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