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

191–200 of 415 posts

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

#191

Post by johnfn »

jw1224 wrote: post #76
usehackernews wrote: post #68

Magnusviri[0], the original author of the SD M1 repo credited in this article, has merged his fork into the Lstein Stable Diffusion fork. You can now run the Lstein fork[1] with M1 as of a few hours ago. This adds a ton of functionality - GUI, Upscaling & Facial improvements, weighted subprompts etc. This has been a big undertaking over the last few days, and I highly recommend checking it out. See the mac m1 readme…

Brilliant, thank you! I just got OP's setup working, but this seems much more user-friendly. Giving it a try now... EDIT: Got it working, with a couple of pre-requisite steps: 0. `rm` the existing `stable-diffusion` repo (assuming you followed OP's original setup) 1. Install `conda`, if you don't already have it: brew install --cask miniconda 2. Install the other build requirements referenced in OP's setup: brew inst…

I followed all these steps, but I got this error:

> User specified autocast device_type must be 'cuda' or 'cpu'

> Are you sure your system has an adequate NVIDIA GPU?

I found the solution here: https://github.com/lstein/stable-diffusion/issues/293#issuec...

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

#192

Post by jastanton »

toinewx wrote: post #163
jw1224 wrote: post #76

Earlier quoted context omitted.

Brilliant, thank you! I just got OP's setup working, but this seems much more user-friendly. Giving it a try now... EDIT: Got it working, with a couple of pre-requisite steps: 0. `rm` the existing `stable-diffusion` repo (assuming you followed OP's original setup) 1. Install `conda`, if you don't already have it: brew install --cask miniconda 2. Install the other build requirements referenced in OP's setup: brew inst…

I was able not to have black images by using a different sampler --sampler k_euler full command: "photography of a cat on the moon" -s 20 -n 3 --sampler k_euler -W 384 -H 384

I tried that as well but resulted in an error:

AttributeError: module 'torch._C' has no attribute '_cuda_resetPeakMemoryStats'

https://gist.github.com/JAStanton/73673d249927588c93ee530d08...

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

#194

Post by sroussey »

bfirsh wrote: post #93
sroussey wrote: post #92

This should be put into a docket image to avoid various potential conflicts with locally installed libraries. Anyone do this for the M1?

Unfortunately this can't run in Docker because Docker for Mac can't access the M1 GPU. (Several layers of virtualization and emulation!)

Ah, thanks. Yes, that makes sense.

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

#195

Post by zone411 »

jdminhbg wrote: post #190
zone411 wrote: post #169

Earlier quoted context omitted.

The performance gap to the top-end Nvidia cards will get much larger as they release new cards later this year, though.

Maybe, but I can buy a Mac, you just order one from Apple.

It's not clear if the shortages will happen with this new release as they did last time. Ethereum mining is going away and not as many people are stuck at home because of Covid. On the other hand, the performance increase looks to be substantial, increasing the demand.

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

#197

Post by dmd »

yieldcrv wrote: post #159
usehackernews wrote: post #68

Magnusviri[0], the original author of the SD M1 repo credited in this article, has merged his fork into the Lstein Stable Diffusion fork. You can now run the Lstein fork[1] with M1 as of a few hours ago. This adds a ton of functionality - GUI, Upscaling & Facial improvements, weighted subprompts etc. This has been a big undertaking over the last few days, and I highly recommend checking it out. See the mac m1 readme…

are there benchmarks? I was following the github issue and the CPU bound one was at 4-5 minutes, the MDS one was at 30 seconds, then 18 seconds, and people were still calling that slow. What is it currently at now? and I don't know what "fast" is, to compare What are the Windows 10 with nice Nvidia chips w/ CUDA getting? Just curious whats comprehensive

Wait, what? On my M1 imac I’m getting about 25 minutes. What am i doing wrong?

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

#198

Post by arthurcolle »

toinewx wrote: post #156
jw1224 wrote: post #76

Earlier quoted context omitted.

Brilliant, thank you! I just got OP's setup working, but this seems much more user-friendly. Giving it a try now... EDIT: Got it working, with a couple of pre-requisite steps: 0. `rm` the existing `stable-diffusion` repo (assuming you followed OP's original setup) 1. Install `conda`, if you don't already have it: brew install --cask miniconda 2. Install the other build requirements referenced in OP's setup: brew inst…

I only get black images.

You have to disable the safety checker after creating the pipe

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

#199

Post by arthurcolle »

toinewx wrote: post #152
usehackernews wrote: post #68

Magnusviri[0], the original author of the SD M1 repo credited in this article, has merged his fork into the Lstein Stable Diffusion fork. You can now run the Lstein fork[1] with M1 as of a few hours ago. This adds a ton of functionality - GUI, Upscaling & Facial improvements, weighted subprompts etc. This has been a big undertaking over the last few days, and I highly recommend checking it out. See the mac m1 readme…

Everything works excepts it only generates black images, did you run python scripts/preload_models.py python scripts/dream.py --full_precision ?

Disable safety check

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

#200

Post by MintsJohn »

my123 wrote: post #85
switchers wrote: post #57

Earlier quoted context omitted.

6600XT reporting in. Spent a few hours on Windows and WSL2 setup attempts, got no where. I don't run Ubuntu at home and don't want to dual boot just for this. From looking around I think I'd have a better chance on native Ubuntu.

Buy an NVIDIA card. ROCm isn't supported in any way on WSL2, but CUDA is. AMD just doesn't invest in their developer ecosystem. Also as you use a 6600 XT, no official ROCm support for the die that you use. Only for navi21.

Or wait, if its just about stable diffusion multiple people try to create onnx and directml forks of the models/scripts, which atleast in theory can work for AMD gpus in windows and wsl2
Post reply on HN