InvokeAI

Sorry about that, web link rot sure is real eh. This is an example of the original file: https://github.com/magnusviri/stable-diffusion/blob/79ac0f34... Which seems to have been renamed, and cleaned up a bit here: https://github.com/magnusviri/stable-diffusion/blob/main/doc... However, per the note on the magnusviri repo, the following repo should be used for a stable set of this SD Toolkit: https://github.com/invoke-ai/InvokeAI with instructions here https://github.com/invoke-ai/InvokeAI/blob/main/docs/install...

>Which repo or build are you using BTW, is it the one related to this readme? https://github.com/magnusviri/stable-diffusion/blob/main/REA... Yes, this one. However it was like a month ago I think, so speeds might have improved. I'm getting ~2.2s/step with another implementation: https://news.ycombinator.com/item?id=33006447

Not M1 comparible but I'm working on testing various GPU vs M1 comparisons, with a few accessible cloud providers. My impression is times should be the same, but it's nice to hear other real-world stats for M1 with SD. Makes me really want to rent the Hetzner M1 now. Which repo or build are you using BTW, is it the one related to this readme? https://github.com/magnusviri/stable-diffusion/blob/main/REA...

SD on an Intel mac with Vega graphics runs pretty well though — I think it ran at something like ~3-5 iterations/s for me, which is decent. I ran either https://github.com/magnusviri/stable-diffusion or https://github.com/lstein/stable-diffusion which have MPS support

https://github.com/magnusviri/stable-diffusion/commit/d0b168... Copying this change fixed seeds on M1 for me.

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 [3] [0] https://github.com/magnusviri/stable-diffusion [1] https://github.com/lstein/stable-diffusion [2] https://github.com/lstein/stable-diffusion/blob/main/README-...

I'm using the fork here: https://github.com/magnusviri/stable-diffusion.git (apple-silicon-mps-support branch). Pretty easy to set up, though I had to take all the Homebrew stuff out of my environment before setting up the Conda environment (can also just export GRPC_PYTHON_BUILD_SYSTEM_OPENSSL=1 GRPC_PYTHON_BUILD_SYSTEM_ZLIB=1, at least in my case). Otherwise, I followed the normal steps to set things up, and I'm now here generating 1 image every 30 seconds at default settings. This is on a M1 Max MacBook Pro at 64GB RAM.

I found this repo early on and have been using it to run inference on my M1 Pro MBP. https://github.com/ModeratePrawn/stable-diffusion-cpu For me it runs at about 3.5 seconds per iteration per picture at 512x512. There is also a fork that uses metal here and is much faster: https://github.com/magnusviri/stable-diffusion/tree/apple-si... but it doesn't support seeding the rng and will occasionally produce completely black output. Useful if you want to spit out a whole bunch of images for one prompt but you lose the ability to re-run a specific seed with a tweaked prompt or increased iterations.

looks like there is an easier path using metal shaders: https://dev.to/craigmorten/setting-up-stable-diffusion-for-m... and https://github.com/magnusviri/stable-diffusion/tree/apple-si...

There are as well forks for the GPU in Apple’s M1 chips: https://github.com/magnusviri/stable-diffusion