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

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
}