Hacker News Reader

Comment by geuis | Hacker News Reader

I've been looking into this for the last 2 days. Unless you're running an M1 Mac or newer, you're SOL.

Stable Diffusion is built on PyTorch. PyTorch mainly has been designed to work with Nvidia cards. However PyTorch added support for something called RocM like a year ago that adds compatibility with newer AMD cards.

Unfortunately RocM doesn't support slightly older AMD cards in conjunction with intel processors.

So my 32gb pretty powerful 2020 16in MacBook Pro isn't capable of running Stable Diffusion.

Any native app will likely have to rely on a remote cloud gpu. And boy, those are fucking expensive. Been researching what I need to stand up a service the last few days and it isn't cost friendly.

View on HN

> I've been looking into this for the last 2 days. Unless you're running an M1 Mac or newer, you're SOL.

And not just any old M1 Mac. Last week I got it running on my 2021 8GB M1 MacBook Air and it's slow. Images at 512x512 with 10 steps take between 7 and 10 minutes to generate.

It's the only thing I do that hits performance limitations on the 8GB machine so there's no regrets on that score, but with the way this stuff is progressing 16GB+ is a realistic minimum for comfortable use.

FWIW I'm on a 2021 16GB M1 MacBook Pro and it takes about 7min for me as well.

I've just been following the steps here with default settings: https://replicate.com/blog/run-stable-diffusion-on-m1-mac, but maybe there's a better way to run it at this point?

That's what I initially followed, too. But there does seem to be a better way - I've just installed CHARL-E [0] (mentioned elsewhere in this thread) and it was trivial to set up. Literally download the dmg, drag into Applications, and run.

It's an electron app and you can either download it with the weights, or without and add them separately.

Using that it just took slightly over 5 minutes on my 8GB so it's a little bit quicker for me. Maybe the code has improved since I cloned stuff over a week ago, or maybe it's just different system resources when it is run. Either way, it looks like the easy way I've been waiting for.

[0] https://www.charl-e.com

Edit: It is however missing the CFG setting.

I've been running the Intel CPU version [0] for a while now on a 2013 MacMini. Works fine; it takes several minutes per image but I can live with that.

[0] https://news.ycombinator.com/item?id=32642255

There is work on a CoreML version which may play nicer with older Macs w/sufficiently beefy dGPUs.

https://github.com/huggingface/diffusers/issues/443

Will the CoreML version run faster than https://replicate.com/blog/run-stable-diffusion-on-m1-mac on an M1 Mac?

> And boy, those are fucking expensive.

Unless you want to train the model, Lambda Labs is somewhat cheap:

https://lambdalabs.com/service/gpu-cloud

Apple's MPS drivers supports AMD GPUs on MacOS

Just heard about MPS in another thread.

Reply on news.ycombinator.com