StableDiffusionTelegram icon indicating copy to clipboard operation
StableDiffusionTelegram copied to clipboard

Published 20 hours ago • verified publisher icon jossalgon

debian server

Open rafalohaki opened this issue 2 years ago • 1 comments

i installed pytorch for cpu on debian server got error: Pipelines loaded with torch_dtype=torch.float16 cannot run with cpu or mps device. It is not recommended to move them to cpu or mps as running them will fail. Please make sure to use a cuda device to run the pipeline in inference. due to the lack of support for float16 operations on those devices in PyTorch. Please remove the torch_dtype=torch.float16 argument, or use a cuda device to run inference.

rafalohaki avatar Dec 10 '22 13:12 rafalohaki

Does anyone have any solution for this?

gisty1 avatar Mar 16 '23 16:03 gisty1