Error occurred when executing GroundingDinoSAMSegment (segment anything): Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument mat2 in method wrapper_CUDA_mm)

[Ymshkz]

When I run this item in Comfyui, it reports an error like this

Error occurred when executing GroundingDinoSAMSegment (segment anything):

Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument mat2 in method wrapper_CUDA_mm)

File "D:\Comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\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 "D:\Comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\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 "D:\Comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_segment_anything\node.py", line 325, in main (images, masks) = sam_segment( ^^^^^^^^^^^^ File "D:\Comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_segment_anything\node.py", line 247, in samsegment masks, , _ = predictor.predict_torch( ^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context return func(*args, *kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "D:\Comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_LayerStyle\py\sam_hq\predictor.py", line 114, in predict_torch sparse_embeddings, dense_embeddings = self.model.prompt_encoder( ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\segment_anything\modeling\prompt_encoder.py", line 158, in forward box_embeddings = self._embed_boxes(boxes) ^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Comfyui\ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\segment_anything\modeling\prompt_encoder.py", line 97, in _embed_boxes corner_embedding = self.pe_layer.forward_with_coords(coords, self.input_image_size)

I'm a complete novice in this area. I hope that when someone answers the question, he can try his best to describe it in a way that a novice can understand. Thank you.