lucataco/florence-2-base 🖼️❓📝 → ❓
About
Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
Example Output
Output
{"text":"{'<CAPTION>': 'A green car parked in front of a yellow building.'}"}
Performance Metrics
0.82s
Prediction Time
69.52s
Total Time
All Input Parameters
{
"image": "https://replicate.delivery/pbxt/L9z39PBucXIWQM8fgd1M5XQdiGDWpD07EUdMuncsCVim9YQb/car.jpg",
"task_input": "Caption"
}
Input Parameters
- image (required)
- Grayscale input image
- task_input
- Input task
- text_input
- Text Input(Optional)
Output Schema
- img
- Img
- text
- Text
Version Details
- Version ID
c81609117f666d3a86b262447f80d41ac5158a76adb56893301843a23165eaf8- Version Created
- June 25, 2024