Octpus commited on
Commit
b2750c1
·
unverified ·
1 Parent(s): 63f45c1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -23,7 +23,9 @@ We introduce `MuseTalk`, a **real-time high quality** lip-syncing model (30fps+
23
  ## 🔥 Updates
24
  We're excited to unveil MuseTalk 1.5.
25
  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.
26
- Learn more details [here](https://arxiv.org/abs/2410.10122)
 
 
27
 
28
  # Overview
29
  `MuseTalk` is a real-time high quality audio-driven lip-syncing model trained in the latent space of `ft-mse-vae`, which
 
23
  ## 🔥 Updates
24
  We're excited to unveil MuseTalk 1.5.
25
  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.
26
+ Learn more details [here](https://arxiv.org/abs/2410.10122).
27
+ The inference code and model weights of MuseTalk 1.5 are now available, with the training code set to be released soon.
28
+ Stay tuned! 🚀
29
 
30
  # Overview
31
  `MuseTalk` is a real-time high quality audio-driven lip-syncing model trained in the latent space of `ft-mse-vae`, which