Is it possible to run it on AMD Gpu?
tomaszmac opened this issue · 1 comments
tomaszmac commented
I have the fork version of SD for AMDs gpus and when trying to run this I'm getting an error
raise RuntimeError('Attempting to deserialize object on a CUDA ' RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.
Is there a workaround to make it work on AMD?
VeteranXT commented
+1