Moondream2 | Vision

fal-ai/moondream2/object-detection

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

Inference

Commercial use

Schema

Playground API

Input

Image URL*

Hint: you can drag and drop file(s) here, or provide a base64 encoded data URL Accepted file types: jpg, jpeg, png, webp, gif, avif

Object*

Result

Idle

{
  "image": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019,
    "width": 1024,
    "height": 1024
  }
}

Your request will cost $0.02 per Imag.

Moondream2 Vision

Input

Result

Logs