Keypoint Detection Model¶
v3¶
Class: RoboflowKeypointDetectionModelBlockV3 (there are multiple versions of this block)
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@v3to 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_mode |
str |
not available. | ✅ |
custom_confidence |
float |
not available. | ✅ |
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 v3.
- inputs:
Icon Visualization,Slack Notification,Label Visualization,Instance Segmentation Model,Multi-Label Classification Model,Dot Visualization,Camera Calibration,Trace Visualization,Roboflow Custom Metadata,Dynamic Zone,Semantic Segmentation Model,Relative Static Crop,Image Threshold,Keypoint Visualization,PTZ Tracking (ONVIF),Template Matching,Single-Label Classification Model,Blur Visualization,Circle Visualization,Keypoint Detection Model,Crop Visualization,Email Notification,Classification Label Visualization,OpenAI,Google Gemini,OpenAI,Identify Outliers,Twilio SMS Notification,CSV Formatter,Twilio SMS/MMS Notification,Model Monitoring Inference Aggregator,Keypoint Detection Model,Anthropic Claude,Google Gemini,Image Convert Grayscale,Distance Measurement,Stability AI Inpainting,Depth Estimation,S3 Sink,Model Comparison Visualization,Motion Detection,Google Gemini,Detections List Roll-Up,Florence-2 Model,LMM,Size Measurement,Dynamic Crop,Clip Comparison,SIFT Comparison,Multi-Label Classification Model,VLM As Detector,Grid Visualization,Polygon Visualization,Mask Visualization,Semantic Segmentation Model,Webhook Sink,Image Slicer,OCR Model,Detection Event Log,Object Detection Model,Object Detection Model,GLM-OCR,Roboflow Dataset Upload,Object Detection Model,Polygon Zone Visualization,SIFT,Morphological Transformation,Perspective Correction,Instance Segmentation Model,Anthropic Claude,Image Slicer,Absolute Static Crop,Email Notification,Camera Focus,EasyOCR,Polygon Visualization,OpenAI,VLM As Classifier,Stitch OCR Detections,Color Visualization,Local File Sink,Line Counter,Image Contours,Roboflow Vision Events,OpenAI,Single-Label Classification Model,Llama 3.2 Vision,Clip Comparison,Instance Segmentation Model,VLM As Detector,JSON Parser,Triangle Visualization,LMM For Classification,Pixel Color Count,Background Color Visualization,Stitch OCR Detections,Identify Changes,Line Counter,Qwen3.5-VL,CogVLM,Image Blur,Stitch Images,Anthropic Claude,Contrast Equalization,Corner Visualization,Halo Visualization,Stability AI Image Generation,Detections Consensus,Reference Path Visualization,Buffer,Line Counter Visualization,Multi-Label Classification Model,Keypoint Detection Model,Roboflow Dataset Upload,Heatmap Visualization,Text Display,VLM As Classifier,Camera Focus,Single-Label Classification Model,Image Preprocessing,SIFT Comparison,Bounding Box Visualization,Stability AI Outpainting,Halo Visualization,Background Subtraction,Dimension Collapse,QR Code Generator,Pixelate Visualization,Ellipse Visualization,Google Vision OCR,Florence-2 Model - outputs:
Icon Visualization,Triangle Visualization,Moondream2,Background Color Visualization,Roboflow Dataset Upload,Label Visualization,Instance Segmentation Model,Multi-Label Classification Model,Object Detection Model,Model Comparison Visualization,Qwen3.5-VL,Dot Visualization,Qwen2.5-VL,Trace Visualization,SAM2 Video Tracker,SAM 3,Roboflow Custom Metadata,Corner Visualization,Detections Classes Replacement,Velocity,Instance Segmentation Model,Detections List Roll-Up,Florence-2 Model,Semantic Segmentation Model,Detections Consensus,Detection Offset,Dynamic Crop,SAM 3,Keypoint Visualization,ByteTrack Tracker,Multi-Label Classification Model,Keypoint Detection Model,Single-Label Classification Model,SmolVLM2,Roboflow Dataset Upload,Heatmap Visualization,Blur Visualization,Circle Visualization,Byte Tracker,Keypoint Detection Model,Segment Anything 2 Model,Crop Visualization,Detections Merge,Multi-Label Classification Model,SAM 3,Single-Label Classification Model,Semantic Segmentation Model,Webhook Sink,Detections Transformation,Color Visualization,SORT Tracker,Bounding Box Visualization,OC-SORT Tracker,Model Monitoring Inference Aggregator,Keypoint Detection Model,Roboflow Vision Events,Qwen3-VL,Object Detection Model,Object Detection Model,Single-Label Classification Model,GLM-OCR,Detections Filter,Pixelate Visualization,Ellipse Visualization,Instance Segmentation Model,Florence-2 Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Keypoint Detection Model in version v3 has.
Bindings
-
input
images(image): The image to infer on..model_id(roboflow_model_id): Roboflow model identifier..confidence_mode(string): not available.custom_confidence(float_zero_to_one): not available.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 v3
{
"name": "<your_step_name_here>",
"type": "roboflow_core/roboflow_keypoint_detection_model@v3",
"images": "$inputs.image",
"model_id": "my_project/3",
"confidence_mode": "<block_does_not_provide_example>",
"custom_confidence": "<block_does_not_provide_example>",
"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"
}
v2¶
Class: RoboflowKeypointDetectionModelBlockV2 (there are multiple versions of this block)
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:
Icon Visualization,Roboflow Dataset Upload,Slack Notification,Label Visualization,Multi-Label Classification Model,Dot Visualization,Camera Calibration,Polygon Zone Visualization,SIFT,Trace Visualization,Morphological Transformation,Perspective Correction,Instance Segmentation Model,Dynamic Zone,Roboflow Custom Metadata,Florence-2 Model,Semantic Segmentation Model,Anthropic Claude,Relative Static Crop,Image Slicer,Image Threshold,Keypoint Visualization,PTZ Tracking (ONVIF),Template Matching,Absolute Static Crop,Single-Label Classification Model,Blur Visualization,Circle Visualization,Email Notification,Keypoint Detection Model,Camera Focus,Crop Visualization,Email Notification,Classification Label Visualization,OpenAI,Google Gemini,OpenAI,Polygon Visualization,Identify Outliers,VLM As Classifier,Color Visualization,Line Counter,Local File Sink,Twilio SMS Notification,Twilio SMS/MMS Notification,Image Contours,Model Monitoring Inference Aggregator,Anthropic Claude,Roboflow Vision Events,OpenAI,Google Gemini,Image Convert Grayscale,Single-Label Classification Model,Llama 3.2 Vision,Distance Measurement,Clip Comparison,Instance Segmentation Model,VLM As Detector,JSON Parser,Triangle Visualization,Stability AI Inpainting,Pixel Color Count,Background Color Visualization,Identify Changes,Depth Estimation,Line Counter,S3 Sink,Model Comparison Visualization,Image Blur,Stitch Images,Anthropic Claude,Motion Detection,Contrast Equalization,Google Gemini,Corner Visualization,Detections List Roll-Up,Halo Visualization,Stability AI Image Generation,Florence-2 Model,Detections Consensus,Reference Path Visualization,Size Measurement,Buffer,Dynamic Crop,Line Counter Visualization,Clip Comparison,SIFT Comparison,Multi-Label Classification Model,Keypoint Detection Model,Roboflow Dataset Upload,Heatmap Visualization,Text Display,VLM As Classifier,VLM As Detector,Grid Visualization,Polygon Visualization,Camera Focus,Semantic Segmentation Model,Webhook Sink,Image Slicer,Image Preprocessing,SIFT Comparison,Bounding Box Visualization,Stability AI Outpainting,Halo Visualization,Detection Event Log,Background Subtraction,Object Detection Model,Object Detection Model,Dimension Collapse,QR Code Generator,Pixelate Visualization,Ellipse Visualization,Mask Visualization - outputs:
Icon Visualization,Triangle Visualization,Moondream2,Background Color Visualization,Roboflow Dataset Upload,Label Visualization,Instance Segmentation Model,Multi-Label Classification Model,Object Detection Model,Model Comparison Visualization,Qwen3.5-VL,Dot Visualization,Qwen2.5-VL,Trace Visualization,SAM2 Video Tracker,SAM 3,Roboflow Custom Metadata,Corner Visualization,Detections Classes Replacement,Velocity,Instance Segmentation Model,Detections List Roll-Up,Florence-2 Model,Semantic Segmentation Model,Detections Consensus,Detection Offset,Dynamic Crop,SAM 3,Keypoint Visualization,ByteTrack Tracker,Multi-Label Classification Model,Keypoint Detection Model,Single-Label Classification Model,SmolVLM2,Roboflow Dataset Upload,Heatmap Visualization,Blur Visualization,Circle Visualization,Byte Tracker,Keypoint Detection Model,Segment Anything 2 Model,Crop Visualization,Detections Merge,Multi-Label Classification Model,SAM 3,Single-Label Classification Model,Semantic Segmentation Model,Webhook Sink,Detections Transformation,Color Visualization,SORT Tracker,Bounding Box Visualization,OC-SORT Tracker,Model Monitoring Inference Aggregator,Keypoint Detection Model,Roboflow Vision Events,Qwen3-VL,Object Detection Model,Object Detection Model,Single-Label Classification Model,GLM-OCR,Detections Filter,Pixelate Visualization,Ellipse Visualization,Instance Segmentation Model,Florence-2 Model
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)
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:
Icon Visualization,Roboflow Dataset Upload,Slack Notification,Label Visualization,Multi-Label Classification Model,Dot Visualization,Camera Calibration,Polygon Zone Visualization,SIFT,Trace Visualization,Morphological Transformation,Perspective Correction,Instance Segmentation Model,Dynamic Zone,Roboflow Custom Metadata,Florence-2 Model,Semantic Segmentation Model,Anthropic Claude,Relative Static Crop,Image Slicer,Image Threshold,Keypoint Visualization,PTZ Tracking (ONVIF),Template Matching,Absolute Static Crop,Single-Label Classification Model,Blur Visualization,Circle Visualization,Email Notification,Keypoint Detection Model,Camera Focus,Crop Visualization,Email Notification,Classification Label Visualization,OpenAI,Google Gemini,OpenAI,Polygon Visualization,Identify Outliers,VLM As Classifier,Color Visualization,Line Counter,Local File Sink,Twilio SMS Notification,Twilio SMS/MMS Notification,Image Contours,Model Monitoring Inference Aggregator,Anthropic Claude,Roboflow Vision Events,OpenAI,Google Gemini,Image Convert Grayscale,Single-Label Classification Model,Llama 3.2 Vision,Distance Measurement,Clip Comparison,Instance Segmentation Model,VLM As Detector,JSON Parser,Triangle Visualization,Stability AI Inpainting,Pixel Color Count,Background Color Visualization,Identify Changes,Depth Estimation,Line Counter,S3 Sink,Model Comparison Visualization,Image Blur,Stitch Images,Anthropic Claude,Motion Detection,Contrast Equalization,Google Gemini,Corner Visualization,Detections List Roll-Up,Halo Visualization,Stability AI Image Generation,Florence-2 Model,Detections Consensus,Reference Path Visualization,Size Measurement,Buffer,Dynamic Crop,Line Counter Visualization,Clip Comparison,SIFT Comparison,Multi-Label Classification Model,Keypoint Detection Model,Roboflow Dataset Upload,Heatmap Visualization,Text Display,VLM As Classifier,VLM As Detector,Grid Visualization,Polygon Visualization,Camera Focus,Semantic Segmentation Model,Webhook Sink,Image Slicer,Image Preprocessing,SIFT Comparison,Bounding Box Visualization,Stability AI Outpainting,Halo Visualization,Detection Event Log,Background Subtraction,Object Detection Model,Object Detection Model,Dimension Collapse,QR Code Generator,Pixelate Visualization,Ellipse Visualization,Mask Visualization - outputs:
Icon Visualization,Moondream2,Roboflow Dataset Upload,Slack Notification,Label Visualization,Instance Segmentation Model,Dot Visualization,Trace Visualization,Polygon Zone Visualization,Detections Stitch,SAM 3,Time in Zone,Roboflow Custom Metadata,Morphological Transformation,Instance Segmentation Model,Perspective Correction,Florence-2 Model,Semantic Segmentation Model,Cache Get,Anthropic Claude,Image Threshold,Keypoint Visualization,PTZ Tracking (ONVIF),Single-Label Classification Model,Cache Set,Blur Visualization,Circle Visualization,Email Notification,Crop Visualization,Email Notification,Classification Label Visualization,OpenAI,SAM 3,Detections Merge,OpenAI,Google Gemini,Polygon Visualization,OpenAI,Stitch OCR Detections,Color Visualization,Twilio SMS Notification,YOLO-World Model,Local File Sink,Line Counter,Twilio SMS/MMS Notification,Model Monitoring Inference Aggregator,Anthropic Claude,Roboflow Vision Events,OpenAI,Path Deviation,Google Gemini,Llama 3.2 Vision,Time in Zone,Detections Filter,Distance Measurement,Clip Comparison,Instance Segmentation Model,Time in Zone,Triangle Visualization,Stability AI Inpainting,LMM For Classification,Pixel Color Count,Background Color Visualization,Stitch OCR Detections,S3 Sink,Depth Estimation,Line Counter,Model Comparison Visualization,CogVLM,Anthropic Claude,Image Blur,SAM2 Video Tracker,Google Gemini,Contrast Equalization,Corner Visualization,Detections Classes Replacement,Velocity,Detections List Roll-Up,CLIP Embedding Model,Florence-2 Model,Stability AI Image Generation,Halo Visualization,Detections Consensus,Reference Path Visualization,Size Measurement,LMM,Dynamic Crop,Line Counter Visualization,SAM 3,Detection Offset,Perception Encoder Embedding Model,Multi-Label Classification Model,ByteTrack Tracker,Keypoint Detection Model,Roboflow Dataset Upload,Heatmap Visualization,Text Display,Byte Tracker,Segment Anything 2 Model,Polygon Visualization,Mask Visualization,Webhook Sink,Seg Preview,Detections Transformation,Image Preprocessing,SIFT Comparison,SORT Tracker,Bounding Box Visualization,Stability AI Outpainting,Halo Visualization,OC-SORT Tracker,Object Detection Model,GLM-OCR,QR Code Generator,Pixelate Visualization,Google Vision OCR,Ellipse Visualization,Path Deviation
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"
}