microsoft/omniparser-v2

OmniParser is a screen parsing tool to convert general GUI screen to structured elements.

Input
Configure the inputs for the AI model.

Input image to process

640
1920

Icon detection image size

0.01
1

Threshold for removing bounding boxes with low confidence

0.01
1

Threshold for removing bounding boxes with large overlap

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.

omniparser-v2 - ikalos.ai