Skip to main content
POST
KLING V1.6 Image-to-Video
KLING V1.6 Image-to-Video is an AI image-to-video generation model developed by the Kuaishou AI team. It can convert images into dynamic 5-second videos, supports 720p / 1080p resolutions, and provides high-quality visual output with enhanced motion and semantic understanding.
This is an asynchronous API and will only return the asynchronous task’s task_id. You should use that 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
Video generation mode.Supported:
  • Standard: Fast generation, lower cost, generates 720p videos.
  • Professional: High quality, higher cost, generates 1080p videos, and allows setting an end frame.
Default value: Standard.
string
required
URL of the starting-frame image used for video generation.
string
URL of the ending-frame image used for video generation.
Available only when mode is Professional.
string
required
The prompt used to guide the generation.Value range: 1 <= x <= 2000.
string
Negative prompt, used to indicate what the model should avoid generating.Value range: 0 <= x <= 2000.
integer
Duration of the generated video (seconds). Default value: 5.
Available values: 5, 10
float
Guidance strength parameter, controlling how closely the generated content follows the prompt.Value range: 0 <= x <= 1. Default value: 0.5.

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