RuntimeError: Expected all tensors to be on the same device

#114
by distoff1 - opened

Using contol net model (canny) on automatic1111 by CPU only (i have poor GPU) gives me this error. anyone knows the solution of this error ?

File "C:\Users\Aorus\a1111\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\linear.py", line 114, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument mat1 in method wrapper_CUDA_addmm)

Thank you.

sometimes swapping out to another model then reloading the intended model works for me

sometimes swapping out to another model then reloading the intended model works for me

ok, i'll try it. thank you

Sign up or log in to comment