Model Comparison Visualization

Class: ModelComparisonVisualizationBlockV1

Source: inference.core.workflows.core_steps.visualizations.model_comparison.v1.ModelComparisonVisualizationBlockV1

The ModelComparisonVisualization block draws all areas predicted by neither model with a specified color, lets overlapping areas of the predictions shine through, and colors areas predicted by only one model with a distinct color.

Type identifier

Use the following identifier in step "type" field: roboflow_core/model_comparison_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_a	str	Color of the areas Model A predicted that Model B did not...	✅
color_b	str	Color of the areas Model B predicted that Model A did not..	✅
background_color	str	Color of the areas neither model predicted..	✅
opacity	float	Transparency of the 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 Model Comparison Visualization in version v1.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Model Comparison 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_a (Union[object_detection_prediction, instance_segmentation_prediction, keypoint_detection_prediction]): Predictions.
  • color_a (string): Color of the areas Model A predicted that Model B did not...
  • predictions_b (Union[object_detection_prediction, instance_segmentation_prediction, keypoint_detection_prediction]): Predictions.
  • color_b (string): Color of the areas Model B predicted that Model A did not..
  • background_color (string): Color of the areas neither model predicted..
  • opacity (float_zero_to_one): Transparency of the overlay..

• output

  • image (image): Image in workflows.

Example JSON definition of step Model Comparison Visualization in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/model_comparison_visualization@v1",
    "image": "$inputs.image",
    "copy_image": true,
    "predictions_a": "$steps.object_detection_model.predictions",
    "color_a": "GREEN",
    "predictions_b": "$steps.object_detection_model.predictions",
    "color_b": "RED",
    "background_color": "BLACK",
    "opacity": 0.7
}