search

Rudrabha / Wav2Lip

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs
https://synclabs.so
10.28k stars 2.21k forks source link

What files need to be modified for training HD #220

Closed wowopc closed 3 years ago

wowopc commented 3 years ago

Modify the file hparam img_size=96，increase ?264？ fps=25， Where is the neural network architecture modified ？

wowopc commented 3 years ago

Modify file wav2lip.py ？ If I need to train a 960*540 video, how do I set it up?

wowopc commented 3 years ago

Change the model architecture to accommodate more high-resolution faces How to modify?

prajwalkr commented 3 years ago

Training on high resolution videos needs a lot of changes, and it is a work in progress from our side.

burning846 commented 2 years ago

Training on high resolution videos needs a lot of changes, and it is a work in progress from our side.

any progress？