Image GenerationActive
moondream3-preview / point
point
Moondream3 is a cutting-edge vision-language model that delivers advanced visual reasoning with built-in object detection, pointing, and OCR capabilities—bringing fast, cost-effective, and scalable inference to real-world applications.
Image to TextBf16
Model ID
point
Provider
moondream3-preview
Updated
1770899028
wiro playground—moondream3-preview/point
Updated 1770899028
The Moondream 3 "Point" model is a dedicated capability within the Moondream 3 vision-language model (VLM) designed for highly precise point detection or visual grounding. It allows users to pinpoint the exact location (outputting normalized (x, y) coordinates) of an object or feature specified by a natural language prompt.
Example prompts
Great starting points for point.
empty parking slotImage Generation
blue carImage Generation
API quick start
Run point with a single API call.
POST https://api.wiro.ai/v1/Run/moondream3-preview/point
{
"prompt": "empty parking slot",
"inputImage": "https://your-cdn.com/input.png"
}