RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False.

[SssTwins]

when i use comfy_pixelization, i got an error

ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization_init_.py", line 264, in pixelize
model.load()
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization_init_.py", line 150, in load
self.G_A_net = define_G(3, 3, 64, "c2pGen", "instance", False, "normal", 0.02, [0])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization\pixelization\models\networks.py", line 138, in define_G
net = C2PGen(input_nc, output_nc, ngf, 2, 4, 256, 256, activ='relu', pad_type='reflect')
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization\pixelization\models\c2pGen.py", line 79, in init
self.PBEnc = PixelBlockEncoder(input_dim, dim, style_dim, norm='none', activ=activ, pad_type=pad_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization\pixelization\models\c2pGen.py", line 124, in init
vgg19.load_state_dict(torch.load('./pixelart_vgg19.pth'))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization_init_.py", line 118, in load
return torch.load(filename, map_location='cpu', *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1026, in load
return _load(opened_zipfile,
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1438, in _load
result = unpickler.load()
^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1408, in persistent_load
typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1382, in load_tensor
wrap_storage=restore_location(storage, location),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 391, in default_restore_location
result = fn(storage, location)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 266, in _cuda_deserialize
device = validate_cuda_device(location)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 250, in validate_cuda_device
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.

These are my pc device parameters

cpu: AMD Ryzen™ 7 5700X
gpu: AMD Radeon™ RX 6650 XT

What have I tried?

change ComfyUI\custom_nodes\comfy_pixelization_init_.py
line 36, from 'return torch.device(get_optimal_device_name())' to 'return torch.device("cpu")'
line 118, from 'return torch.load(filename, *args, **kwargs)' to 'return torch.load(filename, map_location='cpu', *args, **kwargs)'
line 153 from 'G_A_state = torch.load(path_160_net_G_A)' to 'G_A_state = torch.load(path_160_net_G_A, map_location=device)'
line 158 from 'alias_state = torch.load(path_alias_net)' to 'alias_state = torch.load(path_alias_net,map_location=device)'

Look forward to hearing from you

[SssTwins]

when i use comfy_pixelization, i got an error

ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization__init__.py", line 264, in pixelize
model.load()
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization__init__.py", line 150, in load
self.G_A_net = define_G(3, 3, 64, "c2pGen", "instance", False, "normal", 0.02, [0])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization\pixelization\models\networks.py", line 138, in define_G
net = C2PGen(input_nc, output_nc, ngf, 2, 4, 256, 256, activ='relu', pad_type='reflect')
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization\pixelization\models\c2pGen.py", line 79, in init
self.PBEnc = PixelBlockEncoder(input_dim, dim, style_dim, norm='none', activ=activ, pad_type=pad_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization\pixelization\models\c2pGen.py", line 124, in init
vgg19.load_state_dict(torch.load('./pixelart_vgg19.pth'))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy_pixelization__init__.py", line 118, in load
return torch.load(filename, map_location='cpu', *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1026, in load
return _load(opened_zipfile,
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1438, in _load
result = unpickler.load()
^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1408, in persistent_load
typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 1382, in load_tensor
wrap_storage=restore_location(storage, location),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 391, in default_restore_location
result = fn(storage, location)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 266, in _cuda_deserialize
device = validate_cuda_device(location)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 250, in validate_cuda_device
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.

These are my pc device parameters

cpu: AMD Ryzen™ 7 5700X
gpu: AMD Radeon™ RX 6650 XT

What have I tried?

change ComfyUI\custom_nodes\comfy_pixelization__init__.py
line 36, from 'return torch.device(get_optimal_device_name())' to 'return torch.device("cpu")'
line 118, from '**return torch.load(filename, *args, kwargs)' to '**return torch.load(filename, map_location='cpu', *args, kwargs)'
line 153 from 'G_A_state = torch.load(path_160_net_G_A)' to 'G_A_state = torch.load(path_160_net_G_A, map_location=device)'
line 158 from 'alias_state = torch.load(path_alias_net)' to 'alias_state = torch.load(path_alias_net,map_location=device)'

Look forward to hearing from you

comfy run as cpu mode

[filipemeneses]

Awesome, thanks for reaching out, I'll try later with the following (used this as guide)

            G_A_state = torch.load(path_160_net_G_A, map_location={'cuda:0': device})
...
            alias_state = torch.load(path_alias_net, map_location={'cuda:0': device})