search

ShmuelRonen / VideoReTalking-HQ

VideoReTalking-HQ is a high-quality video retalking tool for enhancing and synchronizing video frames with audio inputs using advanced face enhancement techniques, including GFPGAN, and expression control.
15 stars 3 forks source link

Hi Shmuel, maybe you can help with a bug? #1

Open gilushon opened 2 weeks ago

gilushon commented 2 weeks ago

Hi Shmuel, I downloaded video-Retalking and followed all the steps, but i am getting an error, maybe you can help in this matter? I included a picture of the error.

Capture

And this is the log (base) C:\WINDOWS\system32>cd C:\VideoReTalking-HQ-main

(base) C:\VideoReTalking-HQ-main>dir Volume in drive C has no label. Volume Serial Number is 883D-7D36

Directory of C:\VideoReTalking-HQ-main

08/06/2024 09:23

. 08/06/2024 09:23 .. 08/06/2024 09:23 3,139 .gitignore 08/06/2024 09:23 3,776 app.py 27/06/2024 15:17 checkpoints 08/06/2024 09:23 examples 08/06/2024 09:23 16,955 inference.py 08/06/2024 09:23 models 08/06/2024 09:23 5,360 README.md 08/06/2024 09:23 165 requirements.txt 08/06/2024 09:23 results 08/06/2024 09:23 68 start.bat 08/06/2024 09:23 temp 08/06/2024 09:23 third_part 08/06/2024 09:23 utils 6 File(s) 29,463 bytes 9 Dir(s) 1,134,921,420,800 bytes free

(base) C:\VideoReTalking-HQ-main>start.bat

(base) C:\VideoReTalking-HQ-main>call conda activate video_retalking Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Exception in callback _ProactorBasePipeTransport._call_connection_lost(None) handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)> Traceback (most recent call last): File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\asyncio\events.py", line 81, in _run self._context.run(self._callback, *self._args) File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\asyncio\proactor_events.py", line 162, in _call_connection_lost self._sock.shutdown(socket.SHUT_RDWR) ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host Traceback (most recent call last): File "inference.py", line 13, in from third_part.GPEN.gpen_face_enhancer import FaceEnhancement File "C:\VideoReTalking-HQ-main\third_part\GPEN\gpen_face_enhancer.py", line 11, in from face_model.face_gan import FaceGAN File "C:\VideoReTalking-HQ-main\third_part/GPEN\face_model\face_gan.py", line 13, in from face_model.gpen_model import FullGenerator File "C:\VideoReTalking-HQ-main\third_part/GPEN\face_model\gpen_model.py", line 16, in from face_model.op import FusedLeakyReLU, fused_leaky_relu, upfirdn2d File "C:\VideoReTalking-HQ-main\third_part/GPEN\face_model\op__init__.py", line 1, in from .fused_act import FusedLeakyReLU, fused_leaky_relu File "C:\VideoReTalking-HQ-main\third_part/GPEN\face_model\op\fused_act.py", line 8, in from torch.utils.cpp_extension import load, _import_module_from_library File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\torch\utils\cpp_extension.py", line 23, in from pkg_resources import packaging # type: ignore[attr-defined] ImportError: cannot import name 'packaging' from 'pkg_resources' (C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\pkg_resources__init__.py) Traceback (most recent call last): File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\gradio\queueing.py", line 541, in process_events response = await route_utils.call_process_api( File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\gradio\route_utils.py", line 276, in call_process_api output = await app.get_blocks().process_api( File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\gradio\blocks.py", line 1938, in process_api data = await self.postprocess_data(block_fn, result["prediction"], state) File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\gradio\blocks.py", line 1763, in postprocess_data outputs_cached = await processing_utils.async_move_files_to_cache( File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\gradio\processing_utils.py", line 485, in async_move_files_to_cache return await client_utils.async_traverse( File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\gradio_client\utils.py", line 1003, in async_traverse new_obj[key] = await async_traverse(value, func, is_root) File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\gradio_client\utils.py", line 999, in async_traverse return await func(json_obj) File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\gradio\processing_utils.py", line 460, in _move_to_cache temp_file_path = await block.async_move_resource_to_block_cache( File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\gradio\blocks.py", line 294, in async_move_resource_to_block_cache temp_file_path = processing_utils.save_file_to_cache( File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\gradio\processing_utils.py", line 250, in save_file_to_cache temp_dir = hash_file(file_path) File "C:\Users\sg1_a\anaconda3\envs\video_retalking\lib\site-packages\gradio\processing_utils.py", line 182, in hash_file with open(file_path, "rb") as f: PermissionError: [Errno 13] Permission denied: 'C:\VideoReTalking-HQ-main'

ShmuelRonen commented 1 week ago

It's probably because the video input file recognition problem