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

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[string, rgb_color]): 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"
}