Maintain a dedicated Hugging Face model card

README.md

@@ -8,6 +8,8 @@ tags:
 - bimamba
 ---
 
+<!-- Hugging Face model card source. Upload this file as README.md to xlt99/FlowerDance. -->
+
 <h1 align="center">🌸 FlowerDance</h1>
 <h3 align="center">MeanFlow for Efficient and Refined 3D Dance Generation</h3>
 
@@ -18,7 +20,7 @@ tags:
   <a href="https://sun-happy-ykx.github.io/FlowerDance/">
     <img src="https://img.shields.io/badge/Project_Page-FlowerDance-blue" alt="Project Page">
   </a>
-  <a href="#code">
+  <a href="https://github.com/XulongT/FlowerDance">
     <img src="https://img.shields.io/badge/Conference-ECCV%202026-orange" alt="Conference">
   </a>
   <a href="https://huggingface.co/xlt99/FlowerDance">
@@ -45,25 +47,34 @@ tags:
 
 ## 🚀 Code
 
+The complete training, evaluation, and inference code is maintained in the [GitHub repository](https://github.com/XulongT/FlowerDance).
+
 ### 🛠️ Set up the Environment
 
 To set up the necessary environment for running this project, follow the steps below:
 
-1. **Create a new conda environment**
+1. **Clone the repository**
+
+   ```bash
+   git clone https://github.com/XulongT/FlowerDance.git
+   cd FlowerDance
+   ```
+
+2. **Create a new conda environment**
 
    ```bash
    conda create -n Flower_env python=3.10
    conda activate Flower_env
    ```
 
-2. **Install PyTorch (CUDA 12.8)**
+3. **Install PyTorch (CUDA 12.8)**
 
    ```
    pip install torch==2.7.1+cu128 torchvision==0.22.1+cu128 torchaudio==2.7.1+cu128 \
        --index-url https://download.pytorch.org/whl/cu128
    ```
    
-3. **Install remaining dependencies**
+4. **Install remaining dependencies**
 
    ```bash
    pip install -r requirements.txt
@@ -73,10 +84,8 @@ To set up the necessary environment for running this project, follow the steps b
 
 ## 📦 Download Resources
 
-- Download the complete **preprocessed data archive** from [Hugging Face](https://huggingface.co/datasets/xlt99/FlowerDance-Preprocessed/resolve/main/data.7z?download=true) and extract it in the project root. The archive contains the required `./data/` directory.
-- Download the **evaluation checkpoint** from [Hugging Face](https://huggingface.co/xlt99/FlowerDance/resolve/main/train-3700.pt?download=true) and place it at `./runs/train/uniform2/weights/train-3700.pt`.
-
-The preprocessed data archive is only required for training and evaluation. The custom-music inference script can download the checkpoint automatically and does not require the dataset archive.
+- Download the complete **preprocessed data archive** from [Hugging Face](https://huggingface.co/datasets/xlt99/FlowerDance-Preprocessed/resolve/main/data.7z?download=true) and extract it so that the preprocessed files are located under `./data/`.
+- The **pretrained checkpoint** is hosted in this model repository. Custom-music inference downloads it automatically when `--checkpoint` is omitted.
 
 ---
 
@@ -94,9 +103,10 @@ FlowerDance/
     ├── requirements.txt
     ├── args.py  
     ├── EDGE.py
+    ├── train.py
+    ├── test.py
     ├── inference.py
     ├── inpaint.py
-    ├── test.py
     └── vis.py     
 ```
 ---
@@ -105,7 +115,7 @@ FlowerDance/
 
 ```bash
 export WANDB_MODE=offline
-accelerate launch train.py --batch_size 128  --epochs 4000 --feature_type baseline
+accelerate launch train.py --batch_size 128 --epochs 4000 --feature_type baseline
 ```
 ---
 
@@ -113,7 +123,7 @@ accelerate launch train.py --batch_size 128  --epochs 4000 --feature_type baseli
 
 ### 🧪 Evaluate the Model
 
-To evaluate the our model’s performance:
+To evaluate the model:
 
 ```bash
 python test.py --batch_size 128