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

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"
}