Skip to main content
POST
/
vendors
/
klingai
/
v1
/
kling-v3-omni
/
video-to-video
/
generation
Video to Video Generation
curl --request POST \
  --url https://api.mulerouter.ai/vendors/klingai/v1/kling-v3-omni/video-to-video/generation \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "Transform @Video1 into an animated painting style with vibrant colors",
  "video_list": [
    {
      "video_url": "https://example.com/source-video.mp4",
      "refer_type": "feature"
    }
  ],
  "mode": "pro"
}
'
{
  "task_info": {
    "id": "8e1e315e-b50d-4334-a231-be7d19a372f4",
    "status": "pending",
    "created_at": "2026-03-03T00:00:00Z",
    "updated_at": "2026-03-03T00:00:00Z"
  }
}

​
Overview

Generate new videos from existing videos using the Kling V3 Omni model. Use @Video1 in the prompt to reference the input video:
  • Video references — provide source videos via video_list with refer_type (base or feature)
  • Element references — reference up to 4 elements when using reference video
  • First/Last frame control — optionally set opening and closing frames
  • Keep original sound — preserve audio from the source video with keep_original_sound

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
prompt
string
required

Text prompt describing the desired transformation. Use @Video1 to reference the input video.

Maximum string length: 2500
​
video_list
object[]
required

List of input videos. At least one video is required.

Minimum array length: 1
​
first_frame
string | null

First frame image (URL or Base64). Sets the opening frame of the generated video.

​
last_frame
string | null

Last frame image (URL or Base64). Sets the closing frame of the generated video.

​
negative_prompt
string | null

Negative prompt to exclude unwanted content.

​
images
string[]

Optional list of reference image URLs or Base64 strings.

​
elements
object[]

Element list. Combined count of images and elements must not exceed 4 when using reference video.

Maximum array length: 4
​
mode
enum<string>
default:pro

Generation mode. std for standard quality, pro for higher quality.

Available options:
std,
pro
​
aspect_ratio
enum<string> | null

Aspect ratio of the generated video.

Available options:
16:9,
9:16,
1:1
​
duration
integer
default:5

Duration of the generated video in seconds (3-15).

Response

Accepted - Task created successfully

​
task_info
object