Upload folder using huggingface_hub

README.md

@@ -3,7 +3,7 @@
 # 🎯 HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV 2025)
 
 [![Project Website](https://img.shields.io/badge/🌐-Project%20Website-deepgray)](https://mizzenai.github.io/HPSv3.project/)
-[![arXiv](https://img.shields.io/badge/arXiv-2411.07232-b31b1b.svg)]()
+[![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)]()
 [![ICCV 2025](https://img.shields.io/badge/ICCV-2025-blue.svg)]()
 [![Model](https://img.shields.io/badge/🤗-Model-yellow)](https://huggingface.co/MizzenAI/HPSv3)
 [![Dataset](https://img.shields.io/badge/🤗-Dataset-green)](https://huggingface.co/MizzenAI/HPDv3)
@@ -295,14 +295,14 @@ COHP uses multiple state-of-the-art diffusion models for initial generation: **F
 We perform [DanceGRPO](https://github.com/XueZeyue/DanceGRPO) as the reinforcement learning method. Here are some results.
 All experiments using the same setting and we use **Stable Diffusion 1.4** as our backbone.
 
-<div style="display: flex; justify-content: space-around; align-items: center;">
-  <div style="text-align: center;">
-    <img src="assets/rl1.jpg"  width="290"/>
-  </div>
-  <div style="text-align: center;">
-    <img src="assets/rl2.jpg" width="300"/>
-  </div>
-</div>
+<p align="center">
+  <img src="assets/rl1.jpg"  width="600"/>
+</p>
+
+<p align="center">
+  <img src="assets/rl2.jpg"  width="600"/>
+</p>
+
 
 ### More Results of HPsv3 as Reward Model (Stable Diffusion 1.4)
 <p align="center">