Available now

Florence-2 Dense Region Captions: region captions

Microsoft's Florence-2 finds the regions of an image and gives each one a short caption inside a labeled box.

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 and Florence-2 marks the parts it recognizes, such as people, objects and areas, with a box and a short description for each. The result is the list of boxes with their positions and captions, and a copy of your image with the boxes drawn on it.

What you can build

  • Quick inventories of what is in a photo
  • Alt text drafts for busy images
  • Labels to check a dataset or a photo archive

Prompting tips

  • Use a clear, well-lit image; small or blurry objects may get no box.
  • If you need one specific object, the open-vocabulary detection version lets you name it.

What to check

Read each label alongside its region. Correct imagined attributes or relationships before turning the results into published captions or alt text.

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