search

SamKhoze / ComfyUI-DeepFuze

DeepFuze is a state-of-the-art deep learning tool that seamlessly integrates with ComfyUI to revolutionize facial transformations, lipsyncing, Face Swapping, Lipsync Translation, video generation, and voice cloning.
https://cogidigm.com/
Other
299 stars 32 forks source link

ERROR could not be loaded with cv. if select cuda device #33

Closed ItsmeEsal closed 3 months ago

ItsmeEsal commented 3 months ago

I have installed cuda toolkit 11.8 and cudnn 8.9.2 which I got in the readme page link, I have checked the cuda version using the nvcc --version command and it produces the same message in tutorial : nvcc: NVIDIA(R) Cuda compiler driver Copyright (c) 2005-2022 NVIDIA Corporation Built on Wed_Sep_21_10:41:10_Pacific_Daylight_Time_2022 Cuda compilation tools, release 11.8, V11.8.89 Build cuda_11.8.r11.8/compiler.31833905_0

i have set environment, and doing all in readme, but still not work, displaying error message : Error occurred when executing DeepFuzeAdavance:

E:\AI_Collection\ComfyUI\ComfyUI\output\deepfuze\enhanced17211040623053725.mp4 could not be loaded with cv.

File "E:\AI_Collection\ComfyUI\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\AI_Collection\ComfyUI\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:\AI_Collection\ComfyUI\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\AI_Collection\ComfyUI\ComfyUI\custom_nodes\ComfyUI-DeepFuze\nodes.py", line 1335, in lipsyncgenerate return load_video_cv(filename,0,'Disabled',512,512,0,0,1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\AI_Collection\ComfyUI\ComfyUI\custom_nodes\ComfyUI-DeepFuze\nodes.py", line 446, in load_video_cv (width, height, fps, duration, total_frames, target_frame_time) = next(gen) ^^^^^^^^^ File "E:\AI_Collection\ComfyUI\ComfyUI\custom_nodes\ComfyUI-DeepFuze\nodes.py", line 365, in cv_frame_generator raise ValueError(f"{video} could not be loaded with cv.")

I Use Portable ComfyUI in di window 11, and download deepfuze in comfy manager. I think i have been reinstalling 2 times or more, but still not work

ItsmeEsal commented 3 months ago

i found the mistake, i use onnxruntime-gpu version 1.18.1, but this version not work, so i change version to 1.18.0 its work for me👌