Moondream3 Detect - Object Detection

Moondream3 Detect is a specialized vision-language model for finding objects in images and returning their bounding box coordinates.

Features

• Object Detection: Find specific objects in images
• Bounding Boxes: Get precise coordinate locations
• Multiple Objects: Detect multiple instances of the same object
• Natural Language: Specify objects using plain English

Example Usage

Detect Cars

{
  "image": "https://example.com/photo.jpg",
  "prompt": "car"
}

Detect People

{
  "image": "https://example.com/photo.jpg",
  "prompt": "person"
}

Detect Any Object

{
  "image": "https://example.com/photo.jpg",
  "prompt": "bicycle"
}

Output Format

Returns bounding box coordinates in the format: [x1, y1, x2, y2] where (x1, y1) is the top-left corner and (x2, y2) is the bottom-right corner.

Best Practices

• Use specific object names for better accuracy
• Supported formats: JPEG, PNG, WebP
• Max image size: 10MB

Pricing

Fixed price per request. Contact WaveSpeed for volume discounts.