https://t.co/AqWz06w4OU ByteDance open source SOTA lip-sync model LatentSync: Audio Conditioned Latent Diffusion Models for Lip Sync. This could literally replace every news anchor or news reporter. And its already there.
— Chubby♨️ (@kimmonismus) Jan 4, 2025
from Twitter https://twitter.com/kimmonismus
January 04, 2025 at 04:00PM
via IFTTT
No comments:
Post a Comment