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