Does this workflow support multiple people in the same frame?

Yes. The SDPose-OOD node supports multi-person detection and will render pose maps for all detected subjects per frame. For crowded scenes, consider raising the confidence threshold to reduce false positives.

Which model file do I need and where should it go?

Use sdpose_wholebody_fp16.safetensors. Place it in ComfyUI/models/checkpoints/. Then select it in the SDPose-OOD node before running the workflow.

How do I keep the output aligned with the source video?

Pass the frame rate from LoadVideo into CreateVideo, and keep the output resolution consistent with the input. This preserves one-to-one timing and sizing for downstream use.

What can I do if detection is jittery or misses hands/face?

Try increasing the input resolution for clearer details, raise the detection confidence to reduce noise, and ensure good lighting and contrast in the source. For performance-constrained GPUs, balance resolution and frame skip to maintain stability.

SDPose-OOD: Video to Pose Map

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.

API

Use this workflow from code

Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.

utility_sdpose_ood_video_to_pose_map.json

Fetching workflow JSON…

Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.

// Install (beta)
npm i @comfyorg/sdk

// Run "SDPose-OOD: Video to Pose Map" (TypeScript)
import { Comfy } from "@comfyorg/sdk";

const client = new Comfy({ apiKey: "comfyui-..." });

// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("utility_sdpose_ood_video_to_pose_map_api.json");

const job = await client.run(wf);
await job.getOutputs("680")[0].toFile("output.png");  // SaveVideo

The SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).

Comfy Cloud API access requires a plan with an API key.

SDK docs Get an API key

FAQ