games (OpenRCT, OpenTTD) that use original, proprietary assets to play the games with their open source engines. Similar to those games, anyone is also able to distribute their own open data files if they so wish It's unlikely anyone actually will start training an open source AI model f…

I don't know what your point is. They use the terms "open source AI models" and "open source Generative AI models"

Yes, someone else could spend the millions of dollars to create a model that actually is open source, but shouldn't the people advertising their models as open source do that?

Re: Stable Diffusion 2.0

#357

Post by less_less »

kikokikokiko wrote: post #313
hdjjhhvvhga wrote: post #296

Earlier quoted context omitted.

When I was younger, I also thought that way. I also felt that being artist has nothing to with money: a true artist will always create out of their internal need, not for money. Then came the brutal reality: creating high-quality artwork needs time. Some can be created after work, but not that much. Some forms of art require expensive instruments. Some, like filmmaking, require collaboration and coordination of many…

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…

What? No. Capitalism is a more specific system for organizing goods and services, wherein the means of production and distribution of those goods and services (buildings, land, machines and other tools, vehicles etc) are privately owned and operated by workers (who are paid a wage) for the profit of the owners. That's only been the norm for a few hundred years, and only in certain places. Also, capitalism is separate from copyright and other IP, though IP as currently implemented is pretty obviously a capitalist concept.

Re: Stable Diffusion 2.0

#358

Post by naillo »

millimeterman wrote: post #161
liuliu wrote: post #41

Seems the structure of UNet hasn't changed other than the text encoder input (768 to 1024). The biggest change is on the text encoder, switched from ViT-L14 to ViT-H14 and fine-tuned based on https://arxiv.org/pdf/2109.01903.pdf . Seems the 768-v model, if used properly, can substantially speed-up the generation, but not exactly sure yet. Seems straightforward to switch to 512-base model for my app next week.

I'm disappointed they didn't push parameter count higher, but I suppose they want to maintain the ability to run on older/lower end consumer GPUs. Unfortunately it severely limits how high-quality the output can be.

They're motivating that choice via this paper: https://arxiv.org/pdf/2203.15556.pdf The paper shows that you can get better performance than gpt-3 with a much smaller model if you bump up the training time and training data like x4.

Re: Stable Diffusion 2.0

#359

Post by concordDance »

braingenious wrote: post #300
concordDance wrote: post #262

Earlier quoted context omitted.

Yes to the first and no to the second seem the obvious answers here.

Quoted post unavailable.

So your hypothesis is that if the FBI gives the database to a company it will inevitably leak to the pedophile underworld?

I can't judge how likely that is.

I guess I also don't care much as I only really care aboit stopping production using real children, simulated CSAM gets a shrug and even use of old CSAM only gets a frown.

Re: Stable Diffusion 2.0

#360

Post by tormeh »

I can't see any progress on AMD/Intel GPU support :( Would love to see Vulkan or at least ROCm support. With SD1 you could follow some guides online to make it work, since PyTorch itself supports ROCm, but the state of non-Nvidia GPU support in the DL space is quite sad.
Post reply on HN