Florence-2 - Vision Foundation Model
Parameters
Image
Upload image
Model
Florence-2 Large (Best Quality)
Florence-2 Base (Faster)
Florence-2 Large Fine-tuned
Florence-2 Base Fine-tuned
Task
Caption - Generate Description
OCR - Extract Text
Detect - Object Detection
Open Vocab - Detect Custom Classes
Ground - Locate Phrases in Caption
Dense Caption - Multi-region Descriptions
Generate image captions with varying detail levels
Detail Level
Brief
Normal
Detailed
Run Task
Results
Upload an image and run a task