Not working on macOS (Silicon)

[ParityError]

% git clone https://github.com/adobe-research/custom-diffusion.git
Cloning into 'custom-diffusion'...
remote: Enumerating objects: 214, done.
remote: Counting objects: 100% (49/49), done.
remote: Compressing objects: 100% (35/35), done.
remote: Total 214 (delta 26), reused 31 (delta 14), pack-reused 165
Receiving objects: 100% (214/214), 51.28 MiB | 33.20 MiB/s, done.
Resolving deltas: 100% (88/88), done.
% git clone https://github.com/CompVis/stable-diffusion.git
Cloning into 'stable-diffusion'...
remote: Enumerating objects: 340, done.
remote: Total 340 (delta 0), reused 0 (delta 0), pack-reused 340
Receiving objects: 100% (340/340), 42.65 MiB | 30.80 MiB/s, done.
Resolving deltas: 100% (114/114), done.
% cd stable-diffusion
% conda env create -f environment.yaml
Collecting package metadata (repodata.json): done
Solving environment: failed

ResolvePackageNotFound: 
  - pip=20.3
  - torchvision=0.12.0
  - cudatoolkit=11.3
  - python=3.8.5

[nupurkmr9]

Hi, Thanks for your interest in our work. The error seems to be an issue with MacOS, as discussed here as well. Installing anaconda/miniconda and then setting up environment with cudatoolkit==9.0 in environment.yaml should remove this issue. But MacOS will only support CPU version which will be very slow. I will try to run it on a MacOS and add more detailed steps as soon as possible. Thanks.

[ParityError]

@nupurkmr9 Thanks for the info.

Do you plan on creating a google colab version? I tried the one on huggingface, which seems to get stuck infinitely training (maybe it's timing out) and never completes.