search

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
6.44k stars 953 forks source link

No face detected in this image, mask sharp .. UnboundLocalError: local variable 'mask_sharp' referenced before assignment (HELP) #165

Closed AIhasArrived closed 10 months ago

AIhasArrived commented 10 months ago

Hello I tried an HD video with a person that talks during all the video, but it keeps saying: "no face detected in this image"!! I don't understand. Is it related to the type of file and their encoding maybe? (audio and video)

Error in the end:

....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

Screenshot: image

AIhasArrived commented 10 months ago

Found solution here: https://github.com/OpenTalker/video-retalking/issues/14