Fuser

Moondream Detection

Provided by Fal — Learn More

MoonDreamNext Detection is a multimodal vision-language model for gaze detection, bbox detection, point detection, and more.

Preview

Inputs

Image
image

The image to analyze

Detection Prompt
text

Describe what to detect in the image

Detection Type
dropdown

Type of detection to perform

default: bbox_detectionAccepts: Bounding Box - Draw boxes around objects, Point - Find specific points, Gaze - Detect where someone is looking
Use Ensemble
toggle

Whether to use ensemble method for gaze detection (more accurate but slower)

default: false

Outputs

Result Image
image

Image with detection visualization

Detection Details
text

Text description of what was detected