> For the complete documentation index, see [llms.txt](https://sogni.gitbook.io/sogni-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sogni.gitbook.io/sogni-docs/sogni-pocket/advanced-features/controlnet/face-and-pose-capture.md).

# Face and Pose Capture

<figure><img src="/files/JZ0IowsQRLJmJst7yMXK" alt=""><figcaption></figcaption></figure>

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](https://youtu.be/RH0-jM6TZYY?si=F3dgfUO2ROkUuCG0)

### OpenPose ControlNet Model

&#x20;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&#x20;

* 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.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://sogni.gitbook.io/sogni-docs/sogni-pocket/advanced-features/controlnet/face-and-pose-capture.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.