Keypoint Detection Model¶
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:
Google Gemini,Mask Visualization,Google Gemini,Image Convert Grayscale,Dimension Collapse,Florence-2 Model,VLM As Detector,Identify Outliers,Image Blur,Depth Estimation,Clip Comparison,VLM As Detector,Semantic Segmentation Model,Crop Visualization,Florence-2 Model,Model Monitoring Inference Aggregator,Corner Visualization,Multi-Label Classification Model,Anthropic Claude,Keypoint Visualization,Google Gemini,VLM As Classifier,Clip Comparison,Detections Consensus,VLM As Classifier,Triangle Visualization,Stability AI Inpainting,Stitch Images,Local File Sink,Llama 3.2 Vision,Perspective Correction,Stability AI Image Generation,Reference Path Visualization,Halo Visualization,Trace Visualization,Buffer,Grid Visualization,Polygon Visualization,Polygon Zone Visualization,Motion Detection,PTZ Tracking (ONVIF),Detections List Roll-Up,JSON Parser,Object Detection Model,Template Matching,Identify Changes,Halo Visualization,SIFT Comparison,Size Measurement,Label Visualization,Image Slicer,Dynamic Crop,Distance Measurement,Anthropic Claude,Image Threshold,Instance Segmentation Model,Line Counter Visualization,OpenAI,Email Notification,Slack Notification,Line Counter,Webhook Sink,Stability AI Outpainting,Heatmap Visualization,Ellipse Visualization,Pixel Color Count,Camera Focus,Icon Visualization,SIFT,OpenAI,Roboflow Dataset Upload,Background Color Visualization,SIFT Comparison,Text Display,Keypoint Detection Model,Image Contours,Blur Visualization,Contrast Equalization,Dynamic Zone,QR Code Generator,Dot Visualization,Background Subtraction,Detection Event Log,Color Visualization,Roboflow Dataset Upload,Roboflow Custom Metadata,Twilio SMS Notification,Absolute Static Crop,Relative Static Crop,Bounding Box Visualization,OpenAI,S3 Sink,Polygon Visualization,Twilio SMS/MMS Notification,Camera Calibration,Model Comparison Visualization,Camera Focus,Image Slicer,Circle Visualization,Single-Label Classification Model,Line Counter,Classification Label Visualization,Image Preprocessing,Email Notification,Anthropic Claude,Morphological Transformation,Pixelate Visualization - outputs:
Qwen3-VL,Detections Filter,Instance Segmentation Model,Florence-2 Model,SAM 3,Single-Label Classification Model,Moondream2,GLM-OCR,Multi-Label Classification Model,Webhook Sink,Semantic Segmentation Model,Crop Visualization,Heatmap Visualization,Instance Segmentation Model,SmolVLM2,Ellipse Visualization,Model Monitoring Inference Aggregator,Florence-2 Model,Icon Visualization,Roboflow Dataset Upload,Corner Visualization,Qwen2.5-VL,Background Color Visualization,Multi-Label Classification Model,OC-SORT Tracker,Velocity,Keypoint Detection Model,Keypoint Visualization,Detection Offset,SORT Tracker,Detections Consensus,Qwen3.5-VL,Triangle Visualization,Blur Visualization,Keypoint Detection Model,Pixelate Visualization,Dot Visualization,Roboflow Dataset Upload,Trace Visualization,Color Visualization,Roboflow Custom Metadata,Bounding Box Visualization,Byte Tracker,ByteTrack Tracker,SAM 3,Detections Classes Replacement,Detections Transformation,Segment Anything 2 Model,Model Comparison Visualization,Detections List Roll-Up,Circle Visualization,Single-Label Classification Model,Object Detection Model,SAM 3,Detections Merge,Object Detection Model,Label Visualization,Dynamic Crop
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:
Google Gemini,Mask Visualization,Google Gemini,Image Convert Grayscale,Dimension Collapse,Florence-2 Model,VLM As Detector,Identify Outliers,Image Blur,Depth Estimation,Clip Comparison,VLM As Detector,Semantic Segmentation Model,Crop Visualization,Florence-2 Model,Model Monitoring Inference Aggregator,Corner Visualization,Multi-Label Classification Model,Anthropic Claude,Keypoint Visualization,Google Gemini,VLM As Classifier,Clip Comparison,Detections Consensus,VLM As Classifier,Triangle Visualization,Stability AI Inpainting,Stitch Images,Local File Sink,Llama 3.2 Vision,Perspective Correction,Stability AI Image Generation,Reference Path Visualization,Halo Visualization,Trace Visualization,Buffer,Grid Visualization,Polygon Visualization,Polygon Zone Visualization,Motion Detection,PTZ Tracking (ONVIF),Detections List Roll-Up,JSON Parser,Object Detection Model,Template Matching,Identify Changes,Halo Visualization,SIFT Comparison,Size Measurement,Label Visualization,Image Slicer,Dynamic Crop,Distance Measurement,Anthropic Claude,Image Threshold,Instance Segmentation Model,Line Counter Visualization,OpenAI,Email Notification,Slack Notification,Line Counter,Webhook Sink,Stability AI Outpainting,Heatmap Visualization,Ellipse Visualization,Pixel Color Count,Camera Focus,Icon Visualization,SIFT,OpenAI,Roboflow Dataset Upload,Background Color Visualization,SIFT Comparison,Text Display,Keypoint Detection Model,Image Contours,Blur Visualization,Contrast Equalization,Dynamic Zone,QR Code Generator,Dot Visualization,Background Subtraction,Detection Event Log,Color Visualization,Roboflow Dataset Upload,Roboflow Custom Metadata,Twilio SMS Notification,Absolute Static Crop,Relative Static Crop,Bounding Box Visualization,OpenAI,S3 Sink,Polygon Visualization,Twilio SMS/MMS Notification,Camera Calibration,Model Comparison Visualization,Camera Focus,Image Slicer,Circle Visualization,Single-Label Classification Model,Line Counter,Classification Label Visualization,Image Preprocessing,Email Notification,Anthropic Claude,Morphological Transformation,Pixelate Visualization - outputs:
Google Gemini,Google Vision OCR,Mask Visualization,Google Gemini,Path Deviation,Detections Filter,Florence-2 Model,Image Blur,GLM-OCR,Cache Set,Depth Estimation,Crop Visualization,Model Monitoring Inference Aggregator,Florence-2 Model,Corner Visualization,Cache Get,Anthropic Claude,OC-SORT Tracker,Keypoint Visualization,Google Gemini,Seg Preview,Clip Comparison,SORT Tracker,Detections Consensus,Triangle Visualization,OpenAI,Stability AI Inpainting,Llama 3.2 Vision,Perspective Correction,Stability AI Image Generation,YOLO-World Model,Reference Path Visualization,Halo Visualization,Trace Visualization,Polygon Visualization,Polygon Zone Visualization,Stitch OCR Detections,CogVLM,Detections Stitch,PTZ Tracking (ONVIF),Detections List Roll-Up,Stitch OCR Detections,Time in Zone,CLIP Embedding Model,SAM 3,Halo Visualization,SIFT Comparison,Size Measurement,Label Visualization,Dynamic Crop,Distance Measurement,Perception Encoder Embedding Model,Anthropic Claude,Image Threshold,Instance Segmentation Model,Line Counter Visualization,OpenAI,Email Notification,SAM 3,Slack Notification,Time in Zone,Moondream2,Line Counter,Webhook Sink,Stability AI Outpainting,Instance Segmentation Model,Heatmap Visualization,Ellipse Visualization,Pixel Color Count,LMM For Classification,Icon Visualization,Roboflow Dataset Upload,OpenAI,Background Color Visualization,Text Display,Time in Zone,Velocity,Detection Offset,LMM,Contrast Equalization,Blur Visualization,QR Code Generator,Dot Visualization,Roboflow Dataset Upload,Color Visualization,Roboflow Custom Metadata,Twilio SMS Notification,Bounding Box Visualization,S3 Sink,OpenAI,Byte Tracker,Twilio SMS/MMS Notification,Polygon Visualization,ByteTrack Tracker,SAM 3,Detections Classes Replacement,Segment Anything 2 Model,Detections Transformation,Model Comparison Visualization,Email Notification,Circle Visualization,Line Counter,Morphological Transformation,Classification Label Visualization,Image Preprocessing,Local File Sink,Detections Merge,Anthropic Claude,Path Deviation,Pixelate Visualization
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"
}