Wav2Lip
Wav2Lip copied to clipboard
The output video have clear box around mouth region.
Hi, I have tried the library its an exceptional work. I am doing inference but facing an issue regarding the output. The output generated have some boxy effect around the mouth. Is there any way to remove it ?
It seems like adjusting resize_factor argument to get a lower resolution video can make the box less obvious,but also blur the whole result video...
Hi @rohaantahir ,
I also met the same question, have you solved it?
@liuquande no the issue is with their model. It is trained on low resolution that is why bounding box is created.
You can change the network topology to work with 256x256 or 512x512 resolution and train it from scratch
change img_size from 96 to 256 or 512?
change img_size from 96 to 256 or 512?
that just causes errors because the model is expecting 96 so when i change it to 256 it throws the architecture off.
really looking for a fix as the video output quality is pretty bad with that blurry rectangle that appears over the modified portion of the image
Would fine-tune the model resolve this issue? How to do that?
@1800dinky I'm pretty sure they do it on purpose