Improve model card: Add pipeline tag, library name, license, and update paper/code links

README.md

@@ -1,39 +1,20 @@
+---
+pipeline_tag: image-to-image
+library_name: diffusers
+license: apache-2.0
+---
 
-<div align="center">
-
-<h1>
-    Vivid-VR:<br> 
-    Distilling Concepts from Diffusion Transformer for Photorealistic Video Restoration
-</h1>
-
-<div>
-    <a href='https://csbhr.github.io/' target='_blank'>Haoran Bai</a>,&emsp;
-    <a href='https://github.com/chenxx89' target='_blank'>Xiaoxu Chen</a>,&emsp;
-    <a href='https://ieeexplore.ieee.org/author/37088928879' target='_blank'>Canqian Yang</a>,&emsp;
-    <a href='https://github.com/HeZongyao' target='_blank'>Zongyao He</a>,&emsp;
-    <a href='https://scholar.google.com/citations?user=brmDxnsAAAAJ&hl=zh-CN' target='_blank'>Sibin Deng</a>,&emsp;
-    <a href='https://scholar.google.com/citations?user=NpTmcKEAAAAJ&hl=en' target='_blank'>Ying Chen<sup>∗</sup></a>
-</div>
-<div>
-    Alibaba Group - Taobao & Tmall Group
-</div>
-<div>
-    * Corresponding author
-</div>
-
-<a href='#' target='_blank'>Paper (<span style='color:red;'>Coming soon!</span>)</a> | 
-<a href='https://csbhr.github.io/projects/vivid-vr/' target='_blank'>Project Page</a>
+# Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration
 
+[📚 Paper](https://huggingface.co/papers/2508.14483) | [🌐 Project Page](https://csbhr.github.io/projects/vivid-vr/) | [💻 Code](https://github.com/csbhr/Vivid-VR)
 
-<div style="width: 100%; text-align: center; margin:auto;">
+<div align="center">
     <img style="width:100%" src="assets/teaser.png">
 </div>
 
-For more quantitative results and visual results, go checkout our <a href="https://csbhr.github.io/projects/vivid-vr/" target="_blank">[project page]</a>
+For more quantitative results and visual results, go checkout our [project page](https://csbhr.github.io/projects/vivid-vr/)
 
 ---
-</div>
-
 
 ## 🎬 Overview
 ![overall_structure](assets/framework.png)
@@ -132,8 +113,4 @@ python VRDiT/inference.py \
 - CogVideoX1.5-5B models are distributed under the terms of the [CogVideoX License](https://huggingface.co/zai-org/CogVideoX1.5-5B/blob/main/LICENSE).
 - cogvlm2-llama3-caption models are distributed under the terms of the [CogVLM2 License](https://modelscope.cn/models/ZhipuAI/cogvlm2-video-llama3-base/file/view/master?fileName=LICENSE&status=0) and [LLAMA3 License](https://modelscope.cn/models/ZhipuAI/cogvlm2-video-llama3-base/file/view/master?fileName=LLAMA3_LICENSE&status=0).
 - Real-ESRGAN models are distributed under the terms of the [BSD 3-Clause License](https://github.com/xinntao/Real-ESRGAN/blob/master/LICENSE).
-- easyocr models are distributed under the terms of the [JAIDED.AI Terms and Conditions](https://www.jaided.ai/terms/).
-
-
-
-
+- easyocr models are distributed under the terms of the [JAIDED.AI Terms and Conditions](https://www.jaided.ai/terms/).