Moondream 2

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

Input

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

URL of the image to be processed

Uploading a file needs an account. Create accountJPEG, PNG, WebP · up to 25 MB

Object to be detected in the image

Price$0.04 / image

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use Moondream 2

Getting started

Locate a named object in a photo with Moondream 2 Object Detection. Use a specific object label rather than an instruction to edit the image.

Review your result

Check missed objects and incorrect detections manually; detection is not a segmentation cutout.

Inputs and settings

Send image_url and the object label in object.

Review the detected objects and the annotated image together. Keep the original dimensions when using coordinates downstream.