Update README.md

README.md

@@ -1,5 +1,13 @@
 ---
 license: mit
+language:
+- en
+- zh
+base_model:
+- Wan-AI/Wan2.2-I2V-A14B
+tags:
+- video
+- generation
 ---
 [![arXiv](https://img.shields.io/badge/arXiv-2511.12578-b31b1b.svg)](https://arxiv.org/abs/2511.12578)
 [![Project Page](https://img.shields.io/badge/Project_Page-green)](https://scottykma.github.io/tempomaster-gitpage/)
@@ -8,4 +16,4 @@ TempoMaster is a video diffusion model built on Wan-Video, which is capable of g
 
 The model first generates a low-frame-rate video as a global blueprint. It then uses the existing frames as temporal anchors to infer and insert additional frames in between, progressively upsampling the video to higher frame rates.
 
-This approach effectively structures long-term temporal dynamics and mitigates the issue of visual drifting caused by error accumulation.
+This approach effectively structures long-term temporal dynamics and mitigates the issue of visual drifting caused by error accumulation.