Image
Florence-2 OCR with Regions
Read text from an image together with its detected regions.
- Image editing
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Florence-2 OCR with Regions. Review your own result before publishing.
A starting point.
Read text from an image together with its detected regions. Use the region output to relate recognized words to their location in the source.
Before you publish.
Check names, numbers and punctuation against the original. Small lettering, rotation or a complex background can lead to omissions; OCR output needs review before reuse.
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. Inspect the returned text labels and region coordinates together; check the output schema before using them in an application.
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/ocr-with-region. 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 OCR with Regions through the API.
Start with this model ID for the endpoint featured on this page:
florence-2-large/ocr-with-region
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.