ComfyUI Node
Wan Pose Detect — YOLO + ViTPose (V2)
Standalone YOLO + ViTPose detection. Takes an IMAGE batch and a POSEMODEL bundle (from OnnxDetectionModelLoaderV2) and emits a POSEDATA bundle compatible with the V2 editor and downstream conditioning nodes. No face-cropping / gaze pipeline — keypoints only.
Wan Pose Detect — YOLO + ViTPose (V2)
- images
- model
- pose_data
- info
◄detection_threshold0.30►
◄pose_threshold0.30►
◄use_clahetrue►
◄use_blur_for_posefalse►
◄blur_radius2►
◄blur_sigma1.5►
◄rescale1.25►
◄fallback_to_full_frametrue►
CategoryWanAnimatePreprocessV2/extras
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| images | IMAGE | RGB image stack to detect poses on. Float [0,1], shape (B,H,W,3). | |
| model | POSEMODEL | ViTPose+YOLO bundle from OnnxDetectionModelLoaderV2. | |
| detection_thresholdopt | FLOAT | 0.300–1 | YOLO person-detection confidence threshold. |
| pose_thresholdopt | FLOAT | 0.300–1 | Per-keypoint confidence threshold; below this the keypoint's confidence is forced to 0. |
| use_claheopt | BOOLEAN | true | CLAHE contrast enhancement on the 256x192 pose crop. Matches the main preprocessor default. |
| use_blur_for_poseopt | BOOLEAN | false | Apply a Gaussian blur to the images before YOLO+ViTPose (anti-aliases noisy frames). |
| blur_radiusopt | INT | 20–32 | — |
| blur_sigmaopt | FLOAT | 1.50–8 | — |
| rescaleopt | FLOAT | 1.251–2 | Bbox padding factor before crop for ViTPose. 1.25 = match the main preprocessor. |
| fallback_to_full_frameopt | BOOLEAN | true | If YOLO finds no person in a frame, run ViTPose on the entire frame instead of skipping it. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| pose_data | POSEDATA | — |
| info | STRING | — |