Skip to main content
POST
/
v3
/
async
/
kling-v3.0-motion-control
Kling V3.0 Motion Control
curl --request POST \
  --url https://api.novita.ai/v3/async/kling-v3.0-motion-control \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "image": "<string>",
  "video": "<string>",
  "prompt": "<string>",
  "model_name": "<string>",
  "negative_prompt": "<string>",
  "keep_original_sound": true,
  "character_orientation": "<string>"
}
'
{
  "task_id": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://novita.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Kling V3.0 Motion Control extracts motion trajectories from reference videos and applies them to reference images to generate videos while maintaining subject consistency. Supports standard and professional modes with per-second billing.
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 URL or base64 encoded image; supports .jpg, .jpeg, .png. Image file size must not exceed 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; supports .mp4, .mov. Video file size must not exceed 10MB; width and height must be >= 300px; duration 3-30 seconds.
​
prompt
string
Positive prompt for scene description, style, lighting; must not exceed 2500 characters.Length limit: 0 - 2500
​
model_name
string
default:"kling-v3-0-std"
required
Model name. kling-v3-0-std: standard mode, cost-effective; kling-v3-0-pro: professional mode, higher video quality.Optional values: kling-v3-0-std, kling-v3-0-pro
​
negative_prompt
string
Negative prompt describing elements to avoid in the generated video; must not exceed 2500 characters.Length limit: 0 - 2500
​
keep_original_sound
boolean
default:true
Whether to keep the original audio from the reference video.
​
character_orientation
string
required
Output frame mode:
  • image: uses the reference image’s pose and composition, transfers motion to the image subject (outputs 5 seconds)
  • video: uses the reference video’s pose and composition, applies video motion to the image subject (output duration matches reference video, up 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.