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: Reference Path Visualization, Blur Visualization, Pixelate Visualization, Classification Label Visualization, Instance Segmentation Model, Background Color Visualization, Dynamic Crop, Keypoint Visualization, Camera Focus, Mask Visualization, Single-Label Classification Model, Image Slicer, Absolute Static Crop, Stability AI Image Generation, Image Blur, Circle Visualization, Grid Visualization, Crop Visualization, Image Convert Grayscale, Image Threshold, Trace Visualization, Multi-Label Classification Model, Object Detection Model, Polygon Visualization, Triangle Visualization, Stability AI Inpainting, Keypoint Detection Model, Halo Visualization, Dot Visualization, Polygon Zone Visualization, Camera Calibration, SIFT, Corner Visualization, Image Contours, Model Comparison Visualization, Stitch Images, Bounding Box Visualization, Line Counter Visualization, Image Slicer, Perspective Correction, Image Preprocessing, SIFT Comparison, Label Visualization, Relative Static Crop, Color Visualization, Ellipse Visualization
• outputs: Blur Visualization, Pixelate Visualization, Background Color Visualization, Dynamic Crop, Time in Zone, Byte Tracker, Segment Anything 2 Model, Detection Offset, Model Monitoring Inference Aggregator, Florence-2 Model, Florence-2 Model, Detections Filter, Detections Transformation, Roboflow Dataset Upload, Circle Visualization, Crop Visualization, Trace Visualization, Path Deviation, Triangle Visualization, Detections Consensus, Stitch OCR Detections, Dot Visualization, Detections Merge, Velocity, Detections Stitch, Size Measurement, Roboflow Custom Metadata, Detections Classes Replacement, Detections Stabilizer, Label Visualization, Path Deviation, Line Counter, Corner Visualization, Time in Zone, Model Comparison Visualization, Roboflow Dataset Upload, Bounding Box Visualization, Byte Tracker, Perspective Correction, Byte Tracker, Line Counter, Distance Measurement, Color Visualization, Ellipse 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"
}