OpenTalker / video-retalking

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
https://opentalker.github.io/video-retalking/
Apache License 2.0
6.02k stars 895 forks source link

New to tis but have an error stopping me can anyone hhelp? #249

Open AiBJt opened 2 weeks ago

AiBJt commented 2 weeks ago

[Info] Using cuda for inference. [Step 0] Number of frames available for inference: 822 [Step 1] Using saved landmarks. [Step 2] 3DMM Extraction In Video:: 100%|████████████████████████████████████████████| 822/822 [00:08<00:00, 97.96it/s] using expression center Load checkpoint from: checkpoints/DNet.pt Load checkpoint from: checkpoints/LNet.pth Load checkpoint from: checkpoints/ENet.pth [Step 3] Using saved stablized video. [Step 4] Load audio; Length of mel chunks: 819 [Step 5] Reference Enhancement: 14%|██████▋ | 114/819 [00:37<03:49, 3.07it/s] Traceback (most recent call last): File "C:\Users\black\Downloads\video-retalking-main\venv\lib\site-packages\gradio\queueing.py", line 407, in call_prediction output = await route_utils.call_process_api( File "C:\Users\black\Downloads\video-retalking-main\venv\lib\site-packages\gradio\route_utils.py", line 226, in call_process_api output = await app.get_blocks().process_api( File "C:\Users\black\Downloads\video-retalking-main\venv\lib\site-packages\gradio\blocks.py", line 1550, in process_api result = await self.call_function( File "C:\Users\black\Downloads\video-retalking-main\venv\lib\site-packages\gradio\blocks.py", line 1185, in call_function prediction = await anyio.to_thread.run_sync( File "C:\Users\black\Downloads\video-retalking-main\venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "C:\Users\black\Downloads\video-retalking-main\venv\lib\site-packages\anyio_backends_asyncio.py", line 2177, in run_sync_in_workerthread return await future File "C:\Users\black\Downloads\video-retalking-main\venv\lib\site-packages\anyio_backends_asyncio.py", line 859, in run result = context.run(func, args) File "C:\Users\black\Downloads\video-retalking-main\venv\lib\site-packages\gradio\utils.py", line 661, in wrapper response = f(args, **kwargs) File "C:\Users\black\Downloads\video-retalking-main\webUI.py", line 383, in inference pred, , _ = enhancer.process(img, img, face_enhance=True, possion_blending=False) File "C:\Users\black\Downloads\video-retalking-main\third_part\GPEN\gpen_face_enhancer.py", line 113, in process mask_sharp = cv2.GaussianBlur(mask_sharp, (0,0), sigmaX=1, sigmaY=1, borderType = cv2.BORDER_DEFAULT) UnboundLocalError: local variable 'mask_sharp' referenced before assignment

I have absolutely no idea what i have done wrong, It was supposed to be a standalone download that required nothing but running of a bat file, anyway thanks for any help!

AiBJt commented 2 weeks ago

Im on windows 10 let me know if you need any other info.