Dynamic Crop

Class: DynamicCropBlockV1

Source: inference.core.workflows.core_steps.transformations.dynamic_crop.v1.DynamicCropBlockV1

Create dynamic crops from an image based on detections from detections-based model.

This is useful when placed after an ObjectDetection block as part of a multi-stage workflow. For example, you could use an ObjectDetection block to detect objects, then the DynamicCropBlock block to crop objects, then an OCR block to run character recognition on each of the individual cropped regions.

In addition, for instance segmentation predictions (which provide segmentation mask for each bounding box) it is possible to remove background in the crops, outside of detected instances. To enable that functionality, set mask_opacity to positive value and optionally tune background_color.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
mask_opacity	float	For instance segmentation, mask_opacity can be used to control background removal. Opacity 1.0 removes the background, while 0.0 leaves the crop unchanged..	✅
background_color	Union[Tuple[int, int, int], str]	For background removal based on segmentation mask, new background color can be selected. Can be a hex string (like '#431112') RGB string (like '(128, 32, 64)') or a RGB tuple (like (18, 17, 67))..	✅

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 Dynamic Crop in version v1.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Dynamic Crop in version v1 has.

Bindings

• input

  • images (image): The input image for this step..
  • predictions (Union[instance_segmentation_prediction, keypoint_detection_prediction, object_detection_prediction]): Detection model output containing bounding boxes for cropping..
  • mask_opacity (float_zero_to_one): For instance segmentation, mask_opacity can be used to control background removal. Opacity 1.0 removes the background, while 0.0 leaves the crop unchanged..
  • background_color (Union[rgb_color, string]): For background removal based on segmentation mask, new background color can be selected. Can be a hex string (like '#431112') RGB string (like '(128, 32, 64)') or a RGB tuple (like (18, 17, 67))..

• output

  • crops (image): Image in workflows.
  • predictions (Union[object_detection_prediction, instance_segmentation_prediction, keypoint_detection_prediction]): Prediction with detected bounding boxes in form of sv.Detections(...) object if object_detection_prediction or Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object if instance_segmentation_prediction or Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object if keypoint_detection_prediction.

Example JSON definition of step Dynamic Crop in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/dynamic_crop@v1",
    "images": "$inputs.image",
    "predictions": "$steps.my_object_detection_model.predictions",
    "mask_opacity": "<block_does_not_provide_example>",
    "background_color": "#431112"
}