Skip to content

[CVPR 2026] PersonaLive! : Expressive Portrait Image Animation for Live Streaming

update readme.md

Zhiyuan Lib374bf4914fc
diff --git a/README.md b/README.md
index f59168c..ed89393 100644
--- a/README.md
+++ b/README.md
@@ -17,7 +17,7 @@
## πŸ“‹ TODO
- [ ] If you find PersonaLive useful or interesting, please give us a Star🌟! Your support drives us to keep improving.
- [ ] Fix bugs (If you encounter any issues, please feel free to open an issue or contact me! πŸ™)
-- [ ] Release `training code`.
+- [x] Release `training code`.
- [x] **[2026.02.21]** πŸ₯³ PersonaLive is accepted by CVPR2026 πŸŽ‰.
- [x] **[2025.12.29]** πŸ”₯ Enhance WebUI (Support reference image replacement).
- [x] **[2025.12.22]** πŸ”₯ Supported streaming strategy in offline inference to generate long videos on 12GB VRAM!
@@ -130,6 +130,9 @@ Converting the model to TensorRT can significantly speed up inference (~ 2x ⚑
# Install packages with pip
pip install -r requirements_trt.txt
+# src/models/motion_encoder/FAN_temporal_feature_extractor.py
+self.pos_embed.pos_embed.requires_grad = False
+
# Converting the model to TensorRT
python torch2trt.py
```