ControlNet does not work with Accelerated PyTorch training on Mac :( #502
angelkaragiozov
started this conversation in
Ideas
Replies: 1 comment
-
|
HuggingFace implemented a controlnet training script based on accelerate https://huggingface.co/docs/diffusers/training/controlnet |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi guys ControlNet does not work with Accelerated PyTorch training on Mac
https://developer.apple.com/metal/pytorch/
NotImplementedError: The operator 'aten::upsample_linear1d.out' is not currently implemented for the MPS device. If you want this op to be added in priority during the prototype phase of this feature, please comment on pytorch/pytorch#77764. As a temporary fix, you can set the environment variable
PYTORCH_ENABLE_MPS_FALLBACK=1to use the CPU as a fallback for this op. WARNING: this will be slower than running natively on MPS.P.S.
I found only one solution for Canny edges that works only with SDXL 1.0 -----> https://huggingface.co/diffusers/controlnet-canny-sdxl-1.0
Beta Was this translation helpful? Give feedback.
All reactions