Update README.md

This commit is contained in:
leigest519
2025-07-29 20:01:38 +08:00
committed by GitHub
parent c4034a9e83
commit 442d226752

View File

@@ -15,6 +15,15 @@ Michael R. Lyu<sup>2</sup>, Xiangyu Yue<sup>1✉</sup>
</div> </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 ## Demo Videos
A showcase of how **ScreenCoder** transforms UI screenshots into structured, editable HTML/CSS code using a modular multi-agent framework. 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. 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 ## Project Structure
- `main.py`: The main script to generate final HTML code for a single screenshot. - `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. - `UIED/`: Contains the UIED (UI Element Detection) engine for analyzing screenshots and detecting components.