then - how far away are we from having it on M1/M2 Macs, at least with regular processing?
openvino may be one path I suppose:
https://github.com/openvinotoolkit/openvino/issues/11554
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.
Wow that's impressively fast, I have a relatively recent Nvidia GPU that still takes 10 seconds. And the GPU is already almost as big as the entire macbook
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.
and https://github.com/magnusviri/stable-diffusion/tree/apple-si...
What model are you using? I've been running full-precision SD1.4 on my 3070, albeit with less than 10% VRAM headroom.
I shouldn't have given up so easily, but my tolerance for annoyances on Windows is pretty low (that Windows machine is kept for gaming, the last time I used a Windows machine for anything but launching Steam was when Windows 2000 was the hot new thing...)