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

Run Stable Diffusion on Your M1 Mac’s GPU

replicate.com

Post reply on HN
Print view View original

281–290 of 415 posts

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#281

Post by blagie »

dougmwne wrote: post #25
blagie wrote: post #14

Earlier quoted context omitted.

Are you following progress in robotics?

School us! What’s the latest in robotics that is going to knock our socks off?

I mean, I'm most impressed with the gradual rise of 3d printers capable of printing entire houses.

That doesn't help with plumbing, electrical, kitchen cabinets and all the other stuff that goes into a house -- which is a majority of the cost -- but it's a gradual start.

I see very little which can't be automated, but I see a lot which would take many years of time and effort to automate and integrate.

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#282

Post by Daegalus »

ChildOfChaos wrote: post #98

Is there anyway to keep up with this stuff / beginners guide? I really want to play around with it but it's kinda confusing to me. I don't have an M1 Mac, I have an Intel one with an AMD GPU, not sure if i can run it? don't mind if it's a bit slow, or what is the best way of running it in the cloud? Anything that can product high res for free?

I wrote a guide for AMD.

https://yulian.kuncheff.com/stable-diffusion-fedora-amd/

it's for, but it could be adapted to Linux as.lomg as you install the right drivers and such.

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#283

Post by Daegalus »

yoyohello13 wrote: post #31

Has anybody had success getting newer AMD cards working? ROCm support seems spotty at best, I have a 5700xt and I haven't had much luck getting it working.

you can try my guide. got it working on a 6750XT

https://yulian.kuncheff.com/stable-diffusion-fedora-amd/

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#284

Post by chrisfrantz »

cageface wrote: post #248

After playing around with all of these ML image generators I've found myself surprisingly disenchanted. The tech is extremely impressive but I think it's just human psychology that when you have an unlimited supply of something you tend to value each instance of it less. Turns out I don't really want thousands of good images. I want a handful of excellent ones.

Human curation will likely remain valuable into the future.

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#285

Post by Daegalus »

imtemplain wrote: post #175

I'm ready to pay for a Windows + AMD GPU guide at this point, why is there no single blogpost on this, please help.

I'm sure you can do it by installing the ROCm drivers, install pytorch-rocm based on the download page for pytorch, and make sure to set any settings in environment variables.

you can try following my Linux AMD guide and see what you can pick and choose to get it working

https://yulian.kuncheff.com/stable-diffusion-fedora-amd/

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#286

Post by grishka »

gregsadetsky wrote: post #231

Bananas. Thanks so much... to everyone involved. It works. 14 seconds to generate an image on an M1 Max with the given instructions (`--n_samples 1 --n_iter 1`) Also, interesting/curious small note: images generated with this script are "invisibly watermarked" i.e. steganographied! See https://github.com/bfirsh/stable-diffusion/blob/main/scripts...

> Also, interesting/curious small note: images generated with this script are "invisibly watermarked" i.e. steganographied!

Why?

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#287

Post by Retr0id »

grishka wrote: post #286
gregsadetsky wrote: post #231

Bananas. Thanks so much... to everyone involved. It works. 14 seconds to generate an image on an M1 Max with the given instructions (`--n_samples 1 --n_iter 1`) Also, interesting/curious small note: images generated with this script are "invisibly watermarked" i.e. steganographied! See https://github.com/bfirsh/stable-diffusion/blob/main/scripts...

> Also, interesting/curious small note: images generated with this script are "invisibly watermarked" i.e. steganographied! Why?

So that future iterations of StableDiffusion (or similar models) don't end up getting trained on their own outputs.

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#288

Post by fprog »

pja wrote: post #47
johnfn wrote: post #42

Earlier quoted context omitted.

Haha, busted!

To be fair, the reason the filter is there is that if you ask for a picture of a woman, stable diffusion is pretty likely to generate a naked one! If you tweak the prompt to explicitly mention clothing, you should be OK though.

Wow, is that true? I’ve never heard a more textbook ethical problem with a model.

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#289

Post by fastball »

schappim wrote: post #272

I just got rick-rolled by the model. Using the prompt: "1990s textbook background mephis style"[sic] (yup I meant memphis)[0], I got back this: [1]. Rerunning the same prompt, I got: [2]. [0] https://files.littlebird.com.au/Shared-Image-2022-09-02-10-2... [1] https://files.littlebird.com.au/grid-0004-2xXAGF.png [2] https://files.littlebird.com.au/grid-0005-kcfgq7.png

The rick-roll is the NSFW filter. It's not actually that great at detecting NSFW content.

Re: Run Stable Diffusion on Your M1 Mac’s GPU

#290

Post by bschwindHN »

Everyone posting their pip/build/runtime errors is everything that's wrong with tooling built on top of python and its ecosystem.

It would be nice to see the ML community move on to something that's actually easily reproducible and buildable without "oh install this version of conda", "run pip install for this package", "edit this line in this python script".

Post reply on HN