Available now

Florence-2 OCR with Regions: text reading with regions

Florence-2 OCR with Regions reads the text in an image and marks where each piece of it sits.

Model ID

Input

Fields marked * are required. Review the price before generating.

The image to be processed.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Price$0.60 / run

You sign up first. Your settings are kept.

About this model

Overview

Upload an image with text in it, such as a sign, a receipt or a screenshot. Microsoft's Florence-2 returns the image with a box around each piece of text it reads, and for each box the text found inside and its position.

What you can build

  • Text and its location pulled from photos of signs or labels
  • Checks that lettering in a generated image is spelled right
  • Coordinates for blurring or replacing text in a picture

Prompting tips

  • Upload the image at its full size; small or blurry lettering is read less reliably.
  • Straighten tilted documents first so each line gets its own box.

What to check

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.

Inputs

  • Image (required): The URL of the image to be processed.

Output and limits

  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to: $0.60 / run