ShmuelRonen / ComfyUI_wav2lip

A custom node for ComfyUI that allows you to perform lip-syncing on videos using the Wav2Lip model. It takes an input video and an audio file and generates a lip-synced output video.
76 stars 19 forks source link

unexpected EOF,i have download many wav2lip_gan.pth but all of them failed #39

Closed whmc76 closed 1 month ago

whmc76 commented 1 month ago

got prompt [rgthree] Using rgthree's optimized recursive execution. (80, 279) Length of mel chunks: 3 Load model from: E:\VIDEO\ComfyUI_video\ComfyUI\custom_nodes\ComfyUI_wav2lip\Wav2Lip\checkpoints\wav2lip_gan.pth Load checkpoint from: E:\VIDEO\ComfyUI_video\ComfyUI\custom_nodes\ComfyUI_wav2lip\Wav2Lip\checkpoints\wav2lip_gan.pth 0%| | 0/1 [00:00<?, ?it/s] !!! Exception during processing!!! unexpected EOF, expected 3976502 more bytes. The file might be corrupted. Traceback (most recent call last): File "E:\VIDEO\ComfyUI_video\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\VIDEO\ComfyUI_video\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 "E:\VIDEO\ComfyUI_video\ComfyUI\execution.py", line 75, in map_node_over_list results.append(getattr(obj, func)(slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\VIDEO\ComfyUI_video\ComfyUI\custom_nodes\ComfyUI_wav2lip\wav2lip.py", line 104, in process out_imglist = wav2lip(in_img_list, temp_audio_path, face_detect_batch, mode, model_path, framerate, lipsync_intensity, smoothing_factor) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\VIDEO\ComfyUI_video\ComfyUI\custom_nodes\ComfyUI_wav2lip\Wav2Lip\wav2lipnode.py", line 188, in wav2lip for i, (img_batch, mel_batch, frames, coords) in enumerate(tqdm(gen, File "E:\VIDEO\ComfyUI_video\python_embeded\Lib\site-packages\tqdm\std.py", line 1181, in iter for obj in iterable: File "E:\VIDEO\ComfyUI_video\ComfyUI\custom_nodes\ComfyUI_wav2lip\Wav2Lip\wav2lip_node.py", line 86, in datagen face_det_results = face_detect(frames, face_detect_batch) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\VIDEO\ComfyUI_video\ComfyUI\custom_nodes\ComfyUI_wav2lip\Wav2Lip\wav2lip_node.py", line 41, in face_detect detector = face_detection.FaceAlignment(face_detection.LandmarksType._2D, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\VIDEO\ComfyUI_video\ComfyUI\custom_nodes\ComfyUI_wav2lip\Wav2Lip\face_detection\api.py", line 60, in init self.face_detector = sfd.FaceDetector(device=device, verbose=verbose) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\VIDEO\ComfyUI_video\ComfyUI\custom_nodes\ComfyUI_wav2lip\Wav2Lip\face_detection\detection\sfd\sfd_detector.py", line 22, in init model_weights = load_url(models_urls['s3fd']) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\VIDEO\ComfyUI_video\python_embeded\Lib\site-packages\torch\hub.py", line 770, in load_state_dict_from_url return torch.load(cached_file, map_location=map_location, weights_only=weights_only) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\VIDEO\ComfyUI_video\python_embeded\Lib\site-packages\torch\serialization.py", line 1040, in load return _legacy_load(opened_file, map_location, pickle_module, pickle_load_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\VIDEO\ComfyUI_video\python_embeded\Lib\site-packages\torch\serialization.py", line 1276, in _legacy_load typed_storage._untyped_storage._set_from_file( RuntimeError: unexpected EOF, expected 3976502 more bytes. The file might be corrupted.

whmc76 commented 1 month ago

image search on huggingface i found 3 and they are the same size

ShmuelRonen commented 1 month ago

https://huggingface.co/Nekochu/Wav2Lip/resolve/main/wav2lip_gan.pth?download=true