Skip to main content
POST
/
v3
/
async
/
kling-v2.6-pro-motion-control
Kling V2.6 Pro Motion Control
curl --request POST \
  --url https://api.novita.ai/v3/async/kling-v2.6-pro-motion-control \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "image": "<string>",
  "video": "<string>",
  "prompt": "<string>",
  "negative_prompt": "<string>",
  "keep_original_sound": true,
  "character_orientation": "<string>"
}
'
{
  "task_id": "<string>"
}
The Kling v2.6 Pro Motion Control model generates animations by applying motion from a reference video to a reference image. It extracts motion paths from 3-30 second video clips to produce smooth, realistic video animations while maintaining subject identity consistency.
This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the Task Result API to retrieve the video generation results.

​
Request Headers

​
Content-Type
string
required
Supports: application/json
​
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

​
Request Body

​
image
string
required
Reference image to animate (URL or base64 encoded); supported formats: .jpg, .jpeg, .png. Max file size: 10MB; width and height must be >= 300px; aspect ratio must be between 1:2.5 and 2.5:1.
​
video
string
required
Reference motion video URL; contains the motion sequence to transfer; supported formats: .mp4, .mov. Max file size: 10MB; width and height must be >= 300px; aspect ratio must be between 1:2.5 and 2.5:1. Duration must be between 3 and 30 seconds.
​
prompt
string
Positive prompt for scene description, style, lighting, etc.
​
negative_prompt
string
Negative prompt; max 2500 characters.
​
keep_original_sound
boolean
default:true
Whether to keep the original audio from the reference video.
​
character_orientation
string
required
Character orientation in the generated video, can match either the image or video orientation.
  • image: Matches the character orientation in the image; reference video duration limited to 10 seconds.
  • video: Matches the character orientation in the video; reference video duration limited to 30 seconds.
Optional values: image, video

​
Response

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