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

# Pixverse C1 Reference Image to Video

The Pixverse C1 reference image-to-video tool can generate cinematic videos from 1-7 reference images. It uses the @ref\_name syntax to reference images in the prompt, and supports multi-character/object consistency, multiple resolutions (360p-1080p), variable durations (1-15 seconds), and audio generation.

<Tip>
  This is an **asynchronous** API and will only return the task\_id of the async task. You should use this task\_id to request the [Get Task Result API](/en/docs/models/reference-get-async-task-result) to retrieve the generated result.
</Tip>

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum value: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="images" type="object[]" required={true}>
  List of reference images (1-7 images)

  Array length: 1 - 7

  <Expandable title="properties" defaultOpen={true}>
    <ParamField body="type" type="string" required={true}>
      Reference image type: subject indicates video generation using the person/object in the reference image as the subject; background indicates video generation using the scene/environment in the reference image as the background

      Allowed values: `subject`, `background`
    </ParamField>

    <ParamField body="ref_name" type="string" required={true}>
      A short identifier name for the reference image, used to reference the image in the prompt via the @ref\_name syntax. @ref\_name must be followed by a space
    </ParamField>

    <ParamField body="image_url" type="string" required={true}>
      URL of the reference image
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="prompt" type="string" required={true}>
  Scene description text. Use the @ref\_name syntax to reference uploaded reference images (for example, "@hero running through @city"). @ref\_name must be followed by a space, and the reference name must match the ref\_name in images
</ParamField>

<ParamField body="duration" type="integer" default={5}>
  Duration of the generated video (seconds), range 1-15

  Value range: \[1, 15]
</ParamField>

<ParamField body="resolution" type="string" default="720p">
  Resolution of the output video

  Allowed values: `360p`, `540p`, `720p`, `1080p`
</ParamField>

<ParamField body="aspect_ratio" type="string" default="16:9">
  Aspect ratio of the output video

  Allowed values: `16:9`, `4:3`, `1:1`, `3:4`, `9:16`, `2:3`, `3:2`, `21:9`
</ParamField>

<ParamField body="generate_audio_switch" type="boolean" default={false}>
  Whether to also generate native video audio
</ParamField>

## Response

<ResponseField name="task_id" type="string" required={true}>
  Use the task\_id to request the [Get Task Result API](/en/docs/models/reference-get-async-task-result) to retrieve the generated output.
</ResponseField>