search

comfyanonymous / ComfyUI_TensorRT

MIT License
514 stars 34 forks source link

Error occurred when executing DYNAMIC_TRT_MODEL_CONVERSION #53

Open jikeshiganjia opened 4 months ago

jikeshiganjia commented 4 months ago

Error occurred when executing DYNAMIC_TRT_MODEL_CONVERSION:

load_models_gpu() got an unexpected keyword argument 'force_patch_weights'

File "E:\ComfyUI_SVD_Toolkit(1)\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI_SVD_Toolkit(1)\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 "E:\ComfyUI_SVD_Toolkit(1)\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\ComfyUI_SVD_Toolkit(1)\ComfyUI\custom_nodes\ComfyUI_TensorRT-master\tensorrt_convert.py", line 517, in convert return super()._convert( ^^^^^^^^^^^^^^^^^ File "E:\ComfyUI_SVD_Toolkit(1)\ComfyUI\custom_nodes\ComfyUI_TensorRT-master\tensorrt_convert.py", line 159, in _convert comfy.model_management.load_models_gpu([model], force_patch_weights=True)

zhangyuzhen1990 commented 3 months ago

I met the same problem, have you got any solutions?

th-ink commented 3 months ago

I got the same error also when usign static model conversion. Error occurs with different SD chekpoints (SD XL and 1.5).

th-ink commented 3 months ago

I updated ComfyUI to the latest version (git pull with manual install on Windows) and the problem was resolved. I can now build TensorRT models without an issue.