Available now

Florence-2 Region Proposals: region proposals

Florence-2 Region Proposals marks the areas of an image that likely hold a distinct object, without you naming anything.

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 one image; there is nothing else to set. Microsoft's Florence-2 returns the image with a box drawn around each candidate region, plus the position and size of every box, ready for a later step to label, crop or check.

What you can build

  • Automatic crops of every object in a product shot
  • Starting boxes for a labeling or review job
  • A quick map of what an image contains before editing it

Prompting tips

  • Use it when you do not know in advance what the image holds; to find a named thing, use phrase grounding instead.
  • Expect overlapping boxes on busy scenes and keep the ones you need.

What to check

Review overlapping and empty regions against the source. Choose only useful proposals for the next step of your workflow.

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