> ## 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.

# Kling V2.1 Master Image-to-Video

Kling 2.1 Master is the flagship version of the Kling 2.1 series, featuring top-tier image-to-video generation capabilities, exceptional motion smoothness, cinematic visual effects, outstanding prompt understanding, and support for 1080p HD video output.

<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="image" type="string" required={true}>
  The first-frame image for the video; supported image formats include `.jpg`, `.jpeg`, and `.png`; the image file size must not exceed 10MB, and the resolution must be at least 300\*300 pixels.
</ParamField>

<ParamField body="prompt" type="string" required={true}>
  The positive prompt text for generating the video; must not exceed 2500 characters.
</ParamField>

<ParamField body="duration" type="string" default="5">
  The duration of the generated video (unit: seconds).

  Optional values: `5`, `10`
</ParamField>

<ParamField body="guidance_scale" type="number" default={0.5}>
  Guidance strength parameter, controlling how closely the generated content follows the prompt.

  Value range: 0 to 1<br />
  Step size: 0.01
</ParamField>

<ParamField body="negative_prompt" type="string">
  Negative prompt, used to avoid undesired content; must not exceed 2500 characters.
</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 obtain the generation result
</ResponseField>