Update README.md

README.md

@@ -23,14 +23,15 @@ metrics:
 - lpips
 base_model: "runwayml/stable-diffusion-inpainting"
 ---
+
 <h1 align="center"> FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models </h1>
 
 <p align="center" style="font-size: 18px;">Supported by <a href="https://lavieai.com/">LavieAI</a> and <a href="https://www.loomlyai.com/en">LoomlyAI</a></p>            
 
 
  <div align="center">
-  <a href="https://github.com/Zheng-Chong/FastFit" style="margin: 0 2px; text-decoration: none;">
-    <img src='https://img.shields.io/badge/arXiv-TODO-red?style=flat&logo=arXiv&logoColor=red' alt='arxiv'>
+  <a href="https://arxiv.org/abs/2508.20586" style="margin: 0 2px; text-decoration: none;">
+    <img src='https://img.shields.io/badge/arXiv-2508.20586-red?style=flat&logo=arXiv&logoColor=red' alt='arxiv'>
   </a>
   <a href='https://huggingface.co/zhengchong/FastFit-MR-1024' style="margin: 0 2px; text-decoration: none;">
     <img src='https://img.shields.io/badge/Hugging Face-ckpts-orange?style=flat&logo=HuggingFace&logoColor=orange' alt='huggingface'>
@@ -41,9 +42,6 @@ base_model: "runwayml/stable-diffusion-inpainting"
   <a href="https://fastfit.lavieai.com" style="margin: 0 2px; text-decoration: none;">
     <img src='https://img.shields.io/badge/Demo-Gradio-gold?style=flat&logo=Gradio&logoColor=red' alt='Demo'>
   </a>
-  <a href='https://zheng-chong.github.io/FastFit/' style="margin: 0 2px;">
-    <img src='https://img.shields.io/badge/Webpage-Project-silver?style=flat&logo=&logoColor=orange' alt='webpage'>
-  </a>
   <a href="https://github.com/Zheng-Chong/FastFit/tree/main" style="margin: 0 2px; text-decoration: none;">
     <img src='https://img.shields.io/badge/License-NonCommercial-lightgreen?style=flat&logo=Lisence' alt='License'>
   </a>
@@ -54,6 +52,7 @@ base_model: "runwayml/stable-diffusion-inpainting"
 FastFit is a diffusion-based framework optimized for **high-speed**, **multi-reference virtual try-on**. It enables **simultaneous try-on of multiple fashion items**—such as **tops, bottoms, dresses, shoes, and bags**—on a single person. The framework leverages **reference KV caching** during inference to **significantly accelerate generation**.
  
 ## Updates 
+- **`2025/08/29`**: 📄 We release the [arXiv paper](https://arxiv.org/abs/2508.20586) of FastFit!
 - **`2025/08/06`**: ⚙️ We release [the code for inference and evaluation](https://github.com/Zheng-Chong/FastFit/tree/main?tab=readme-ov-file#inference--evaluation-on-datasets) on the [DressCode-MR](https://huggingface.co/datasets/zhengchong/DressCode-MR), [DressCode](https://huggingface.co/datasets/zhengchong/DressCode-Test), and [VITON-HD](https://huggingface.co/datasets/zhengchong/VITON-HD) test datasets.
 - **`2025/08/05`**: 🧩 We release the [ComfyUI workflow](https://github.com/Zheng-Chong/FastFit/releases/tag/comfyui) for FastFit!
 - **`2025/08/04`**: 🚀 Our [gradio demo](https://fastfit.lavieai.com) is online with Chinese & English support!  The code of the demo is also released in [app.py](app.py).
@@ -174,15 +173,23 @@ python eval.py \
 
 - `--paired`: Include this flag to evaluate results from the paired setting. Omit this flag for the unpaired setting.
 
-<!-- ## Citation
+## Citation
 
 ```bibtex
-
-``` -->
+@misc{chong2025fastfitacceleratingmultireferencevirtual,
+      title={FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models}, 
+      author={Zheng Chong and Yanwei Lei and Shiyue Zhang and Zhuandi He and Zhen Wang and Xujie Zhang and Xiao Dong and Yiling Wu and Dongmei Jiang and Xiaodan Liang},
+      year={2025},
+      eprint={2508.20586},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2508.20586}, 
+}
+```
 
 ## Acknowledgement
 Our code is modified based on [Diffusers](https://github.com/huggingface/diffusers). We adopt [Stable Diffusion v1.5 inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting) as the base model. We use a modified [AutoMasker](https://github.com/Zheng-Chong/CatVTON/blob/edited/model/cloth_masker.py) to automatically generate masks in our [Gradio](https://github.com/gradio-app/gradio) App and [ComfyUI](https://github.com/comfyanonymous/ComfyUI) workflow. Thanks to all the contributors!
 
 ## License
 
-All weights, parameters, and code related to FastFit are governed by the [FastFit Non-Commercial License](https://github.com/Zheng-Chong/FastFit/tree/main). For commercial collaboration, please contact [LavieAI](https://lavieai.com/) or [LoomlyAI](https://www.loomlyai.com/en).
+All weights, parameters, and code related to FastFit are governed by the [FastFit Non-Commercial License](https://github.com/Zheng-Chong/FastFit/tree/main). For commercial collaboration, please contact [LavieAI](https://lavieai.com/) or [LoomlyAI](https://www.loomlyai.com/en).