What does OpenPose ControlNet control?

It controls the pose and position of human figures by extracting a skeleton of keypoints (joints) from a reference and forcing the generated person to match it. It controls posture, not appearance — clothing, style, and background still come from your prompt.

Which OpenPose model variant should I use?

Use body-only for simple full-figure poses. Use body plus hands and face when expressions or precise finger positions matter — though hand keypoints are error-prone. Use hands-only when you just need to fix gestures on an otherwise good generation.

What control strength works best?

A strength around 0.8 to 1.0 reproduces the pose faithfully and suits product or reference work. Drop to 0.5 to 0.7 when you want the model freedom to adjust the pose naturally to the prompt. Below 0.4 the pose becomes a loose suggestion the model may ignore.

Why do hands come out wrong even with OpenPose?

Hand keypoint detection is far less reliable than body detection, and diffusion models already struggle with hands. The hands-and-face model helps but does not guarantee correct fingers. Often the best workflow is to fix the body pose with OpenPose and clean up hands separately with inpainting.

OpenPose ControlNet Guide

OpenPose ControlNet guide

OpenPose is the ControlNet preprocessor for human pose. It reduces a reference figure to a skeleton of keypoints — joints connected by colored limbs — and forces the generated person to adopt that exact posture. It controls position, not appearance: the prompt still decides who the person is, what they wear, and where they are. The two decisions that matter most are which model variant you use and how much control strength you apply.

How it works

The OpenPose preprocessor detects keypoints (shoulders, elbows, wrists, hips, knees, ankles, and optionally face landmarks and finger joints) and draws them as a stick-figure map. ControlNet feeds that map alongside your prompt, biasing the diffusion process toward a person in that pose. The body-only model handles posture; the body + hands + face model adds expression and finger control (less reliably); the hands-only model targets gestures alone. Control strength scales how strongly the map constrains the result.

Tips for reliable poses

Pick the smallest model that covers your need. Body-only is the most robust; only add hands and face when you genuinely need them.
Use strength 0.8–1.0 for faithful reproduction, 0.5–0.7 when you want the model to adapt the pose to the prompt naturally.
Don’t trust hand keypoints. Fix the body with OpenPose, then repair hands with inpainting — detection there is unreliable.
Clean reference, clean pose. A clear, well-lit single figure produces a far better keypoint map than a crowded or low-contrast image.