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