OmniParser V2 for Pure Vision Based General GUI Agent 🔥
OmniParser is a screen parsing tool to convert general GUI screen to structured elements.
Upload image
Drop Image Here
- or -
Click to Upload
Box Threshold
↺
0.01
1
IOU Threshold
↺
0.01
1
Use PaddleOCR
Icon Detect Image Size
↺
640
1920
Submit
Image Output
Parsed screen elements