deepgeek/MuseTalk
2
0
Fork 0
mirror of https://github.com/TMElyralab/MuseTalk.git synced 2026-02-05 09:59:18 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Octpus
2025-04-02 11:51:04 +08:00
committed by GitHub
parent 7f258556b2
commit fbe6a97dff
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -23,7 +23,9 @@ We introduce `MuseTalk`, a **real-time high quality** lip-syncing model (30fps+
## 🔥 Updates ## 🔥 Updates
We're excited to unveil MuseTalk 1.5. We're excited to unveil MuseTalk 1.5.
This version **(1)** integrates training with perceptual loss, GAN loss, and sync loss, significantly boosting its overall performance. **(2)** We've implemented a two-stage training strategy and a spatio-temporal data sampling approach to strike a balance between visual quality and lip-sync accuracy. This version **(1)** integrates training with perceptual loss, GAN loss, and sync loss, significantly boosting its overall performance. **(2)** We've implemented a two-stage training strategy and a spatio-temporal data sampling approach to strike a balance between visual quality and lip-sync accuracy.
Learn more details [here](https://arxiv.org/abs/2410.10122) Learn more details [here](https://arxiv.org/abs/2410.10122).
The inference code and model weights of MuseTalk 1.5 are now available, with the training code set to be released soon.
Stay tuned! 🚀
# Overview # Overview
`MuseTalk` is a real-time high quality audio-driven lip-syncing model trained in the latent space of `ft-mse-vae`, which `MuseTalk` is a real-time high quality audio-driven lip-syncing model trained in the latent space of `ft-mse-vae`, which