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

Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM

github.com

Post reply on HN
Print view View original

141–150 of 151 posts

Re: Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM

#141

Post by bawolff »

mobiclick wrote: post #121
bawolff wrote: post #93

Earlier quoted context omitted.

Refusing to acknowledge the affect of hurtful words on yourself, is pretty much the opposite of "proper habits of the mind". Denial does not make healthy people.

It's not denial so much as it is not caring to the point where you get upset. I think that's the strength of mind that GP is referring to.

I would suggest that anyone who cares so little that there is literally nobody who can say anything that hurts them is basically dead inside.

Part of living is opening yourself up to people. That includes the risk of getting hurt. That's normal and part of the human experience.

Re: Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM

#142

Post by bawolff »

wholinator2 wrote: post #129
mobiclick wrote: post #121

Earlier quoted context omitted.

It's not denial so much as it is not caring to the point where you get upset. I think that's the strength of mind that GP is referring to.

I agree. Just because we have more advanced diagnosis and detection tools these days doesn't mean everything has to be a problem. The internet has really shaken up social norms and signaling and the kids are the first ones to enter the new world. I believe once we have a generation of fully formed 30-50 year olds who grew up with this strange social media, then we'll have the proper understandings and social knowledg…

Im not saying you should broadcast your woes to the world for fake internet points. Just that people should be ok with having a bad day sometimes and that people who think they are too "strong" to ever be sad, usually are the most screwed up mentally.

Re: Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM

#143

Post by NHQ »

cercatrova wrote: post #23
NHQ wrote: post #18

Earlier quoted context omitted.

But what is the correct git command to ignore all that?

There's no git command to ignore it, the main repo should merge their changes and then the other person can make a PR on the updated changes.

Where are PRs in Git?

Re: Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM

#144

Post by Arainach »

Vetch wrote: post #114
Arainach wrote: post #106

Earlier quoted context omitted.

Don't let perfection be the enemy of good. Anyone with a basic machine shop can modify an AR15 for fully automatic fire, and a bump stock can be fabricated even easier. That doesn't mean we should just give up and make these things legal and easily accessible to everyone.

An automatic rifle has almost no positive use to it. This software is not like that and more like something that makes everyone better at a skill, uniformly raising the artistic talent floor. The large majority benefit but some would use their new earned skill for bad. It would be like denying literacy and the printing press because there will always be some people who use it to write very bad distressing things, man…

They're not refusing to distribute the software, they're restricting it for NSFW uses, of which the danger is more significant than any positive uses - much like automatic fire.

Re: Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM

#145

Post by hda2 »

Arainach wrote: post #144
Vetch wrote: post #114

Earlier quoted context omitted.

An automatic rifle has almost no positive use to it. This software is not like that and more like something that makes everyone better at a skill, uniformly raising the artistic talent floor. The large majority benefit but some would use their new earned skill for bad. It would be like denying literacy and the printing press because there will always be some people who use it to write very bad distressing things, man…

They're not refusing to distribute the software, they're restricting it for NSFW uses, of which the danger is more significant than any positive uses - much like automatic fire.

"restricting it for NSFW", according to whose standard? "which the danger", like what?

I'm glad this technology is finally out in the open where people like you no longer have a say in how it is used. The sooner people accept its existence (like they have with Photoshop), the better off and healthier we'll be as a society.

Re: Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM

#146

Post by hda2 »

ziddoap wrote: post #48
hda2 wrote: post #36

Earlier quoted context omitted.

> What's creepy is the very real world that we're approaching where anyone can create porn of anyone else given a few pictures without their consent. Why is that a problem, exactly? > That can cause all sorts of lasting psychological harm and other societal negative consequences. Like what? To me this sounds like a problem with how some people want to have absolute control over what others do and want everyone else t…

> Why is that a problem, exactly? Do you really need someone to spell out to you why being able to create realistic-looking porn of anyone might lead to some issues...? > Someone wants to generate porn of me fucking a donkey? Let them. They already could do that with ms-paint and I don't get magically harmed if they do. What an absolutely wild take. Do you expect this line of thinking to be convincing when you're com…

> Do you really need someone to spell out to you why being able to create realistic-looking porn of anyone might lead to some issues...?

Yes. I honestly have no

> What an absolutely wild take. Do you expect this line of thinking to be convincing when you're comparing AI-generated images to what someone can whip together in MS Paint? Come on. You, me, and everyone else reading here knows that's not even close to a valid comparison.

Wild or not, my point stands. With minimal skills, you can photoshop anyone's face on any pornographic image out there. It's a spot on comparison.

Re: Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM

#147

Post by hda2 »

bawolff wrote: post #141
mobiclick wrote: post #121

Earlier quoted context omitted.

It's not denial so much as it is not caring to the point where you get upset. I think that's the strength of mind that GP is referring to.

I would suggest that anyone who cares so little that there is literally nobody who can say anything that hurts them is basically dead inside. Part of living is opening yourself up to people. That includes the risk of getting hurt. That's normal and part of the human experience.

I don't think anyone in this thread is denying this.

Re: Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM

#148

Post by nl »

JimDabell wrote: post #123
nl wrote: post #120

Earlier quoted context omitted.

That's really annoying, even though I hadn't noticed it until now. I can confirm this is an issue. But the situation seems to be the same on the CompVis derived repos, right? So this is no worse off, but with better engineered and faster code.

Yeah, but with the CompVis derived repos, it’s pretty easy to go in and change all the calls to PyTorch random number generators. Having said that, the last comment [0] on the PyTorch issue gave me the idea of monkey patching the random functions. The supplied code assumes you’re always passing in a generator, which is not true in this case, but if you monkey patch the three rand/randn/randn_like functions to do noth…

This branch seems to fix these issues: https://github.com/huggingface/diffusers/tree/mps

(Annoyingly I just went and made similar changes and was about to create a PR for them. But they have a fix for a "warm-up" issue I wasn't aware of too)

Re: Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM

#149

Post by prettydeep »

saurik wrote: post #72

I was under the impression that generating images where both dimensions were larger than 512 didn't merely require a lot of resources but didn't work well as the model was trained exclusively on 512 by 512 images and while it sort of worked ok to stretch one dimension a bit you got weird repetitions by making the overall canvas too large (as this isn't going to generate higher dpi images, merely ones with greater squ…

This is accurate in my experience. Changing the res. to anything but 512x512 produces inferior results.

Re: Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM

#150

Post by JimDabell »

whywhywhywhy wrote: post #137
JimDabell wrote: post #73

Earlier quoted context omitted.

I wouldn’t recommend using that as-is. MPS doesn’t give deterministic random number generation, which means that seeds become meaningless and you won’t ever be able to reproduce something. You can work around it by generating random numbers on the CPU and then moving them to MPS, but that probably requires a fix in PyTorch. The MPS support issue for diffusers is here: https://github.com/huggingface/diffusers/issues/2…

https://github.com/magnusviri/stable-diffusion/commit/d0b168... Copying this change fixed seeds on M1 for me.

That’s a fix for the CompVis forks, not the diffusers system we are talking about in this thread.

Also, that’s only a partial fix that doesn't really work properly. It doesn’t affect img2img and it still gets things wrong on the first render. Since txt2img starts from scratch each time, that means you’re always getting an incorrect render, it just happens to be the same incorrect render each time.

Post reply on HN