kijai / ComfyUI-SUPIR

SUPIR upscaling wrapper for ComfyUI
Other
1.2k stars 66 forks source link

Error occurred when executing SUPIR_conditioner: #135

Open crockrocks opened 3 weeks ago

crockrocks commented 3 weeks ago

Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.

File "/home/ubuntu/harsh/ComfyUI/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/home/ubuntu/harsh/ComfyUI/execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "/home/ubuntu/harsh/ComfyUI/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/home/ubuntu/harsh/ComfyUI/custom_nodes/ComfyUI-SUPIR/nodes_v2.py", line 571, in condition SUPIR_model.conditioner.to(device) File "/home/ubuntu/harsh/ComfyUI/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1173, in to return self._apply(convert) File "/home/ubuntu/harsh/ComfyUI/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 779, in _apply module._apply(fn) File "/home/ubuntu/harsh/ComfyUI/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 779, in _apply module._apply(fn) File "/home/ubuntu/harsh/ComfyUI/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 779, in _apply module._apply(fn) File "/home/ubuntu/harsh/ComfyUI/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 804, in _apply param_applied = fn(param) File "/home/ubuntu/harsh/ComfyUI/.venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1166, in convert raise NotImplementedError(

Never encountered any such issue , what is causing this issue ?

cvar66 commented 2 weeks ago

identical issue, used to work

cvar66 commented 2 weeks ago

I found the problem, I suspect you are having the same issue. The workflow I was using still had the legacy model loader. Switched it to v2 and it works now.