Skip to main content
POST
/
v3
/
async
/
kling-v3.0-4k-i2v
Kling v3.0 4K Image-to-Video
curl --request POST \
  --url https://api.highwayapi.ai/v3/async/kling-v3.0-4k-i2v \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "image": "<string>",
  "sound": true,
  "prompt": "<string>",
  "duration": 123,
  "cfg_scale": 123,
  "end_image": "<string>",
  "multi_prompt": [
    {}
  ],
  "negative_prompt": "<string>"
}
'
{
  "task_id": "<string>"
}
The Kling v3.0 4K image-to-video tool converts static images into 4K ultra-high-definition dynamic videos, presenting richer visual details, natural motion, and smooth scene dynamics while maintaining subject consistency. It supports flexible durations from 3 to 15 seconds, synchronized audio-video generation, end-frame control, and multi-shot video generation.
This is an asynchronous API and will only return the task_id of the asynchronous task. You should use this task_id to request the Query Task Result API to retrieve the generated result.

​
Request Headers

​
Content-Type
string
required
Enum value: application/json
​
Authorization
string
required
Bearer authentication format: Bearer {{API Key}}.

​
Request Body

​
image
string
required
The video’s first-frame image; supports .jpg, .jpeg, and .png. The image file size must not exceed 10MB; both width and height must be >= 300px; the aspect ratio must be between 1:2.5 and 2.5:1.
​
sound
boolean
default:false
Whether to generate audio at the same time when generating the video.
​
prompt
string
required
The positive prompt text for generating the video. It can describe scene motion, camera movement, actions, speech style, atmosphere, and sound effects; must not exceed 2500 characters.
​
duration
integer
default:5
The duration of the generated video (in seconds). Supports flexible durations from 3 to 15 seconds.Value range: [3, 15]
​
cfg_scale
number
Controls the flexibility of video generation. The higher the value, the more closely the model-generated content follows the prompt; the lower the value, the more natural the motion effects.Value range: [0, 1]
​
end_image
string
End-frame image URL, used to guide the transition effect. Not compatible with multi_prompt. Supports .jpg, .jpeg, and .png.
​
multi_prompt
array
A list of prompts for multi-shot video generation. Divides the video into multiple shots. Mutually exclusive with prompt.
​
negative_prompt
string
Negative prompt, specifying elements to avoid in the visuals and audio; must not exceed 2500 characters.

​
Response Information

​
task_id
string
required
Use task_id to request the Query Task Result API to retrieve the generated output.