Skip to main content
POST
Kling V2.1 Image-to-Video
Kling V2.1 is Kuaishou’s latest-generation AI-powered image-to-video model. It can generate high-quality, cinematic short videos from a single image or text prompt with one click. Compared with Kling 2.0, version 2.1 delivers major breakthroughs in motion smoothness, visual consistency, and prompt understanding.
This is an asynchronous API and only returns the asynchronous task’s task_id. You should use this task_id to request the Get Task Result API to retrieve the video generation result.

Request Headers

string
required
Enum value: application/json
string
required
Bearer authentication format: Bearer {{API key}}.

Request Body

string
required
The first-frame image of 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.
string
required
The positive text prompt for generating the video, up to 2500 characters.
string
Video generation mode.Supported:
  • Standard: Fast generation, low cost, generates 720p videos.
  • Professional: High quality, high cost, generates 1080p videos.
Default value: Standard.
string
default:"5"
The duration of the generated video (in seconds).Available values: 5, 10
number
Guidance strength parameter, controlling how closely the generated content follows the prompt.Value range: 0 to 1
Step: 0.01
string
Negative prompt, used to avoid undesired content; no more than 2500 characters.

Response Information

string
required
The task_id of the asynchronous task. You should use this task_id to request the Get Task Result API to obtain the generation result.