Available now

Florence-2 Object Detection: object detection

Microsoft's Florence-2 Large finds the objects in a photo and marks each one with 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 one image; there is nothing else to set. You get back the image with the detected objects outlined, plus a list of boxes with a label and position for each object it found.

What you can build

  • A quick inventory of what appears in a photo
  • Box coordinates for cropping or tagging images
  • Labels to sort or search a photo collection

Prompting tips

  • Clear, well-lit photos where objects do not overlap much give more complete results.
  • Use the box positions to crop each object into its own image for later edits.

What to check

Compare each box with the original. Check missed objects, overlapping detections and incorrect labels before using the results downstream.

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