> ## Documentation Index
> Fetch the complete documentation index at: https://docs.runable.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Motion Control

> Transfer motion from a reference video onto a still image to create precisely controlled animation.

Motion Control takes motion from a reference video and applies it to a still image. The subject in your image performs the same movements as the subject in the reference video. This gives you precise control over animation without needing to describe motion in words.

<Frame caption="Motion Control concept: a reference video's motion applied to a still image.">
  ![Diagram showing a reference dance video on the left, a still character image in the middle, and the output video on the right where the character performs the dance](https://runable.cloud/assets/feat-2-DvTd8CIw.png)
</Frame>

## How motion control works

<Steps>
  <Step title="Prepare your inputs">
    You need two things:

    * **A still image** - The subject you want to animate (a person, character, mascot, or product).
    * **A reference video** - The motion you want to apply (a dance, a walk, a gesture, or any movement).
  </Step>

  <Step title="Provide both to the agent">
    Upload both the image and the reference video using the **+** button. Describe what you want in the prompt.

    <Prompt description={`Make a character perform a dance from a reference.`} actions={["copy"]}>
      Apply the motion from the reference video to this character image. Keep the character's appearance exactly as shown in the image. Match the body movements from the video.
    </Prompt>

    <Prompt description={`Animate a product mascot with a wave gesture.`} actions={["copy"]}>
      Use the motion from the reference video to animate this mascot. The mascot should wave and turn as shown in the reference. Preserve the mascot's colors and style.
    </Prompt>
  </Step>

  <Step title="Wait for generation">
    The AI processes the motion reference and applies it to your image. A placeholder appears on the canvas while it generates.
  </Step>

  <Step title="Review the result">
    The output video appears on the canvas. Your subject performs the motion from the reference video while keeping its original appearance.

    <Frame caption="The output video on the canvas showing the animated character.">
      <img src="https://mintlify.s3.us-west-1.amazonaws.com/runableinc/images/placeholder.png" alt="Canvas showing the output video of a character performing the dance from the reference video" />
    </Frame>
  </Step>
</Steps>

<Note>
  Motion Control creates a new canvas item. The original image and reference video are preserved. The output video keeps the original sound from the reference video by default.
</Note>

## When to use this

* Making a character or mascot perform a specific dance, gesture, or action.
* Animating a product with precise, repeatable motion.
* Creating consistent motion across multiple characters using the same reference video.
* Producing social media content where a specific movement is required.

## Character orientation

The agent decides whether the character's body follows the reference video's orientation or stays in the original image's pose. By default, the body orientation follows the reference video for the most natural result.

## What you cannot do

* You cannot use motion control with a video as the subject. The subject must be a still image.
* You cannot combine motion from multiple reference videos in a single generation.
* You cannot selectively apply motion to parts of the subject (for example, only the arms).
* You cannot control the duration independently. The output matches the reference video length.

## Next steps

<CardGroup cols={2}>
  <Card icon="pen-to-square" href="/generate-media/ai-videos/edit-a-video" title="Edit a Video">
    Restyle or modify the output video after motion control.
  </Card>

  <Card icon="film" href="/generate-media/ai-videos/combine-into-timeline" title="Combine into Timeline">
    Add the motion-controlled clip to a multi-clip sequence.
  </Card>
</CardGroup>