Moondream2

Class: Moondream2BlockV1

Source: inference.core.workflows.core_steps.models.foundation.moondream2.v1.Moondream2BlockV1

This workflow block runs Moondream2, a multimodal vision-language model. You can use this block to run zero-shot object detection.

Type identifier

Use the following identifier in step "type" field: roboflow_core/moondream2@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
prompt	str	Optional text prompt to provide additional context to Moondream2..	✅
model_version	str	The Moondream2 model to be used for inference..	✅

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to Moondream2 in version v1.

• inputs: Triangle Visualization, Morphological Transformation, Roboflow Dataset Upload, Ellipse Visualization, LMM, Florence-2 Model, Blur Visualization, Halo Visualization, Anthropic Claude, Google Gemini, Camera Focus, Llama 3.2 Vision, Model Comparison Visualization, Keypoint Visualization, Pixelate Visualization, Image Slicer, Stitch OCR Detections, Roboflow Dataset Upload, Line Counter Visualization, Keypoint Detection Model, Label Visualization, SIFT Comparison, QR Code Generator, Email Notification, Slack Notification, Object Detection Model, Corner Visualization, Image Slicer, Florence-2 Model, CSV Formatter, EasyOCR, Object Detection Model, Anthropic Claude, OpenAI, Google Gemini, Bounding Box Visualization, Keypoint Detection Model, Anthropic Claude, Background Subtraction, Background Color Visualization, Image Convert Grayscale, Camera Calibration, Polygon Visualization, Image Blur, VLM As Classifier, Relative Static Crop, Clip Comparison, Heatmap Visualization, CogVLM, Mask Visualization, Image Preprocessing, Twilio SMS Notification, VLM As Detector, Instance Segmentation Model, OpenAI, OCR Model, SIFT, Stitch Images, Stability AI Outpainting, Single-Label Classification Model, Stitch OCR Detections, Dynamic Crop, Model Monitoring Inference Aggregator, Circle Visualization, Color Visualization, Trace Visualization, OpenAI, Icon Visualization, Dot Visualization, Email Notification, Instance Segmentation Model, Camera Focus, Twilio SMS/MMS Notification, Depth Estimation, Contrast Equalization, LMM For Classification, Roboflow Custom Metadata, Grid Visualization, Text Display, Reference Path Visualization, Image Threshold, Perspective Correction, Image Contours, Polygon Zone Visualization, Multi-Label Classification Model, Polygon Visualization, Local File Sink, Halo Visualization, Google Vision OCR, Stability AI Inpainting, Crop Visualization, Google Gemini, Webhook Sink, Absolute Static Crop, Classification Label Visualization, OpenAI, Multi-Label Classification Model, Single-Label Classification Model, Stability AI Image Generation
• outputs: Detections Stitch, Roboflow Dataset Upload, Triangle Visualization, Detections Classes Replacement, PTZ Tracking (ONVIF).md), Ellipse Visualization, Detections Transformation, Florence-2 Model, Blur Visualization, Stitch OCR Detections, Model Comparison Visualization, Dynamic Crop, Model Monitoring Inference Aggregator, Circle Visualization, Detection Offset, Pixelate Visualization, Byte Tracker, Size Measurement, Line Counter, Stitch OCR Detections, Roboflow Dataset Upload, Trace Visualization, Label Visualization, Color Visualization, Icon Visualization, Dot Visualization, Time in Zone, Distance Measurement, Velocity, Detections Stabilizer, Path Deviation, Corner Visualization, Florence-2 Model, Path Deviation, Camera Focus, Roboflow Custom Metadata, Segment Anything 2 Model, Detections Filter, Detections Combine, Perspective Correction, Bounding Box Visualization, Detection Event Log, Background Color Visualization, Byte Tracker, Time in Zone, Crop Visualization, Detections Consensus, Time in Zone, Detections List Roll-Up, Detections Merge, Overlap Filter, Heatmap Visualization, Line Counter, Byte Tracker

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Moondream2 in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Optional text prompt to provide additional context to Moondream2..
  • model_version (roboflow_model_id): The Moondream2 model to be used for inference..

• output

  • predictions (object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.

Example JSON definition of step Moondream2 in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/moondream2@v1",
    "images": "$inputs.image",
    "prompt": "my prompt",
    "model_version": "moondream2/moondream2_2b_jul24"
}