What is the recommend video dimension size?

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

10.18k stars 2.19k forks source link

What is the recommend video dimension size? #242

Closed MZhang88 closed 3 years ago

MZhang88 commented 3 years ago

Hi,

Every video I use for the Wav2Lip keeps telling me to resize ( --resize_factor). Can you please tell me what is the recommend video dimension size? Also, I'm new to all of this and I was wondering if you could spare a few mins and tell me how to I run the --resize_factor? I see no button for this :(. I'm novice.

Thanks

mrlogick commented 3 years ago

I'm having the same issue here: "Image too big to run face detection on GPU. Please use the --resize_factor argument"

Rudrabha commented 3 years ago

We generally recommend, 480p or 720p video as standard for this model. If you have a 1080p, please use --resize_factor 2 to get a 720p output during inference.