Add metadata and improve model card

README.md

@@ -1,3 +1,9 @@
+---
+pipeline_tag: image-to-video
+library_name: diffusers
+license: apache-2.0
+---
+
 <div align ="center">
 <h1> Proteus-ID </h1>
 <h3> Proteus-ID: ID-Consistent and Motion-Coherent Video Customization </h3>
@@ -8,6 +14,12 @@
 [![arXiv](https://img.shields.io/badge/arXiv-2506.23729-b31b1b.svg)](https://arxiv.org/abs/2506.23729)&nbsp;
 </div>
 
+**Proteus-ID** is a novel diffusion-based framework for identity-consistent and motion-coherent video customization. It addresses the challenges of maintaining subject identity while generating fluid, natural motion by introducing:
+
+- **Multimodal Identity Fusion (MIF)**: Unifies visual and textual cues into a joint identity representation.
+- **Time-Aware Identity Injection (TAII)**: Dynamically modulates identity conditioning across denoising steps for fine-detail reconstruction.
+- **Adaptive Motion Learning (AML)**: Enhances motion realism using optical-flow-derived heatmaps.
+
 Authors: [Guiyu Zhang](https://grenoble-zhang.github.io/)<sup>1</sup>, [Chen Shi](https://scholar.google.com.hk/citations?user=o-K_AoYAAAAJ&hl=en)<sup>1</sup>, Zijian Jiang<sup>1</sup>, Xunzhi Xiang<sup>2</sup>, Jingjing Qian<sup>1</sup>, [Shaoshuai Shi](https://shishaoshuai.com/)<sup>3</sup>, [Li Jiang†](https://llijiang.github.io/)<sup>1</sup>
 
 <sup>1</sup> The Chinese University of Hong Kong, Shenzhen&emsp;<sup>2</sup> Nanjing University&emsp;
@@ -25,8 +37,7 @@ Authors: [Guiyu Zhang](https://grenoble-zhang.github.io/)<sup>1</sup>, [Chen Shi
 ```bash
 # 0. Clone the repo
 git clone --depth=1 https://github.com/grenoble-zhang/Proteus-ID.git
-
-cd /nfs/dataset-ofs-voyager-research/guiyuzhang/Opensource/code/Proteus-ID-main
+cd Proteus-ID
 
 # 1. Create conda environment
 conda create -n proteusid python=3.11.0
@@ -89,4 +100,4 @@ If you find our work useful in your research, please consider citing our paper:
 
 ## Acknowledgement
 
-Thansk for these excellent opensource works and models: [CogVideoX](https://github.com/THUDM/CogVideo); [ConsisID](https://github.com/PKU-YuanGroup/ConsisID); [diffusers](https://github.com/huggingface/diffusers).
+Thanks for these excellent opensource works and models: [CogVideoX](https://github.com/THUDM/CogVideo); [ConsisID](https://github.com/PKU-YuanGroup/ConsisID); [diffusers](https://github.com/huggingface/diffusers).