Moondream3 Point - Point Localization

Moondream3 Point is a specialized vision-language model for locating specific objects in images and returning their coordinate points.

Features

• Point Localization: Find exact positions of objects
• Coordinate Points: Get precise x, y coordinates
• Multiple Objects: Locate multiple instances of the same object
• Natural Language: Specify objects using plain English

Example Usage

Locate Person

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

Locate Object

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

Locate Specific Item

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

Output Format

Returns coordinate points in the format: [x, y] where x and y are the pixel coordinates of the object's center or key point.

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.