How fast is it on a m1?
The answer depends VERY MUCH on RAM. My M1 with 8GB takes 70-90 minutes per image. My M1 Pro with 16GB takes 3 minutes per image.
Another data point:
M1 Max with 64GB takes ~40 seconds
Run Stable Diffusion on Your M1 Mac’s GPU
201–210 of 415 posts
Re: Run Stable Diffusion on Your M1 Mac’s GPU
#202Earlier quoted context omitted.
Update: I solved this error more properly by upgrading to the latest version. Thanks bfirsh.
I am having the same issue on MacOS 12.2.1 (21D62); Python 3.10.6 What did you upgrade to solve this? Thanks! (I can get it working with `--precision full`)
I'm now on 12.5.1
Re: Run Stable Diffusion on Your M1 Mac’s GPU
#203I consistently have items only partially in frame- horses/fish/etc- any tips on getting the algo to keep specified items fully in frame?
Struggle with this too. One keyword which helps is 'wide angle'. Sometimes 'full body shot' works for generating humans.
Re: Run Stable Diffusion on Your M1 Mac’s GPU
#204How long does it take to generate a single image? Is it in the 30 min type range or a few mins? It's hypothetically "possible" to run e.g. OPT175B on a consumer GPU via Huggingface Accelerate, but in practice it takes like 30 mins to generate a single token.
On my late 2019 intel macbook pro with 32gb and a AMD 5550m it takes about 7-10 minutes to generate an image.
Re: Run Stable Diffusion on Your M1 Mac’s GPU
#205Is 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?
follow this guide:
https://github.com/lstein/stable-diffusion/blob/main/README-...
i am runnig it on my 2019 intel macbook pro. 10 minutes per picture
Re: Run Stable Diffusion on Your M1 Mac’s GPU
#206For those as keen as I am to try this out, I ran these steps, only to run into an error during the pip install phase: > ERROR: Failed building wheel for onnx I was able to resolve it by doing this: > brew install protobuf Then I ran pip install again, and it worked!
Python dependency hell in a nutshell. Impossible to distribute ML projects that can easily be ran.
Re: Run Stable Diffusion on Your M1 Mac’s GPU
#207Earlier quoted context omitted.
I hope this kickstarts some kind of M1 migration. There are so many ML projects I'd like to try, but they all depend on CUDA.
Do they depend on CUDA, or are they just much better tuned for NVIDIA cards? I thought the whole ML ecosystem was based on training models and then running them on frameworks, where model was sorta like data and the framework handles the hardware? (albeit with models that can be tweaked to run more efficiently on different hardware) (I don't really know the ecosystem so it is definitely possible that they are more cl…
From my experience the bigger frameworks may have support for non-CUDA devices (that is not just the CPU fallback) but many smaller libraries and models will not, and will only have a CUDA kernel for some specialized operation.
I encounter this all the time in computer vision models.
Re: Run Stable Diffusion on Your M1 Mac’s GPU
#208Earlier 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.
An RTX 3090ti with 24GB of VRAM is widely available now that the crypto markets have crashed for $1150 or so. They were $2500 a year ago if you could find them.
Re: Run Stable Diffusion on Your M1 Mac’s GPU
#209Note that once you run the python script for the first time it seems to download a further ~2GB of data
Including a rick astley image for the first thing you gen -_-
Re: Run Stable Diffusion on Your M1 Mac’s GPU
#210How is Stable Diffusion on DreamStudio.ai so much faster than the reports here? Seems to only take 5-10 seconds to generate an image with the default settings. I.e. How are they providing access to GPU compute several orders of magnitude more powerful than an M1, for free?
The guy behind it is an ex hedge fund manager. Using private funds he's built a massive fleet of A1000s at AWS. So it's an enormous amount of compute created from private funds that he considers to be "for humanity". Currently, he funds it and is also the "GPU overlord", he exclusively decides which applications gets to use it. His plan, or at least his claim, is to transform this situation in it being more diversely…
The guy's name is Emad Mostaque btw
There's a recent video interview he did that goes into his vision: https://www.youtube.com/watch?v=YQ2QtKcK2dA