Image
Florence-2 Object Detection
Locate objects in a source image with Florence-2 object detection.
- Image editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Florence-2 Object Detection. Review your own result before publishing.
A starting point.
Locate objects in a source image with Florence-2 object detection. Use the returned labels and bounding boxes as a starting point for image review.
Before you publish.
Compare each box with the original. Check missed objects, overlapping detections and incorrect labels before using the results downstream.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Provide image_url; this operation does not need a text prompt.
Inspect results.bboxes in the returned data. Detection boxes identify regions; they are not pixel-accurate cutout masks.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for florence-2-large/object-detection. Other modes may require different inputs.
| Input | Type | Requirement |
|---|---|---|
image_url | Text | Required |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Florence-2 Object Detection through the API.
Start with this model ID for the endpoint featured on this page:
florence-2-large/object-detection
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.