numz / sd-wav2lip-uhq

Wav2Lip UHQ extension for Automatic1111
Apache License 2.0
1.16k stars 158 forks source link

How much time do you need to lip sync a 10 sec or 1 minute video? #89

Open AIhasArrived opened 8 months ago

AIhasArrived commented 8 months ago

I have been trying the last days with both wav2lip HD (not in auto) and retalker, and found that both are slow and very GPU consuming. I would like to know everyone of you HOW MUCH GPU do you use (what card) and HOW MUCH time does it take for you to do it? What kind of videos/animations are you lip syncing and for how long? (How much time to train X seconds/minutes?)

Please contribute. Because I am about to drop this technology and give up on it, maybe others peoples experiences will give me hope. Maybe this repo is faster? (could not try it yet I need to debug it)

APCOTech commented 8 months ago

I my post here https://github.com/numz/sd-wav2lip-uhq/issues/86#issuecomment-1802740305 .. it took less than 6 minutes for faceswap and wav2lip to complete that 3 seconds video... longer videos will take more but not much, it never exceeded 14 minutes for 1 minute videos with me (laptop rtx 4080 12GB) and (laptop rtx 3080 16GB)

AIhasArrived commented 8 months ago

14 minutes for 1 minute video, ok noted I will try it. I should be able to do it 10 minutes Meaning a video of 10 minutes can be done in 100 minutes lol Thanks for the response. Now i need to fix the bark think (so many things to do, this bark thing really is blocking, hope the fix is simple)