Image
Florence-2 Referring-Expression Segmentation
Select an image region using a referring expression with Florence-2 segmentation.
- Image editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Florence-2 Referring-Expression Segmentation. Review your own result before publishing.
A starting point.
Select an image region using a referring expression with Florence-2 segmentation. Describe which object you mean when several similar subjects are present.
Before you publish.
Compare returned polygon boundaries with the intended object. Inspect thin parts and adjacent subjects before using the selection.
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 and a locating expression in text_input, such as the object’s position and appearance.
Read results.polygons rather than treating the output as detection boxes. This operation returns region coordinates, not an automatically finished transparent cutout.
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/referring-expression-segmentation. Other modes may require different inputs.
| Input | Type | Requirement |
|---|---|---|
image_url | Text | Required |
text_input | 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 Referring-Expression Segmentation through the API.
Start with this model ID for the endpoint featured on this page:
florence-2-large/referring-expression-segmentation
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.