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

401–410 of 519 posts

Re: Stable Diffusion 2.0

#401

Post by SkyPuncher »

FPGAhacker wrote: post #219
SkyPuncher wrote: post #49

Earlier quoted context omitted.

Lol. Especially the AI version of keyboard auto suggest. Let's take a deterministic algorithm that predictably corrects your typos and build it on AI. It will offer you no benefits, but it will completely destroy the utility since it will never work predictably or accurately.

Auto correct and auto suggest are related but different things. Suggest puts up options for the next word.

My comment would remain exactly the same for auto-correct. They are essentially the same thing, just pre and post typing.

They both serve the same purpose of helping the user quickly and accurately communicate on a cell phone. Like auto-suggest, I rely on auto-correct to fix things that I know I commonly mistype. When it doesn't work predictably, it's useless.

Re: Stable Diffusion 2.0

#402

Post by jmiskovic »

machina_ex_deus wrote: post #399
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...

I predicted back when they started backpedaling that there's a chance that sd1.4 or 1.5 will be the best available model to the general public, for a very long duration, because the backlash will force them to self-castrate themselves. You can see nobody likes this new model in any of the stable diffusion communities. It's a big flop and for a good reason. The reason it was so successful in the first place was becaus…

That's like saying that obtaining the On the Origin of Species or Linux kernel will be harder in future. If anything the SD weights will be increasingly ubiquitous as they start embedding it into consumer electronics.

Re: Stable Diffusion 2.0

#403

Post by blitzar »

dismantlethesun wrote: post #397
akie wrote: post #394

Earlier quoted context omitted.

It's remarkable, this sense of entitlement people have. You literally have a computer program here that can make photorealistic imagery of almost ANYTHING you ask it to, which was impossible even half a year ago, and here you are complaining that people won't use it unless it incorporates all of the protected imagery of famous artists and celebrities. Amazing.

Is it entitled to think that a 2.0 will not have regressions on useful functionality?

yes

Re: Stable Diffusion 2.0

#404

Post by Xelynega »

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…

Doesn't your argument in the first paragraph assume that the methods by which humans derive new works from past experiences is equivalent to the way statistical models iteratively remove noise from images based on a set of abstract features derived from an input prompt?

That seems to be the core of the issue, and a much more interesting conversation to have. So why do I keep seeing a version of your first paragraph everywhere and not an explanation on why the assumption can be made?

Re: Stable Diffusion 2.0

#405

Post by rattray »

akie wrote: post #394
CuriouslyC wrote: post #387

Earlier quoted context omitted.

Removing NSFW content is fine, people who care about that can work around it easily. Removing celebrities and commercial artists was a mistake though and I expect this will need to be really impressive in other ways or people aren't going to bother using it.

It's remarkable, this sense of entitlement people have. You literally have a computer program here that can make photorealistic imagery of almost ANYTHING you ask it to, which was impossible even half a year ago, and here you are complaining that people won't use it unless it incorporates all of the protected imagery of famous artists and celebrities. Amazing.

Loss aversion is strong in humans.

Re: Stable Diffusion 2.0

#406

Post by 4RealFreedom »

bowsamic wrote: post #228
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…

No one is ever going to stop using all the available images until there is a law against it. Why would they?

I've seen many arguments about getting laws on the books around ML learning. I would suggest people create a project that creates movies using ML and train it using existing Hollywood movies. I realize this isn't easy but the issue needs to be pushed to people that have the means to force change.

Re: Stable Diffusion 2.0

#407

Post by acidburnNSA »

Tepix wrote: post #288
acidburnNSA wrote: post #156

Awesome. I'm installing on Ubuntu 22.04 right now. Ran into a few errors with the default instructions related to CUDA version mismatches with my nvidia driver. Now I'm trying without conda at all. Made a venv. I upgraded to the latest that Ubuntu provides and then downloaded and installed the appropriate CUDA from [1]. That got me farther. Then ran into the fact that the xformers binaries I had in my earlier attempt…

Which GPU are you using? Used RTX 3090s were relatively cheap in the last couple of weeks...

GeForce GTX 1060 6GB, purchased literally 5 years ago. It worked with an optimized stable diffusion 1.0 so I was hopeful here. If I want to run these models going forward I guess I need something slightly more serious, eh?

Re: Stable Diffusion 2.0

#408

Post by Aachen »

kanonieer wrote: post #263
beanjuice wrote: post #259

Earlier quoted context omitted.

To be clear to the original poster, the naming is terrible because of the nazi associations of the number 88, correct?

Indeed.

From the Netherlands, never heard of it. Living in germany four years now, now that you remind me, I had to dig deep in my memory (at first I thought it might mean SS somehow), but yeah someone once mentioned it's the 8th character of the alphabet and so if you associate HH with the 2nd world war, you can read something into it. Most definitely not among the first associations for me, and believe me we had enough WW2 material in school (including kids that use hitler stuff to be funny). Perhaps 88 is specifically edgy in german high schools or so? I bet if you look at other cultures, it'll mean donkey balls or some such somewhere. I've also heard a german laugh about a 1312 license plate which I'd never think to associate with alphabet offsets in my life. Would be "ieiz" or "lelz" for me, if anything.

TL;DR very far fetched and a bit pointless to go looking for these non-obvious alternative meanings, in my opinion

Re: Stable Diffusion 2.0

#409

Post by Xelynega »

arbol wrote: post #312
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…

The restrictions on creating art are the product of the society you live in, which means they are the product of capitalism if you live in a capitalist society. The way society is organised determines the cost of people's time, the cost of the tools, and the cost of the materials.

Yea I find when people say "ideas shouldn't be ownable" it's really the more general "deriving profit from private ownership was a mistake". Like you kinda point out, most of the reason I can think of that a person would want control of their intellectual property is to derive profit from it.

That reason has nothing to do with intellectual property or how it's created, it's a consequence of living in a capitalist society.

Re: Stable Diffusion 2.0

#410

Post by siraben »

arez wrote: post #369
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...

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

Post reply on HN