From 442d226752f4f87dcd292c566afe361ab33aacd2 Mon Sep 17 00:00:00 2001
From: leigest519 <57628855+leigest519@users.noreply.github.com>
Date: Tue, 29 Jul 2025 20:01:38 +0800
Subject: [PATCH] Update README.md

---
 README.md | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/README.md b/README.md
index a7227fc..1c567e4 100644
--- a/README.md
+++ b/README.md
@@ -15,6 +15,15 @@ Michael R. Lyu<sup>2</sup>, Xiangyu Yue<sup>1✉</sup>
   
 </div>
 
+## Huggingface Demo
+- Try our huggingface demo at [Demo](https://huggingface.co/spaces/Jimmyzheng-10/ScreenCoder)
+
+- Run the demo locally (download from huggingface space):
+
+  ```bash
+  python app.py
+  ```
+  
 ## Demo Videos
 
 A showcase of how **ScreenCoder** transforms UI screenshots into structured, editable HTML/CSS code using a modular multi-agent framework.
@@ -45,15 +54,6 @@ We present qualitative examples to illustrate the improvements achieved by our m
 
 As shown above, our method produces results that are more accurate, visually aligned, and semantically faithful to the original design.
 
-### Demo
-- Try our huggingface demo at [Demo](https://huggingface.co/spaces/Jimmyzheng-10/ScreenCoder)
-
-- Run the demo locally (download from huggingface space):
-
-  ```bash
-  python app.py
-  ```
-
 ## Project Structure
 - `main.py`: The main script to generate final HTML code for a single screenshot.
 - `UIED/`: Contains the UIED (UI Element Detection) engine for analyzing screenshots and detecting components.