This ComfyUI tutorial walks you through SDPose-OOD: Video to Pose Map — a workflow that converts any input video into a clean pose map sequence. The pipeline starts with LoadVideo to decode frames, runs each frame through the SDPose-OOD pose extractor (backed by the sdpose_wholebody_fp16.safetensors checkpoint) to detect whole-body keypoints, and then assembles the pose frames into a final clip with CreateVideo and SaveVideo. The SDPose-OOD node (type ID 01b6a731-fb78-4070-9a38-c87146da9604) supports multi-person detection and outputs a rendered pose map per frame, covering body, hands, and face landmarks.

Technically, the SDPose-OOD model estimates 2D keypoints for every visible person in each frame, then the node renders those landmarks as a pose map image (skeleton/lines and joints) that’s consistent across the sequence. By keeping the original frame rate and dimensions from LoadVideo, CreateVideo can produce a pose video that aligns one-to-one with the source timing, making it ideal as conditioning for downstream generation (e.g., pose-guided image/video synthesis) or for motion analysis and pre-visualization. SaveVideo finalizes the result to your chosen location and codec.