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

11–20 of 151 posts

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

#11

Post by qdot76367 »

For everyone about to comment on the garbage in the commit:

It looks like the committer made their changes in the top commit, then merged the updated CompViz StableDiffusion change set on top of it for some reason. That's where the license change, rick astley image, etc come from.

And yes, StableDiffusion from the original repo will rick roll you if you try to generate something that triggers its NSFW filter.

Here's the code that does it:

https://github.com/CompVis/stable-diffusion/blob/main/script...

And here's what it looks like:

https://twitter.com/qDot/status/1565076751465648128

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

#13

Post by jinseokim »

ceeplusplus wrote: post #4

Unfortunately the author of this PR decided to include garbage like this [1] in it, so this PR is pretty useless. [1] https://github.com/basujindal/stable-diffusion/pull/103/file...

I just reminded "clean room design" technique: https://en.m.wikipedia.org/wiki/Clean_room_design

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

#14

Post by jameshe »

dr_dshiv wrote: post #5

How much VRAM was previously required?

Looks like 10GB in the README[0] for a 512x512 image - though the fork[1] from the repo in this PR claims to be able to work with as little as 4GB VRAM.

[0] https://github.com/CompVis/stable-diffusion#stable-diffusion [1] https://github.com/basujindal/stable-diffusion#txt2img

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

#15

Post by javchz »

jinseokim wrote: post #13
ceeplusplus wrote: post #4

Unfortunately the author of this PR decided to include garbage like this [1] in it, so this PR is pretty useless. [1] https://github.com/basujindal/stable-diffusion/pull/103/file...

I just reminded "clean room design" technique: https://en.m.wikipedia.org/wiki/Clean_room_design

Yeah, reminds me of the old freedoom WADs situation

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

#16

Post by Matheus28 »

ceeplusplus wrote: post #4

Unfortunately the author of this PR decided to include garbage like this [1] in it, so this PR is pretty useless. [1] https://github.com/basujindal/stable-diffusion/pull/103/file...

Seems like author did his work on a different fork and pushed to this one, which included all changes from the other fork...

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

#17

Post by moneycantbuy »

gpt5 wrote: post #12
dr_dshiv wrote: post #5

How much VRAM was previously required?

I can generate a 768x896 pixels image on an RTX 3090, using 23.4/24GB

How does the content of the images look compared to the same prompt and seed for 512x512? I ask because when I make 768x896 with M1 MAX the resulting image is less coherent, more noisy, and or has repeating subject matter, nothing really usable unlike 512x512.

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

#18

Post by NHQ »

qdot76367 wrote: post #11

For everyone about to comment on the garbage in the commit: It looks like the committer made their changes in the top commit, then merged the updated CompViz StableDiffusion change set on top of it for some reason. That's where the license change, rick astley image, etc come from. And yes, StableDiffusion from the original repo will rick roll you if you try to generate something that triggers its NSFW filter. Here's…

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

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

#19

Post by piyh »

oefrha wrote: post #7

Almost impossible to pinpoint what changed thanks to thousands of lines of completely irrelevant changes and shitty commit messages. It seems the only changeset that might be relevant out of +2,273 -1,531 is the +11 -7 from https://github.com/basujindal/stable-diffusion/pull/103/comm... ? Does it even work?

As a learning opportunity for people like me, what does a good PR look like for a large change?

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

#20

Post by adastra22 »

piyh wrote: post #19
oefrha wrote: post #7

Almost impossible to pinpoint what changed thanks to thousands of lines of completely irrelevant changes and shitty commit messages. It seems the only changeset that might be relevant out of +2,273 -1,531 is the +11 -7 from https://github.com/basujindal/stable-diffusion/pull/103/comm... ? Does it even work?

As a learning opportunity for people like me, what does a good PR look like for a large change?

You don’t make large change PRs.
Post reply on HN