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

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"
}