Image
Florence-2 Region Proposals
Find candidate regions in an image with Florence-2 region proposals.
- Image editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Florence-2 Region Proposals. Review your own result before publishing.
A starting point.
Find candidate regions in an image with Florence-2 region proposals. Use them to plan further inspection rather than assuming each proposal is a confirmed object.
Before you publish.
Review overlapping and empty regions against the source. Choose only useful proposals for the next step of your workflow.
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 require a text query.
Inspect results.bboxes and their coordinates. Region proposals are candidate selections, not precise masks or verified object classifications.
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/region-proposal. 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 Region Proposals through the API.
Start with this model ID for the endpoint featured on this page:
florence-2-large/region-proposal
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.