Improve model card: Add pipeline tag, library, links, abstract, and usage

This PR significantly enhances the model card for MimicMotion by:
- Adding `pipeline_tag: image-to-video`, ensuring the model is discoverable under the correct pipeline on the Hub.
- Adding `library_name: diffusers`, which enables the "Use in Diffusers" widget and automatic loading snippets.
- Including a direct link to the paper ([MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance](https://huggingface.co/papers/2406.19680)).
- Adding a link to the official project page ([https://tencent.github.io/MimicMotion](https://tencent.github.io/MimicMotion)).
- Adding a link to the GitHub repository ([https://github.com/Tencent/MimicMotion](https://github.com/Tencent/MimicMotion)).
- Expanding the introduction with a summary of the paper's abstract for better understanding.
- Incorporating a visual overview of the model architecture.
- Providing a detailed "Sample Usage" section based on the project's Quickstart guide, making it easier for users to get started.

README.md

@@ -1,11 +1,91 @@
 ---
 license: other
+pipeline_tag: image-to-video
+library_name: diffusers
 ---
 
-## Introduction
+# MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
 
-Here are the model weights of *MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance*.
+This repository contains the model weights for **MimicMotion**, a controllable video generation framework proposed in the paper [MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance](https://huggingface.co/papers/2406.19680).
+
+MimicMotion addresses significant challenges in video generation, such as controllability, video length, and richness of details. Our approach introduces several innovations:
+-   **Confidence-aware pose guidance:** Ensures high frame quality and temporal smoothness.
+-   **Regional loss amplification:** Significantly reduces image distortion based on pose confidence.
+-   **Progressive latent fusion strategy:** Enables generation of arbitrary length videos with acceptable resource consumption.
+
+With extensive experiments and user studies, MimicMotion demonstrates significant improvements over previous approaches in various aspects.
+
+**[\ud83d\udcda Paper](https://huggingface.co/papers/2406.19680)** | **[\ud83c\udf10 Project Page](https://tencent.github.io/MimicMotion)** | **[\ud83d\udcbb GitHub Repo](https://github.com/Tencent/MimicMotion)**
+
+<div align="center">
+  <img src="https://huggingface.co/tencent/MimicMotion/resolve/main/assets/figures/model_structure.png" alt="MimicMotion Model Architecture" width="640"/>
+  <br/>
+  <i>An overview of the framework of MimicMotion.</i>
+</div>
+
+## Sample Usage
+
+For the initial released version of the model checkpoint, it supports generating videos with a maximum of 72 frames at a 576x1024 resolution. If you encounter insufficient memory issues, you can appropriately reduce the number of frames.
+
+### Environment setup
+
+Recommend python 3+ with torch 2.x are validated with an Nvidia V100 GPU. Follow the command below to install all the dependencies of python:
+
+```bash
+conda env create -f environment.yaml
+conda activate mimicmotion
+```
+
+### Download weights
+If you experience connection issues with Hugging Face, you can utilize the mirror endpoint by setting the environment variable: `export HF_ENDPOINT=https://hf-mirror.com`.
+Please download weights manually as follows:
+```bash
+cd MimicMotions/
+mkdir models
+```
+1. Download DWPose pretrained model: [dwpose](https://huggingface.co/yzd-v/DWPose/tree/main)
+    ```bash
+    mkdir -p models/DWPose
+    wget https://huggingface.co/yzd-v/DWPose/resolve/main/yolox_l.onnx?download=true -O models/DWPose/yolox_l.onnx
+    wget https://huggingface.co/yzd-v/DWPose/resolve/main/dw-ll_ucoco_384.onnx?download=true -O models/DWPose/dw-ll_ucoco_384.onnx
+    ```
+2. Download the pre-trained checkpoint of MimicMotion from [Huggingface](https://huggingface.co/tencent/MimicMotion)
+    ```bash
+    wget -P models/ https://huggingface.co/tencent/MimicMotion/resolve/main/MimicMotion_1-1.pth
+    ```
+3. The SVD model [stabilityai/stable-video-diffusion-img2vid-xt-1-1](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1) will be automatically downloaded.
+
+Finally, all the weights should be organized in `models` as follows:
+
+```
+models/
+├── DWPose
+│   ├── dw-ll_ucoco_384.onnx
+│   └── yolox_l.onnx
+└── MimicMotion_1-1.pth
+```
+
+### Model inference
+
+A sample configuration for testing is provided as `test.yaml`. You can also easily modify the various configurations according to your needs.
+
+```bash
+python inference.py --inference_config configs/test.yaml
+```
+
+Tips: if your GPU memory is limited, try set env `PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:256`.
 
 ## License
 
-These model weights of MimicMotion are fine-tuned with the assistance of Stable Video Diffusion (SVD) Powered by Stability AI. For detailed license information, pease refer to [`LICENSE`](https://huggingface.co/tencent/MimicMotion/blob/main/LICENSE) and [`NOTICE`](https://huggingface.co/tencent/MimicMotion/blob/main/NOTICE) files.
+These model weights of MimicMotion are fine-tuned with the assistance of Stable Video Diffusion (SVD) Powered by Stability AI. For detailed license information, please refer to [`LICENSE`](https://huggingface.co/tencent/MimicMotion/blob/main/LICENSE) and [`NOTICE`](https://huggingface.co/tencent/MimicMotion/blob/main/NOTICE) files.
+
+## Citation
+
+```bibtex
+@inproceedings{zhang2025mimicmotion,
+  title={MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance},
+  author={Yuang Zhang and Jiaxi Gu and Li-Wen Wang and Han Wang and Junqi Cheng and Yuefeng Zhu and Fangyuan Zou},
+  booktitle={International Conference on Machine Learning},
+  year={2025}
+}
+```