Improve model card metadata and add HF paper link

README.md

@@ -1,27 +1,28 @@
 ---
+base_model: runwayml/stable-diffusion-inpainting
+datasets:
+- zhengchong/DressCode-MR
+- zhengchong/DressCode-Test
+- zhengchong/VITON-HD
 language:
 - en
-thumbnail: "https://raw.githubusercontent.com/Zheng-Chong/FastFit/main/assets/img/dataset.png"
+license: other
+metrics:
+- fid
+- ssim
+- lpips
+pipeline_tag: image-to-image
+library_name: diffusers
 tags:
 - virtual-try-on
 - diffusion
 - stable-diffusion
 - multi-reference
-- image-to-image
 - computer-vision
 - comfyui
 - gradio
 - aigc
-license: "other"
-datasets:
-- zhengchong/DressCode-MR
-- zhengchong/DressCode-Test
-- zhengchong/VITON-HD
-metrics:
-- fid
-- ssim
-- lpips
-base_model: "runwayml/stable-diffusion-inpainting"
+thumbnail: https://raw.githubusercontent.com/Zheng-Chong/FastFit/main/assets/img/dataset.png
 ---
 
 <h1 align="center"> FastFit: Accelerating Multi-Reference Virtual Try-On via Cacheable Diffusion Models </h1>
@@ -30,6 +31,9 @@ base_model: "runwayml/stable-diffusion-inpainting"
 
 
  <div align="center">
+  <a href="https://huggingface.co/papers/2508.20586" style="margin: 0 2px; text-decoration: none;">
+    <img src='https://img.shields.io/badge/Paper-2508.20586-blue?style=flat&logo=HuggingFace&logoColor=blue' alt='HF Paper'>
+  </a>
   <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>
@@ -188,8 +192,8 @@ python eval.py \
 ```
 
 ## 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!
+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/main/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).