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

231–240 of 519 posts

Re: Stable Diffusion 2.0

#231

Post by M4v3R »

LASR wrote: post #120
searchableguy wrote: post #30

Earlier quoted context omitted.

What are you building?

It started as an AI-powered MS paint for my son. But after demoing it to a few coworkers, it morphed into a bit more than that. Now it’s more of a storybook creator that young kids can use to generate their own stories. Not looking to monetize at all. But inference is expensive. So might have something to cover costs. Some backstory: When I was growing up in the early 90s, my dad took me into his office over the week…

As a father of a 1.5 year old girl this sounds incredibly awesome and I'm hoping you will release it somehow, looking forward to your Show HN post!

Re: Stable Diffusion 2.0

#232

Post by CapsAdmin »

Sugimot0 wrote: post #97

Amy word on AMD support?

The previous version works fine and has performance on par with NVIDIA. I'm on Linux using the ROCm platform.

There are some specialized third party performance optimizations you might miss out on though, but nothing major IMO.

Re: Stable Diffusion 2.0

#233

Post by kennyloginz »

Operyl wrote: post #8
minimaxir wrote: post #2

GitHub Repo: https://github.com/Stability-AI/stablediffusion HuggingFace Space (currently overloaded unsurprisingly): https://huggingface.co/spaces/stabilityai/stable-diffusion Doing a 2.0 release on a (US) 2-day holiday weekend is an interesting move. It seems a tad more difficult to set up the model than the previous version.

Seems like a potentially good time to launch it, lots of young people with free time.

Definitely something to talk about or share with the fam.

Re: Stable Diffusion 2.0

#234

Post by just-ok »

Hamuko wrote: post #224
fastball wrote: post #76

Earlier quoted context omitted.

Is artificially generated CSAM that doesn't actually involve children in its production not an improvement over the status quo?

"Artificially-generated CSAM" is a misnomer, since it involves no actual sexual abuse. It's "simulated child pornography", a category that would include for example paintings.

Not exactly, since the abuse needed to actually happen for the derivative images to be possible to generate.

Re: Stable Diffusion 2.0

#235

Post by acadapter »

TaylorAlexander wrote: post #154
kmeisthax wrote: post #58

Is there a good explanation of how to train this from scratch with a custom dataset[0]? I've been looking around the documentation on Huggingface, but all I could find was either how to train unconditional U-Nets[1], or how to use the pretrained Stable Diffusion model to process image prompts (which I already know how to do). Writing a training loop for CLIP manually wound up with me banging against all sorts of stra…

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 without the modern copyright system.

It would be interesting to see if this technology can erode the copyright concept a bit. Maybe not remove it completely, but perhaps influence people to create wider definitions for "fair use", and undo the extensions that Disney lobbyists have created.

Re: Stable Diffusion 2.0

#236

Post by otabdeveloper4 »

ftufek wrote: post #81
kmeisthax wrote: post #74

Earlier quoted context omitted.

I have... ~11TBs of free disk space and a 1080ti. Obviously nowhere close to being able to crunch all of Wikimedia Commons, but I'm also not trying to beat Stability AI at their own game. I just want to move the arguments people have about art generators beyond "this is unethical copyright laundering" and "the model is taking reference just like a real human".

To put things in perspective, the dataset it's trained on is ~240TB and Stability has over ~4000 Nvidia A100 (which is much faster than a 1080ti). Without those ingredients, you're highly unlikely to get a model that's worth using (it'll produce mostly useless outputs). That argument also makes little sense when you consider that the model is a couple gigabytes itself, it can't memorize 240TB of data, so it "learned"…

> when you consider that the model is a couple gigabytes itself, it can't memorize 240TB of data, so it "learned".

This is just lossy compression with a large and well-tuned (to the expected problem domain) dictionary.

Video compression codecs can achieve a 500x compression ratio, and they are general-purpose.

Re: Stable Diffusion 2.0

#237

Post by Hamuko »

just-ok wrote: post #234
Hamuko wrote: post #224

Earlier quoted context omitted.

"Artificially-generated CSAM" is a misnomer, since it involves no actual sexual abuse. It's "simulated child pornography", a category that would include for example paintings.

Not exactly, since the abuse needed to actually happen for the derivative images to be possible to generate.

Is Stable Diffusion only able to generate images of things that have actually happened?

Re: Stable Diffusion 2.0

#238

Post by tick_tock_tick »

datalopers wrote: post #82
braingenious wrote: post #72

Earlier quoted context omitted.

LMFAO What do you propose? The FBI releases a CSAM data set for devs to use for “training”? Would you be the one to create the model? Would you run a business that sells synthetic CSAM?

Without the changes they made to Stable Diffusion, it was already able to generate CP. That's why they restricted it from doing so. It did not have child pornography in the training set, but it did have plenty of normal adult nudity, adult pornography, and plenty of fully clothed children, and was able to extrapolate. Anyway, one obvious application: FBI could run a darknet honeypot site selling AI-generated child po…

> FBI could run a darknet honeypot site selling AI-generated child porn. Eliminate the actual problem without endangering children.

It's very unlikely AI generated child porn would even be illegal. Drawn or photoshopped photos aren't so I don't think AI generated would be.

Re: Stable Diffusion 2.0

#239

Post by bambataa »

PartiallyTyped wrote: post #184
sroussey wrote: post #118

Earlier quoted context omitted.

Well, Microsoft and others have this model for recognizing CSAM, trained on those CSAM images.

Apple, and meta have as well. Apparently Facebook has a huge problem with distribution through messenger.

Once I read an article about a guy who got arrested because he’d put child porn on his Dropbox. I had assumed he’d been caught by some more sophisticated means and that was just the public story. I’m amazed that anyone would be stupid enough to distribute CSAM through an account linked to their own name.

Re: Stable Diffusion 2.0

#240

Post by M4v3R »

osener wrote: post #176
prawn wrote: post #149

Earlier quoted context omitted.

Ah - had forgotten. I'll try them first. Thanks.

So does Pixelmator. You can try the free trial which comes with this feature.

Pixelmator's Super ML Resolution does a great job with upscaling images, can highly recommend it.
Post reply on HN