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. Otherwise it will just be None.	❌
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: Blur Visualization, Polygon Visualization, Triangle Visualization, Trace Visualization, Single-Label Classification Model, Label Visualization, Perspective Correction, Camera Calibration, Absolute Static Crop, Image Preprocessing, Relative Static Crop, Keypoint Detection Model, Bounding Box Visualization, Image Threshold, Reference Path Visualization, Stability AI Outpainting, Instance Segmentation Model, SIFT, Camera Focus, Dynamic Crop, Depth Estimation, Halo Visualization, Stability AI Inpainting, Background Color Visualization, Dot Visualization, Classification Label Visualization, SIFT Comparison, Circle Visualization, Image Blur, Keypoint Visualization, Stability AI Image Generation, Object Detection Model, Image Convert Grayscale, Line Counter Visualization, Multi-Label Classification Model, Model Comparison Visualization, Ellipse Visualization, Image Contours, Image Slicer, Crop Visualization, Corner Visualization, Grid Visualization, Pixelate Visualization, Stitch Images, Image Slicer, Mask Visualization, Color Visualization, Polygon Zone Visualization
• outputs: Blur Visualization, Triangle Visualization, Trace Visualization, Size Measurement, Label Visualization, Distance Measurement, Perspective Correction, Model Monitoring Inference Aggregator, Path Deviation, Detections Consensus, Roboflow Dataset Upload, Time in Zone, Detections Filter, Detections Merge, Byte Tracker, Bounding Box Visualization, Segment Anything 2 Model, Detections Stitch, Roboflow Dataset Upload, Detection Offset, Detections Classes Replacement, Dynamic Crop, Byte Tracker, Dot Visualization, Background Color Visualization, Detections Stabilizer, Florence-2 Model, Detections Transformation, Time in Zone, Circle Visualization, Florence-2 Model, PTZ Tracking (ONVIF).md), Path Deviation, Model Comparison Visualization, Ellipse Visualization, Roboflow Custom Metadata, Line Counter, Stitch OCR Detections, Crop Visualization, Corner Visualization, Line Counter, Pixelate Visualization, Velocity, Byte Tracker, Overlap Filter, Color 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..
  • 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": "What is in this image?",
    "model_version": "moondream2/moondream2_2b_jul24"
}