Keypoint Detection Model

v2

Class: RoboflowKeypointDetectionModelBlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.roboflow.keypoint_detection.v2.RoboflowKeypointDetectionModelBlockV2

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Run inference on a keypoint detection model hosted on or uploaded to Roboflow.

You can query any model that is private to your account, or any public model available on Roboflow Universe.

You will need to set your Roboflow API key in your Inference environment to use this block. To learn more about setting your Roboflow API key, refer to the Inference documentation.

Type identifier

Use the following identifier in step "type" field: roboflow_core/roboflow_keypoint_detection_model@v2to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
model_id	str	Roboflow model identifier..	✅
confidence	float	Confidence threshold for predictions..	✅
keypoint_confidence	float	Confidence threshold to predict a keypoint as visible..	✅
class_filter	List[str]	List of accepted classes. Classes must exist in the model's training set..	✅
iou_threshold	float	Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more..	✅
max_detections	int	Maximum number of detections to return..	✅
class_agnostic_nms	bool	Boolean flag to specify if NMS is to be used in class-agnostic mode..	✅
max_candidates	int	Maximum number of candidates as NMS input to be taken into account..	✅
disable_active_learning	bool	Boolean flag to disable project-level active learning for this block..	✅
active_learning_target_dataset	str	Target dataset for active learning, if enabled..	✅

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 Keypoint Detection Model in version v2.

• inputs: Polygon Zone Visualization, Motion Detection, Relative Static Crop, PTZ Tracking (ONVIF).md), Image Preprocessing, Webhook Sink, Dimension Collapse, Google Gemini, Roboflow Dataset Upload, Contrast Equalization, Corner Visualization, Triangle Visualization, Text Display, Slack Notification, Image Slicer, Dynamic Crop, SIFT Comparison, Bounding Box Visualization, Stitch Images, SIFT, Identify Changes, Email Notification, Halo Visualization, Icon Visualization, Morphological Transformation, Anthropic Claude, Size Measurement, QR Code Generator, Grid Visualization, Heatmap Visualization, Image Blur, Florence-2 Model, Google Gemini, Model Comparison Visualization, OpenAI, Distance Measurement, Email Notification, Twilio SMS Notification, Blur Visualization, Absolute Static Crop, Detections List Roll-Up, JSON Parser, Google Gemini, Halo Visualization, Roboflow Dataset Upload, Local File Sink, Dot Visualization, Stability AI Outpainting, Florence-2 Model, OpenAI, VLM As Classifier, Clip Comparison, Detection Event Log, Image Contours, Dynamic Zone, Stability AI Image Generation, VLM As Classifier, Ellipse Visualization, Pixelate Visualization, Reference Path Visualization, Pixel Color Count, Multi-Label Classification Model, Keypoint Visualization, Crop Visualization, Twilio SMS/MMS Notification, Circle Visualization, Roboflow Custom Metadata, Background Color Visualization, Trace Visualization, Camera Focus, Instance Segmentation Model, Template Matching, Line Counter, Color Visualization, Detections Consensus, Polygon Visualization, Object Detection Model, VLM As Detector, OpenAI, Polygon Visualization, Anthropic Claude, Image Threshold, Camera Focus, Mask Visualization, Llama 3.2 Vision, Line Counter, Model Monitoring Inference Aggregator, VLM As Detector, Stability AI Inpainting, Buffer, Background Subtraction, Classification Label Visualization, Image Slicer, Line Counter Visualization, Single-Label Classification Model, Perspective Correction, Keypoint Detection Model, Clip Comparison, Camera Calibration, Depth Estimation, Label Visualization, Identify Outliers, SIFT Comparison, Image Convert Grayscale, Anthropic Claude
• outputs: SAM 3, Webhook Sink, Byte Tracker, Qwen2.5-VL, Ellipse Visualization, Detections Classes Replacement, Pixelate Visualization, SAM 3, Detections Transformation, Multi-Label Classification Model, Moondream2, Keypoint Visualization, Roboflow Dataset Upload, Crop Visualization, Corner Visualization, Triangle Visualization, Circle Visualization, SmolVLM2, Roboflow Custom Metadata, Dynamic Crop, Background Color Visualization, Trace Visualization, Bounding Box Visualization, Instance Segmentation Model, Icon Visualization, Object Detection Model, Heatmap Visualization, Color Visualization, Detections Filter, Detections Consensus, Qwen3-VL, Object Detection Model, Florence-2 Model, Instance Segmentation Model, Segment Anything 2 Model, Model Comparison Visualization, Keypoint Detection Model, Blur Visualization, Model Monitoring Inference Aggregator, Detection Offset, Detections List Roll-Up, Single-Label Classification Model, Multi-Label Classification Model, Roboflow Dataset Upload, Single-Label Classification Model, Dot Visualization, Keypoint Detection Model, Detections Merge, Florence-2 Model, Label Visualization, SAM 3

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Keypoint Detection Model in version v2 has.

Bindings

• input

  • images (image): The image to infer on..
  • model_id (roboflow_model_id): Roboflow model identifier..
  • confidence (float_zero_to_one): Confidence threshold for predictions..
  • keypoint_confidence (float_zero_to_one): Confidence threshold to predict a keypoint as visible..
  • class_filter (list_of_values): List of accepted classes. Classes must exist in the model's training set..
  • iou_threshold (float_zero_to_one): Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more..
  • max_detections (integer): Maximum number of detections to return..
  • class_agnostic_nms (boolean): Boolean flag to specify if NMS is to be used in class-agnostic mode..
  • max_candidates (integer): Maximum number of candidates as NMS input to be taken into account..
  • disable_active_learning (boolean): Boolean flag to disable project-level active learning for this block..
  • active_learning_target_dataset (roboflow_project): Target dataset for active learning, if enabled..

• output

  • inference_id (inference_id): Inference identifier.
  • predictions (keypoint_detection_prediction): Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object.
  • model_id (roboflow_model_id): Roboflow model id.

Example JSON definition of step Keypoint Detection Model in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/roboflow_keypoint_detection_model@v2",
    "images": "$inputs.image",
    "model_id": "my_project/3",
    "confidence": 0.3,
    "keypoint_confidence": 0.3,
    "class_filter": [
        "a",
        "b",
        "c"
    ],
    "iou_threshold": 0.4,
    "max_detections": 300,
    "class_agnostic_nms": true,
    "max_candidates": 3000,
    "disable_active_learning": true,
    "active_learning_target_dataset": "my_project"
}

v1

Class: RoboflowKeypointDetectionModelBlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.roboflow.keypoint_detection.v1.RoboflowKeypointDetectionModelBlockV1

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Run inference on a keypoint detection model hosted on or uploaded to Roboflow.

You can query any model that is private to your account, or any public model available on Roboflow Universe.

You will need to set your Roboflow API key in your Inference environment to use this block. To learn more about setting your Roboflow API key, refer to the Inference documentation.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
model_id	str	Roboflow model identifier..	✅
confidence	float	Confidence threshold for predictions..	✅
keypoint_confidence	float	Confidence threshold to predict a keypoint as visible..	✅
class_filter	List[str]	List of accepted classes. Classes must exist in the model's training set..	✅
iou_threshold	float	Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more..	✅
max_detections	int	Maximum number of detections to return..	✅
class_agnostic_nms	bool	Boolean flag to specify if NMS is to be used in class-agnostic mode..	✅
max_candidates	int	Maximum number of candidates as NMS input to be taken into account..	✅
disable_active_learning	bool	Boolean flag to disable project-level active learning for this block..	✅
active_learning_target_dataset	str	Target dataset for active learning, if enabled..	✅

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 Keypoint Detection Model in version v1.

• inputs: Polygon Zone Visualization, Motion Detection, Relative Static Crop, PTZ Tracking (ONVIF).md), Image Preprocessing, Webhook Sink, Dimension Collapse, Google Gemini, Roboflow Dataset Upload, Contrast Equalization, Corner Visualization, Triangle Visualization, Text Display, Slack Notification, Image Slicer, Dynamic Crop, SIFT Comparison, Bounding Box Visualization, Stitch Images, SIFT, Identify Changes, Email Notification, Halo Visualization, Icon Visualization, Morphological Transformation, Anthropic Claude, Size Measurement, QR Code Generator, Grid Visualization, Heatmap Visualization, Image Blur, Florence-2 Model, Google Gemini, Model Comparison Visualization, OpenAI, Distance Measurement, Email Notification, Twilio SMS Notification, Blur Visualization, Absolute Static Crop, Detections List Roll-Up, JSON Parser, Google Gemini, Halo Visualization, Roboflow Dataset Upload, Local File Sink, Dot Visualization, Stability AI Outpainting, Florence-2 Model, OpenAI, VLM As Classifier, Clip Comparison, Detection Event Log, Image Contours, Dynamic Zone, Stability AI Image Generation, VLM As Classifier, Ellipse Visualization, Pixelate Visualization, Reference Path Visualization, Pixel Color Count, Multi-Label Classification Model, Keypoint Visualization, Crop Visualization, Twilio SMS/MMS Notification, Circle Visualization, Roboflow Custom Metadata, Background Color Visualization, Trace Visualization, Camera Focus, Instance Segmentation Model, Template Matching, Line Counter, Color Visualization, Detections Consensus, Polygon Visualization, Object Detection Model, VLM As Detector, OpenAI, Polygon Visualization, Anthropic Claude, Image Threshold, Camera Focus, Mask Visualization, Llama 3.2 Vision, Line Counter, Model Monitoring Inference Aggregator, VLM As Detector, Stability AI Inpainting, Buffer, Background Subtraction, Classification Label Visualization, Image Slicer, Line Counter Visualization, Single-Label Classification Model, Perspective Correction, Keypoint Detection Model, Clip Comparison, Camera Calibration, Depth Estimation, Label Visualization, Identify Outliers, SIFT Comparison, Image Convert Grayscale, Anthropic Claude
• outputs: Polygon Zone Visualization, PTZ Tracking (ONVIF).md), Stitch OCR Detections, Image Preprocessing, Webhook Sink, Byte Tracker, Detections Classes Replacement, Path Deviation, Stitch OCR Detections, Detections Transformation, Google Gemini, Roboflow Dataset Upload, Contrast Equalization, Corner Visualization, Triangle Visualization, Slack Notification, Text Display, Time in Zone, Dynamic Crop, Detections Stitch, Bounding Box Visualization, CogVLM, Email Notification, LMM For Classification, Morphological Transformation, Icon Visualization, Anthropic Claude, Halo Visualization, Size Measurement, QR Code Generator, Heatmap Visualization, Google Vision OCR, Detections Filter, Image Blur, Florence-2 Model, Instance Segmentation Model, Google Gemini, Email Notification, OpenAI, Twilio SMS Notification, Distance Measurement, Model Comparison Visualization, Path Deviation, Cache Get, Perception Encoder Embedding Model, Blur Visualization, Detections List Roll-Up, Google Gemini, Halo Visualization, Roboflow Dataset Upload, Local File Sink, Dot Visualization, Detections Merge, OpenAI, Florence-2 Model, Stability AI Outpainting, SAM 3, Stability AI Image Generation, Ellipse Visualization, Pixelate Visualization, SAM 3, Time in Zone, Seg Preview, Reference Path Visualization, Pixel Color Count, Moondream2, Keypoint Visualization, YOLO-World Model, Crop Visualization, Twilio SMS/MMS Notification, Circle Visualization, Roboflow Custom Metadata, Background Color Visualization, Trace Visualization, Instance Segmentation Model, Line Counter, Color Visualization, CLIP Embedding Model, Detections Consensus, Polygon Visualization, OpenAI, Segment Anything 2 Model, Anthropic Claude, Polygon Visualization, Cache Set, Time in Zone, Image Threshold, Mask Visualization, Llama 3.2 Vision, Line Counter, Model Monitoring Inference Aggregator, Stability AI Inpainting, Detection Offset, Classification Label Visualization, OpenAI, Line Counter Visualization, Perspective Correction, Clip Comparison, Depth Estimation, Label Visualization, SIFT Comparison, Anthropic Claude, LMM, SAM 3

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Keypoint Detection Model in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • model_id (roboflow_model_id): Roboflow model identifier..
  • confidence (float_zero_to_one): Confidence threshold for predictions..
  • keypoint_confidence (float_zero_to_one): Confidence threshold to predict a keypoint as visible..
  • class_filter (list_of_values): List of accepted classes. Classes must exist in the model's training set..
  • iou_threshold (float_zero_to_one): Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more..
  • max_detections (integer): Maximum number of detections to return..
  • class_agnostic_nms (boolean): Boolean flag to specify if NMS is to be used in class-agnostic mode..
  • max_candidates (integer): Maximum number of candidates as NMS input to be taken into account..
  • disable_active_learning (boolean): Boolean flag to disable project-level active learning for this block..
  • active_learning_target_dataset (roboflow_project): Target dataset for active learning, if enabled..

• output

  • inference_id (string): String value.
  • predictions (keypoint_detection_prediction): Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object.

Example JSON definition of step Keypoint Detection Model in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/roboflow_keypoint_detection_model@v1",
    "images": "$inputs.image",
    "model_id": "my_project/3",
    "confidence": 0.3,
    "keypoint_confidence": 0.3,
    "class_filter": [
        "a",
        "b",
        "c"
    ],
    "iou_threshold": 0.4,
    "max_detections": 300,
    "class_agnostic_nms": true,
    "max_candidates": 3000,
    "disable_active_learning": true,
    "active_learning_target_dataset": "my_project"
}