Available now

Florence-2 Referring-Expression Segmentation: segmentation by text

Microsoft's Florence-2 Large outlines the part of a photo you describe in words, such as "the dog on the left", and returns its exact shape.

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

Text input for the task

Example. Edit it or write your own.

Price$0.60 / run

You sign up first. Your settings are kept.

About this model

Overview

Upload an image and write a short phrase that points to one thing in it. You get back the image with that region marked, plus its outline as a list of polygon points you can use as a selection or mask.

What you can build

  • Selections for later edits, picked by name instead of by hand
  • Masks for one product in a crowded shelf photo
  • Outlines of people or objects for layout work

Prompting tips

  • Point to one thing with color, position or size, for example "the smaller white cup in front".
  • Keep the phrase short; a long sentence with several objects can mark the wrong one.

What to check

Compare returned polygon boundaries with the intended object. Inspect thin parts and adjacent subjects before using the selection.

Inputs

  • Image (required): The URL of the image to be processed.
  • Text Input (required): Text input for the task.

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