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

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"
}