Improve model card with metadata, links, and usage example

This PR significantly improves the model card for "One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer" by:

- Integrating the `pipeline_tag: image-to-video` to correctly categorize the model for better discoverability on the Hugging Face Hub.
- Adding `library_name: diffusers`, which enables the automatic "how to use" widget on the model page due to its compatibility with the Diffusers library.
- Including direct links to the paper ([https://huggingface.co/papers/2511.22940](https://huggingface.co/papers/2511.22940)), project page ([https://ssj9596.github.io/one-to-all-animation-project/](https://ssj9596.github.io/one-to-all-animation-project/)), and the GitHub repository ([https://github.com/ssj9596/One-to-All-Animation](https://github.com/ssj9596/One-to-All-Animation)).
- Adding a "Quick Inference" section with a code snippet directly sourced from the official GitHub README to provide immediate usability instructions.
- Incorporating "Highlights", "Showcase" with visual examples, and "Dependencies and Installation" sections for comprehensive information.

Please review and merge this PR if everything looks good.

README.md

@@ -1,3 +1,101 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: image-to-video
+library_name: diffusers
+---
+
+# One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer
+
+[🌐 Project Page](https://ssj9596.github.io/one-to-all-animation-project/) | [📄 Paper](https://huggingface.co/papers/2511.22940) | [💻 Code](https://github.com/ssj9596/One-to-All-Animation)
+
+This repository contains the model and code for "One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer." We present a unified framework for high-fidelity character animation and image pose transfer for references with arbitrary layouts. This work reformulates training as a self-supervised outpainting task, designs a reference extractor for comprehensive identity feature extraction, integrates hybrid reference fusion attention, and introduces identity-robust pose control and a token replace strategy for coherent long-video generation.
+
+## 🌟 Highlights
+
+We provide a **complete and reproducible** training and evaluation pipeline:
+
+- ✅ **Full Training Code**: Three-stage progressive training from scratch
+- ✅ **Complete Benchmarks**: Reproduction code and pre-trained checkpoints
+- ✅ **Flexible Training Codebase**: Multi-resolution, multi-aspect-ratio, and multi-frame training codebase
+- ✅ **Datasets**: Pre-processed open-source datasets + self-collected cartoon data
+
+## 🎭 Showcase - 1.3B Model Results
+
+<p align="center">
+  <img src="https://github.com/ssj9596/One-to-All-Animation/raw/main/assets/combined_video1.gif" height="300"/> &nbsp;&nbsp; <img src="https://github.com/ssj9596/One-to-All-Animation/raw/main/assets/combined_video2.gif" height="300"/>
+</p>
+
+## 🔧 Dependencies and Installation
+
+1. Clone Repo
+    ```bash
+    git clone https://github.com/ssj9596/One-to-All-Animation.git
+    cd One-to-All-Animation
+    ```
+
+2. Create Conda Environment and Install Dependencies
+    ```bash
+    # create new conda env
+    conda create -n one-to-all python=3.12
+    conda activate one-to-all
+
+    # install pytorch
+    pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/cu124
+    # or
+    pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 -i https://mirrors.aliyun.com/pypi/simple/
+
+    # install python dependencies
+    pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
+
+
+    # (Recommended) install flash attention 3 (or 2) from source:
+    # https://github.com/Dao-AILab/flash-attention
+    ```
+
+3. Download Models
+
+   - Download pretrained models
+   ```bash
+    cd ./pretrained_models 
+    bash download_pretrained_models.py
+    ```
+
+   - Download checkpoints
+    ```bash
+    cd ./checkpoints
+    bash download_checkpoints.py
+    ```
+
+    > 💡 **Tip**: Edit the script and uncomment the specific models you want to download.
+    > - **1.3B_1**: Best performance on video benchmark among 1.3B models (paper results).
+    > - **1.3B_2**: Further trained on v1 with large camera movement data and increased image ratio. Better for dynamic video generation. Best on image benchmark (paper results). 
+    > - **14B**: Best overall performance among 14B models (paper results).
+
+## ☕️ Quick Inference
+
+We provide several examples in the [`examples`](https://github.com/ssj9596/One-to-All-Animation/tree/main/examples) folder. 
+Run the following commands to try it out:
+
+```bash
+# Step 1: Prepare model input
+cd video-generation
+python infer_preprocess.py
+
+# Step 2: Run inference with your preferred model
+python inference_1.3b.py  # For 1.3B model
+# or
+python inference_14b.py   # For 14B model
+```
+You can enter the script to modify the input path.
+
+## 📚 Citation
+If you find **One-to-All Animation** useful, consider citing our work:
+
+```bibtex
+@inproceedings{shi2025onetoall,
+  title={One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer},
+  author={Shi, Shijun and Xu, Jing and Li, Zhihang and Peng, Chunli and Yang, Xiaoda and Lu, Lijing and Hu, Kai and Zhang, Jiangning},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year={2025}
+}
+```