🕺Face and Pose Capture

Use Face and Pose Capture to gain full control over human expression and posture in your creations. This tool lets you extract facial expressions and body poses from any image, then apply them to your creations using a ControlNet model.

Face Capture

Detects human faces in your selected image and maps their expressions using facial landmarks—like eyes, mouth, and eyebrows. This lets you transfer the emotion, perspective, and structure of a face (Not the actual face itself.) Use your prompt and style settings to control the final appearance.

Pose Capture

Analyzes the full-body posture of people in an image, generating a skeleton-like “bones and joints” map. This gives you precise control over how subjects are posed in your outputs.

▶️ Watch Tutorial Video

OpenPose ControlNet Model

A fast model that interprets both face and body landmark maps to guide the main model—working together with your prompt and other settings.

💡Tips

• Face and Pose Capture can be used simultaneously for even more control.

• Use Pose alone when generating characters that shouldn’t include a human face. If human faces keep appearing in your results, try adding “human face” to the Avoid prompt field. Lowering the ControlNet strength to around 75% can also help by giving the model more freedom.