> ## 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.

# Wan 2.5 Preview Image-to-Video

The Wan 2.5 Preview image-to-video model supports generating 5-second or 10-second videos from a first-frame image and text. New audio capabilities: it supports automatic dubbing, and you can also customize the audio file.

<Tip>
  This is an **asynchronous** API and only returns the task\_id of the asynchronous 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 video generation 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="input" type="object" required={true}>
  Basic input information, such as prompts.

  <Expandable title="Field descriptions" defaultOpen={true}>
    <ParamField body="prompt" type="string" required={false}>
      Positive text prompt. Chinese and English are supported, with a maximum length of 2000 characters. Content beyond the limit will be automatically truncated.

      Example value: A kitten running on the grass.
    </ParamField>

    <ParamField body="negative_prompt" type="string" required={false}>
      Negative prompt, used to describe content to avoid when generating the video. It can be used to avoid or limit certain visual elements.

      Chinese and English are supported, with a maximum length of 500 characters. Content beyond the limit will be automatically truncated.

      Example value: low resolution, errors, worst quality, low quality, incomplete, extra fingers, poor proportions, etc.
    </ParamField>

    <ParamField body="img_url" type="string" required={true}>
      The URL of the starting-frame image used for video generation.

      The URL must be publicly accessible and support the HTTP or HTTPS protocol.

      Image restrictions:

      * Image formats: JPEG, JPG, PNG (transparency not supported), BMP, WEBP;
      * Size requirements: image width and height must be within the \[360, 2000] pixel range;
      * File size must not exceed 10 MB.
    </ParamField>

    <ParamField body="audio_url" type="string" required={false}>
      The URL of the audio file used for video generation. For detailed usage, refer to the audio settings description.

      Audio requirements:

      * Formats: wav, mp3;
      * Duration: 3-30 seconds;
      * File size must not exceed 15 MB.

      Handling of overly long audio: If the audio duration exceeds the target video duration (such as 5 seconds or 10 seconds), only the first 5 seconds or first 10 seconds will be kept, and the remaining part will be automatically discarded. If the audio duration is shorter than the video duration, the remaining portion will be silent video. For example, if the audio is 3 seconds and the video is 5 seconds, the first 3 seconds of the output video will have sound, and the last 2 seconds will be silent.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="parameters" type="object" required={false}>
  Video processing parameters, such as specifying the output video resolution, duration, etc.

  <Expandable title="Field descriptions" defaultOpen={true}>
    <ParamField body="resolution" type="string" required={false}>
      Resolution tier of the generated video.<br />
      Options: `480P`, `720P`, `1080P`. Default value: `1080P`.
    </ParamField>

    <ParamField body="duration" type="integer" required={false}>
      Specifies the duration of the generated video. Supported values: `5` or `10` (unit: seconds).

      Default value: `5`.
    </ParamField>

    <ParamField body="prompt_extend" type="bool" required={false}>
      Whether to enable intelligent prompt rewriting. When enabled, a large model will be used to intelligently rewrite the input prompt. This can significantly improve generation quality for shorter prompts, but it will also increase processing time.

      * `true`: Default, enable intelligent rewriting;
      * `false`: Do not rewrite.

      Example value: true.
    </ParamField>

    <ParamField body="audio" type="boolean" required={false}>
      Whether to add audio.

      Parameter priority: audio\_url > audio. This parameter is only effective when audio\_url is empty.

      * `true`: Default, automatically add dubbing to the video;
      * `false`: Do not add audio; the output will be a silent video.

      Example value: true.
    </ParamField>

    <ParamField body="seed" type="integer" required={false}>
      Random seed, used to control the randomness of the content generated by the model. Value range: \[0, 2147483647].

      If not provided, a random number will be generated automatically. If you want more stable generation results, you can pass in the same seed value.

      Example value: 12345.
    </ParamField>
  </Expandable>
</ParamField>

## Response Information

<ResponseField name="task_id" type="string" required={true}>
  The task\_id of the asynchronous 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 generation result
</ResponseField>