Detect — CLI Command

Usage

momentry detect --image <PATH> --objects <LIST> [OPTIONS]

Description

Detect specified objects in an image using CLIP (fast) or Qwen3-VL (accurate). Supports cascade mode for optimal results.

Arguments

None (uses options).

Options

Option	Type	Required	Default	Description
-i, --image	string	Yes	—	Image file path
-o, --objects	string[]	Yes	—	Objects to detect (comma separated)
--cascade	bool	No	false	Use cascade mode (CLIP first, Qwen3-VL for high confidence)
--threshold	f32	No	0.7	CLIP confidence threshold for cascade

Examples

# Detect single object
momentry detect --image photo.jpg --objects cat

# Detect multiple objects
momentry detect --image photo.jpg --objects cat,dog,car

# Cascade mode with custom threshold
momentry detect --image photo.jpg --objects person --cascade --threshold 0.8

Agent Callable

Format: momentry detect '<json-args>'

JSON Args:

{
  "image": "/path/to/image.jpg",
  "objects": ["cat", "dog"],
  "cascade": false,
  "threshold": 0.7
}

Returns: JSON with detected objects and confidence scores.

Related Commands

• vision — Vision LLM management
• process — Process with YOLO module