Source: https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-and-pose-capture/

# Face and Pose Capture

Face and Pose Capture pulls a stick-figure skeleton (and optionally a set of face landmarks) out of a reference image, then uses that skeleton to compose the generation. The output can be a different person, an alien, a robot, or a stylized character — the _pose_ and _facial structure_ come from the reference, but the identity, style, and setting come from your prompt.

This is the OpenPose ControlNet, running inside Pocket. It works from a still you've selected from your library or a live camera capture.

[Watch the tutorial video](https://youtu.be/RH0-jM6TZYY)

## [#](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-and-pose-capture/#what-it-captures)What it captures

Two complementary signals you can use together or separately:

### [#](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-and-pose-capture/#pose-capture)Pose Capture

Analyzes full-body posture and produces a "bones and joints" skeleton — torso, limbs, hands, head position. This is what locks the silhouette of your output to the reference. Sports, dance, action, choreography, hero shots: anywhere you care that the body is doing a specific thing.

### [#](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-and-pose-capture/#face-capture)Face Capture

Detects faces and marks their landmarks — eyes, eyebrows, mouth, jaw. This carries over the _expression_ and _angle_ of the face, but **not the identity**. The model still invents the face; it just constrains how that face is posed and what it's emoting. (If you want identity preservation, use [Face Transfer](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-transfer/) instead.)

Both signals feed the same OpenPose ControlNet model alongside your prompt.

## [#](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-and-pose-capture/#how-to-start)How to start

1.  Open Advanced Guidance and tap **Pose & Facial Expressions**.
2.  Choose a reference: pick an image from your library or use the live camera.
3.  Toggle Face Capture and/or Pose Capture depending on what you want to keep.
4.  Write a prompt for the new subject and style.
5.  Generate.

## [#](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-and-pose-capture/#when-to-use-each)When to use each

| You want to keep | Turn on |
| --- | --- |
| Body posture only | Pose |
| Expression and head angle only | Face |
| Both — a full performance | Both |

Use Pose alone when the subject shouldn't have a human face at all (a robot, a mech, an animal in a human stance).

## [#](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-and-pose-capture/#prompt-tips)Prompt tips

-   **Describe the subject, not the pose.** The skeleton already encodes the pose. Spend tokens on who and what — "a samurai in storm-lit rain, ink wash style."
-   **If unwanted human faces keep showing up**, add "human face" to the **Avoid** prompt field. Pose can pull faces in even when you didn't want them.
-   **Lower ControlNet strength to about 75%** to give the model more freedom with the body — useful when the reference pose is anatomically extreme.
-   **Match camera framing in the prompt** — "full body shot," "from above," "low angle." The skeleton doesn't carry the lens.

## [#](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-and-pose-capture/#workflows)Workflows

**Celebrity pose, different subject.** Reference a famous magazine cover or movie still, capture the pose, prompt for a completely different character. Common for fan art and album covers.

**Choreography reference.** Capture a dancer mid-move from a photo; prompt for a stylized character to repeat the move. Good for storyboarding music videos.

**Sports and action.** A snapshot of an athlete becomes a comic-book superhero, a video-game character, or a fantasy warrior in the same moment of motion.

**Consistent character poses.** Use the same skeleton across several generations to build a turn-around or pose sheet, then re-prompt for variations.

## [#](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-and-pose-capture/#tips)Tips

-   One clear subject in the reference works best. Crowds confuse the skeleton.
-   High-contrast, well-lit references give cleaner skeletons.
-   Pose and Face can run together — they are not exclusive.
-   If hands look broken, that's expected: hand keypoints are the noisiest part of OpenPose. Closing the prompt with "detailed hands" or accepting that limitation are both valid.

## [#](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-and-pose-capture/#see-also)See also

[ControlNet— the four Pocket guidance modes.](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/)[Face Transfer— when you want the actual face, not just its pose.](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/face-transfer/)[Sketch a Masterpiece— guide by drawn lines instead of a photographed body.](https://docs.sogni.ai/sogni-create/pocket/advanced-features/controlnet/sketch-a-masterpiece/)[Advanced Features— Pocket's other power tools.](https://docs.sogni.ai/sogni-create/pocket/advanced-features/)