Add model card metadata

README.md

@@ -1,3 +1,9 @@
+---
+license: mit
+library_name: diffusers
+pipeline_tag: text-to-video
+---
+
 # AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset
 
 This repository contains the pre-trained weights of [AccVideo](https://arxiv.org/abs/2503.19462). AccVideo is a novel efficient distillation method to accelerate video diffusion models with synthetic datset. Our method is 8.5x faster than HunyuanVideo.
@@ -83,4 +89,4 @@ If you find [AccVideo](https://arxiv.org/abs/2503.19462) useful for your researc
 ```
 
 ## Acknowledgements
-The code is built upon [FastVideo](https://github.com/hao-ai-lab/FastVideo) and [HunyuanVideo](https://github.com/Tencent/HunyuanVideo), we thank all the contributors for open-sourcing. 
+The code is built upon [FastVideo](https://github.com/hao-ai-lab/FastVideo) and [HunyuanVideo](https://github.com/Tencent/HunyuanVideo), we thank all the contributors for open-sourcing.