Spaces:
Configuration error
Configuration error
Octpus
commited on
Update README.md
Browse files
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
|