deepgeek/MuseTalk
2
0
Fork 0
mirror of https://github.com/TMElyralab/MuseTalk.git synced 2026-02-04 17:39:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README and LICENSE

Browse Source
This commit is contained in:
czk32611
2024-04-26 09:24:23 +08:00
parent ef36109b06
commit 2c52de01b4
2 changed files with 142 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -266,6 +266,9 @@ As a complete solution to virtual human generation, you are suggested to first a
#### :new: Real-time inference
Here, we provide the inference script. This script first applies necessary pre-processing such as face detection, face parsing and VAE encode in advance. During inference, only UNet and the VAE decoder are involved, which makes MuseTalk real-time.
Note that in this script, the generation time is also limited by I/O (e.g. saving images).
```
python -m scripts.realtime_inference --inference_config configs/inference/realtime.yaml
```