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:
Slack Notification,Anthropic Claude,QR Code Generator,Keypoint Detection Model,Clip Comparison,Anthropic Claude,OpenAI,Instance Segmentation Model,Google Vision OCR,Circle Visualization,Bounding Box Visualization,Single-Label Classification Model,Florence-2 Model,VLM As Classifier,Image Slicer,Google Gemini,Image Contours,Image Blur,Keypoint Detection Model,Qwen 3.6 API,Dot Visualization,Polygon Zone Visualization,Single-Label Classification Model,Label Visualization,Icon Visualization,Image Threshold,Roboflow Vision Events,LMM For Classification,Depth Estimation,Line Counter Visualization,Object Detection Model,Stitch Images,Blur Visualization,Morphological Transformation,Relative Static Crop,LMM,Model Comparison Visualization,Trace Visualization,Qwen3.5-VL,Florence-2 Model,Camera Focus,MoonshotAI Kimi,Grid Visualization,Pixelate Visualization,CogVLM,Instance Segmentation Model,Twilio SMS/MMS Notification,OpenAI,Image Convert Grayscale,Llama 3.2 Vision,Keypoint Visualization,Twilio SMS Notification,Polygon Visualization,Qwen-VL,S3 Sink,Halo Visualization,Camera Focus,SIFT Comparison,Keypoint Detection Model,Local File Sink,Classification Label Visualization,Google Gemma,Semantic Segmentation Model,Mask Visualization,Multi-Label Classification Model,Morphological Transformation,Multi-Label Classification Model,Camera Calibration,SIFT,Google Gemini,Email Notification,Anthropic Claude,MoonshotAI Kimi,Roboflow Dataset Upload,Image Preprocessing,Semantic Segmentation Model,Text Display,Image Slicer,Corner Visualization,Multi-Label Classification Model,Absolute Static Crop,Stitch OCR Detections,Llama 3.2 Vision,Halo Visualization,Roboflow Asset Library Attributes,GLM-OCR,Object Detection Model,Roboflow Custom Metadata,Email Notification,Dynamic Crop,Reference Path Visualization,OpenAI,Instance Segmentation Model,OpenRouter,Background Color Visualization,Single-Label Classification Model,Model Monitoring Inference Aggregator,Ellipse Visualization,CSV Formatter,Stability AI Outpainting,Contrast Enhancement,VLM As Detector,EasyOCR,Triangle Visualization,OCR Model,Crop Visualization,Webhook Sink,Google Gemma API,Perspective Correction,Qwen 3.5 API,Stability AI Image Generation,Stitch OCR Detections,OpenAI-Compatible LLM,Color Visualization,Heatmap Visualization,Contrast Equalization,Instance Segmentation Model,Object Detection Model,Polygon Visualization,Background Subtraction,Google Gemini,Roboflow Dataset Upload,OpenAI,Stability AI Inpainting - outputs:
Detections Stabilizer,Distance Measurement,Velocity,Detection Offset,Line Counter,Camera Focus,Circle Visualization,Bounding Box Visualization,Path Deviation,Florence-2 Model,Roboflow Dataset Upload,Detections Filter,Overlap Filter,Corner Visualization,Stitch OCR Detections,Detections Transformation,Detections Consensus,Byte Tracker,PTZ Tracking (ONVIF),Path Deviation,ByteTrack Tracker,Roboflow Custom Metadata,Detections Combine,Mask Area Measurement,Detections Merge,Dot Visualization,Dynamic Crop,Overlap Analysis,Icon Visualization,Label Visualization,Time in Zone,Background Color Visualization,Detections Stitch,Byte Tracker,Roboflow Vision Events,Model Monitoring Inference Aggregator,Ellipse Visualization,Triangle Visualization,OC-SORT Tracker,Crop Visualization,Per-Class Confidence Filter,Blur Visualization,Line Counter,Perspective Correction,SAM2 Video Tracker,Detection Event Log,Stitch OCR Detections,Model Comparison Visualization,Size Measurement,Color Visualization,Heatmap Visualization,Detections List Roll-Up,Trace Visualization,BoT-SORT Tracker,Segment Anything 2 Model,Florence-2 Model,SORT Tracker,Time in Zone,Pixelate Visualization,Time in Zone,Detections Classes Replacement,Byte Tracker,Roboflow Dataset Upload
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"
}