Segment Anything 2 Model

Class: SegmentAnything2BlockV1

Source: inference.core.workflows.core_steps.models.foundation.segment_anything2.v1.SegmentAnything2BlockV1

Run Segment Anything 2, a zero-shot instance segmentation model, on an image.

** Dedicated inference server required (GPU recomended) **

You can use pass in boxes/predictions from other models to Segment Anything 2 to use as prompts for the model. If you pass in box detections from another model, the class names of the boxes will be forwarded to the predicted masks. If using the model unprompted, the model will assign integers as class names / ids.

Type identifier

Use the following identifier in step "type" field: roboflow_core/segment_anything@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
version	str	Model to be used. One of hiera_large, hiera_small, hiera_tiny, hiera_b_plus.	✅
threshold	float	Threshold for predicted masks scores.	✅
multimask_output	bool	Flag to determine whether to use sam2 internal multimask or single mask mode. For ambiguous prompts setting to True is recomended..	✅

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 Segment Anything 2 Model in version v1.

• inputs: VLM as Detector, Byte Tracker, Google Vision OCR, Overlap Filter, SAM 3, Classification Label Visualization, Detections Stabilizer, Circle Visualization, SIFT Comparison, Image Contours, Relative Static Crop, Detections Filter, Image Preprocessing, LMM For Classification, VLM as Classifier, Ellipse Visualization, Stitch Images, Triangle Visualization, Stability AI Inpainting, Detections Combine, QR Code Generator, Image Slicer, VLM as Classifier, Background Color Visualization, Model Monitoring Inference Aggregator, Segment Anything 2 Model, Template Matching, Moondream2, Velocity, OCR Model, Dot Visualization, Florence-2 Model, SIFT, Morphological Transformation, Detections Transformation, EasyOCR, Reference Path Visualization, Halo Visualization, SIFT Comparison, Gaze Detection, Polygon Visualization, Image Slicer, Florence-2 Model, Detection Offset, Slack Notification, Clip Comparison, Image Convert Grayscale, Instance Segmentation Model, OpenAI, Byte Tracker, Color Visualization, Line Counter, PTZ Tracking (ONVIF).md), Object Detection Model, Keypoint Detection Model, Google Gemini, JSON Parser, Label Visualization, Email Notification, Llama 3.2 Vision, Trace Visualization, Byte Tracker, Dynamic Zone, YOLO-World Model, Email Notification, Corner Visualization, Mask Visualization, Time in Zone, CogVLM, Stability AI Outpainting, OpenAI, Roboflow Custom Metadata, Detections Stitch, Stitch OCR Detections, Blur Visualization, Time in Zone, CSV Formatter, Crop Visualization, VLM as Detector, OpenAI, Grid Visualization, Detections Classes Replacement, Perspective Correction, Twilio SMS Notification, Absolute Static Crop, Single-Label Classification Model, Seg Preview, Contrast Equalization, Roboflow Dataset Upload, Roboflow Dataset Upload, Polygon Zone Visualization, Stability AI Image Generation, Webhook Sink, Depth Estimation, Bounding Box Visualization, Camera Focus, Line Counter Visualization, Instance Segmentation Model, Multi-Label Classification Model, Icon Visualization, Image Blur, Time in Zone, Pixelate Visualization, Image Threshold, Detections Merge, Path Deviation, Keypoint Detection Model, Anthropic Claude, LMM, Google Gemini, Cosine Similarity, Identify Outliers, Dynamic Crop, Bounding Rectangle, Path Deviation, Detections Consensus, Model Comparison Visualization, Camera Calibration, Local File Sink, Keypoint Visualization, Identify Changes, Object Detection Model
• outputs: Byte Tracker, Overlap Filter, Blur Visualization, Time in Zone, Circle Visualization, Detections Stabilizer, Crop Visualization, Detections Filter, Detections Classes Replacement, Perspective Correction, Ellipse Visualization, Triangle Visualization, Roboflow Dataset Upload, Stability AI Inpainting, Detections Combine, Roboflow Dataset Upload, Background Color Visualization, Model Monitoring Inference Aggregator, Segment Anything 2 Model, Velocity, Distance Measurement, Dot Visualization, Florence-2 Model, Bounding Box Visualization, Detections Transformation, Halo Visualization, Icon Visualization, Polygon Visualization, Florence-2 Model, Time in Zone, Detection Offset, Pixelate Visualization, Path Deviation, Byte Tracker, PTZ Tracking (ONVIF).md), Color Visualization, Line Counter, Detections Merge, Label Visualization, Byte Tracker, Trace Visualization, Dynamic Zone, Dynamic Crop, Bounding Rectangle, Path Deviation, Line Counter, Detections Consensus, Model Comparison Visualization, Size Measurement, Corner Visualization, Mask Visualization, Time in Zone, Roboflow Custom Metadata, Detections Stitch

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Segment Anything 2 Model in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • boxes (Union[object_detection_prediction, keypoint_detection_prediction, instance_segmentation_prediction]): Bounding boxes (from another model) to convert to polygons.
  • version (string): Model to be used. One of hiera_large, hiera_small, hiera_tiny, hiera_b_plus.
  • threshold (float): Threshold for predicted masks scores.
  • multimask_output (boolean): Flag to determine whether to use sam2 internal multimask or single mask mode. For ambiguous prompts setting to True is recomended..

• output

  • predictions (instance_segmentation_prediction): Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object.

Example JSON definition of step Segment Anything 2 Model in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/segment_anything@v1",
    "images": "$inputs.image",
    "boxes": "$steps.object_detection_model.predictions",
    "version": "hiera_large",
    "threshold": 0.3,
    "multimask_output": true
}