Mask Visualization

Class: MaskVisualizationBlockV1

Source: inference.core.workflows.core_steps.visualizations.mask.v1.MaskVisualizationBlockV1

The MaskVisualization block uses a detected polygon from an instance segmentation to draw a mask using sv.MaskAnnotator.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
copy_image	bool	Enable this option to create a copy of the input image for visualization, preserving the original. Use this when stacking multiple visualizations..	✅
color_palette	str	Select a color palette for the visualised elements..	✅
palette_size	int	Specify the number of colors in the palette. This applies when using custom or Matplotlib palettes..	✅
custom_colors	List[str]	Define a list of custom colors for bounding boxes in HEX format..	✅
color_axis	str	Choose how bounding box colors are assigned..	✅
opacity	float	Transparency of the Mask overlay..	✅

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 Mask Visualization in version v1.

• inputs: Line Counter Visualization, Halo Visualization, Absolute Static Crop, OpenAI, Dimension Collapse, Image Preprocessing, Buffer, Size Measurement, Mask Visualization, Email Notification, VLM as Detector, Ellipse Visualization, Keypoint Visualization, Instance Segmentation Model, Trace Visualization, LMM For Classification, Camera Focus, Detections Consensus, Multi-Label Classification Model, Time in Zone, Line Counter, Template Matching, VLM as Detector, Pixelate Visualization, Velocity, Webhook Sink, Florence-2 Model, Google Vision OCR, Detection Offset, Stitch OCR Detections, Detections Classes Replacement, Segment Anything 2 Model, Line Counter, Anthropic Claude, Object Detection Model, Image Convert Grayscale, Image Slicer, CogVLM, Model Monitoring Inference Aggregator, Triangle Visualization, Reference Path Visualization, Local File Sink, Florence-2 Model, Relative Static Crop, OpenAI, Dynamic Zone, Twilio SMS Notification, Path Deviation, Detections Stabilizer, SIFT Comparison, Stability AI Inpainting, Color Visualization, Instance Segmentation Model, Grid Visualization, Clip Comparison, Classification Label Visualization, Single-Label Classification Model, LMM, JSON Parser, Clip Comparison, Detections Stitch, Keypoint Detection Model, Google Gemini, Roboflow Dataset Upload, Bounding Rectangle, Path Deviation, Roboflow Dataset Upload, Bounding Box Visualization, Detections Transformation, Polygon Visualization, Pixel Color Count, Depth Estimation, Polygon Zone Visualization, Perspective Correction, Stitch Images, Identify Outliers, OCR Model, Detections Filter, CSV Formatter, Stability AI Image Generation, VLM as Classifier, Model Comparison Visualization, Llama 3.2 Vision, Background Color Visualization, Dynamic Crop, Blur Visualization, SIFT, Corner Visualization, Image Contours, Label Visualization, VLM as Classifier, Time in Zone, Image Slicer, Dot Visualization, Slack Notification, Roboflow Custom Metadata, Distance Measurement, Circle Visualization, Image Threshold, Image Blur, Identify Changes, SIFT Comparison, Crop Visualization, Camera Calibration
• outputs: Line Counter Visualization, Halo Visualization, Absolute Static Crop, OpenAI, Image Preprocessing, Buffer, Mask Visualization, VLM as Detector, Ellipse Visualization, Keypoint Visualization, Instance Segmentation Model, Trace Visualization, LMM For Classification, Camera Focus, Multi-Label Classification Model, Byte Tracker, Time in Zone, Template Matching, Gaze Detection, VLM as Detector, Pixelate Visualization, SmolVLM2, Moondream2, Florence-2 Model, Google Vision OCR, Anthropic Claude, Single-Label Classification Model, Object Detection Model, Segment Anything 2 Model, Qwen2.5-VL, Image Convert Grayscale, YOLO-World Model, Object Detection Model, Image Slicer, CogVLM, Reference Path Visualization, Triangle Visualization, Florence-2 Model, Relative Static Crop, OpenAI, Barcode Detection, Detections Stabilizer, SIFT Comparison, Stability AI Inpainting, Color Visualization, Instance Segmentation Model, Clip Comparison, CLIP Embedding Model, Classification Label Visualization, LMM, Multi-Label Classification Model, Clip Comparison, Detections Stitch, Keypoint Detection Model, Keypoint Detection Model, Google Gemini, Roboflow Dataset Upload, Roboflow Dataset Upload, Bounding Box Visualization, Pixel Color Count, Polygon Visualization, Depth Estimation, Polygon Zone Visualization, Camera Calibration, Perspective Correction, Stitch Images, Dominant Color, OCR Model, Stability AI Image Generation, VLM as Classifier, Model Comparison Visualization, Llama 3.2 Vision, Background Color Visualization, SIFT, Blur Visualization, Dynamic Crop, Corner Visualization, Image Contours, Label Visualization, VLM as Classifier, Image Slicer, Dot Visualization, Circle Visualization, QR Code Detection, Image Threshold, Image Blur, Crop Visualization, Single-Label Classification Model

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Mask Visualization in version v1 has.

Bindings

• input

  • image (image): The image to visualize on..
  • copy_image (boolean): Enable this option to create a copy of the input image for visualization, preserving the original. Use this when stacking multiple visualizations..
  • predictions (instance_segmentation_prediction): Predictions.
  • color_palette (string): Select a color palette for the visualised elements..
  • palette_size (integer): Specify the number of colors in the palette. This applies when using custom or Matplotlib palettes..
  • custom_colors (list_of_values): Define a list of custom colors for bounding boxes in HEX format..
  • color_axis (string): Choose how bounding box colors are assigned..
  • opacity (float_zero_to_one): Transparency of the Mask overlay..

• output

  • image (image): Image in workflows.

Example JSON definition of step Mask Visualization in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/mask_visualization@v1",
    "image": "$inputs.image",
    "copy_image": true,
    "predictions": "$steps.instance_segmentation_model.predictions",
    "color_palette": "DEFAULT",
    "palette_size": 10,
    "custom_colors": [
        "#FF0000",
        "#00FF00",
        "#0000FF"
    ],
    "color_axis": "CLASS",
    "opacity": 0.5
}