AnimalPose Estimator (AP10K)

ControlNet Preprocessors/Faces and Poses Estimators

AnimalPosePreprocessor

Example

JSON Example

{
  "class_type": "AnimalPosePreprocessor",
  "inputs": {
    "image": [
      "node_id",
      0
    ]
  }
}

This example shows required inputs only. Connection values like ["node_id", 0] should reference actual node IDs from your workflow.

Inputs

Name	Type	Status	Constraints	Default
image	IMAGE	required	-	-
bbox_detector	ENUM 6 options None yolox_l.torchscript.pt yolox_l.onnx yolo_nas_l_fp16.onnx yolo_nas_m_fp16.onnx yolo_nas_s_fp16.onnx	optional	-	"yolox_l.torchscript.pt"
pose_estimator	ENUM 2 options rtmpose-m_ap10k_256_bs5.torchscript.pt rtmpose-m_ap10k_256.onnx	optional	-	"rtmpose-m_ap10k_256_bs5.torchscript.pt"
resolution	INT	optional	min: 64, max: 16384, step: 64	512

Outputs

Index	Name	Type	Is List	Connection Reference
0	IMAGE	IMAGE	No	["{node_id}", 0]
1	POSE_KEYPOINT	POSE_KEYPOINT	No	["{node_id}", 1]

How to connect to these outputs

To connect another node's input to an output from this node, use the connection reference format:

["node_id", output_index]

Where node_id is the ID of this AnimalPosePreprocessor node in your workflow, and output_index is the index from the table above.

Example

If this node has ID "5" in your workflow:

• IMAGE (IMAGE): ["5", 0]
• POSE_KEYPOINT (POSE_KEYPOINT): ["5", 1]

Package: comfyui-controlnet-aux