RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm)

[qaqwqyu]

I was running this on a windows machine yet this error is constantly printed. I tried assigning cuda by changing the files train_cyclegan_turbo.py and cyclegan_turbo.py. It does not work.

Here is the error message:

Traceback (most recent call last):
File "C:\Users\THAD\img2img-turbo\src\train_cyclegan_turbo.py", line 403, in
main(args)
File "C:\Users\THAD\img2img-turbo\src\train_cyclegan_turbo.py", line 194, in main
cyc_fake_b = CycleGAN_Turbo.forward_with_networks(img_a, "a2b", vae_enc, unet, vae_dec, noise_scheduler_1step, timesteps, fixed_a2b_emb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\img2img-turbo\src\cyclegan_turbo.py", line 217, in forward_with_networks
model_pred = unet(x_enc, timesteps, encoder_hidden_states=text_emb).sample # Ensure timesteps and text_emb are on the same device
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch_dynamo\eval_frame.py", line 574, in _fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\diffusers\models\unets\unet_2d_condition.py", line 1143, in forward
emb = self.time_embedding(t_emb, timestep_cond)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\diffusers\models\embeddings.py", line 1304, in forward
sample = self.linear_1(sample)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\THAD\AppData\Local\Programs\Python\Python312\Lib\site-packages\torch\nn\modules\linear.py", line 125, 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, cpu and cuda:0! (when checking argument for argument mat1 in method wrapper_CUDA_addmm)