Skip to content
HiAPI Docs
HiAPI
Playground Get API Key
English
English 中文

Kling 3.0 Omni Transformation API

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name kling-3.0-omni/transformation
Type Video generation (video transformation)
Endpoint POST /v1/tasks
Pricing See HiAPI Pricing

Kling 3.0 Omni transformation rewrites the style, scene, or subject of a source video from a prompt while keeping its camera and motion; output length and aspect ratio follow the source, with 720p to 4k output and @name subject references.

Production guidance

Production guidance
  • For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
  • GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
  • Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Style and scene rewrites

Move an existing video to another season, time of day, or art style while keeping its camera and motion.

video_urlsprompt
Subject replacement

Pass several images of a new subject in elements and name the replacement in the prompt as @name.

elements
High-resolution output

Choose 1080p or 4k to produce a higher-resolution rewrite of existing footage.

resolution

Request parameters

model string required

Fixed value kling-3.0-omni/transformation.

example kling-3.0-omni/transformation
input object required

Model-specific parameters. Put the Kling 3.0 Omni Transformation configuration here.

prompt string required

Describe the scene, subject motion, and camera work. To use a subject from elements, mention it in the prompt as @name. 1–3072 characters.

video_urls string[] required

The video to transform, exactly 1 clip. MP4/MOV, up to 200MB, 3–15.5 seconds, width and height 700–4553px, 24–60fps. Output length and aspect ratio follow the source video; no audio is generated.

resolution enum optional

Resolution of the generated video.

default 720p enum: 720p1080p4k
elements object[] optional

Reusable subjects, up to 7. Each has a name, a short description, and 2–4 images of the same subject; reference it in the prompt as @name to keep the character or object consistent across the video.

example [{"name":"lin","description":"Little girl with a ponytail in a pale yellow dress","element_input_urls":["https://example.com/lin-front.jpg","https://example.com/lin-side.jpg"]}]
name string required

Unique subject name without spaces; referenced in the prompt as @name.

description string required

Short description of the subject.

element_input_urls string[] required

2–4 image URLs of the same subject, JPG/PNG.

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback
when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Rainy night to snowy night

Keeps the source video's camera move and water motion while rewriting the scene as a snowy winter night, at 720p.

Request body
{
  "model": "kling-3.0-omni/transformation",
  "input": {
    "prompt": "Transform the scene into a snowy winter night: the gutter becomes a frozen stream with drifting snowflakes, the paper boat becomes a small glowing paper lantern boat, keep the exact camera motion and water movement from the original video. Cinematic, cold blue tones.",
    "video_urls": [
      "https://static.hiapi.ai/admin-assets/2026/10/13/1791861859228-2b40d774dd4b2262-kling-omni-t2v-golden.mp4"
    ],
    "resolution": "720p"
  }
}
1080p art-style rewrite

Rewrites the same source video as a hand-drawn animation at 1080p; length and aspect ratio follow the source.

Request body
{
  "model": "kling-3.0-omni/transformation",
  "input": {
    "prompt": "Turn the whole shot into a hand-painted watercolor animation: the gutter becomes a winding watercolor stream, the paper boat stays white with pencil-sketch edges, the neon reflections become soft color washes, and the original camera motion and water flow are fully preserved.",
    "video_urls": [
      "https://static.hiapi.ai/admin-assets/2026/10/13/1791861859228-2b40d774dd4b2262-kling-omni-t2v-golden.mp4"
    ],
    "resolution": "1080p"
  }
}
Subject replacement at 4k

Passes two images of a new subject in elements referenced as @fox, replaces the paper boat in the source video with it, and outputs 4k. Replace the example URLs with publicly accessible subject images.

Request body
{
  "model": "kling-3.0-omni/transformation",
  "input": {
    "prompt": "Replace the paper boat in the original video with @fox lying on a floating leaf drifting downstream; fully preserve the original camera motion, water ripples, and neon reflections. Cinematic, shallow depth of field.",
    "video_urls": [
      "https://static.hiapi.ai/admin-assets/2026/10/13/1791861859228-2b40d774dd4b2262-kling-omni-t2v-golden.mp4"
    ],
    "elements": [
      {
        "name": "fox",
        "description": "Small plush fox with orange fur and a white-tipped tail",
        "element_input_urls": [
          "https://example.com/fox-front.jpg",
          "https://example.com/fox-side.jpg"
        ]
      }
    ],
    "resolution": "4k"
  }
}

Getting the result

  1. The response returns a taskId immediately without waiting for generation to finish.
  2. In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
  3. When status=success, download the generated video from output[].url.
  4. When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

Can I set the output length or aspect ratio?

No. Output length and aspect ratio follow the source video, so this model has no duration or aspect_ratio parameter.

What are the source video requirements?

MP4/MOV, up to 200MB, 3–15.5 seconds, width and height 700–4553px, 24–60fps, and exactly one clip.

Is the source audio track kept?

No. This model does not generate audio, and the output has no audio track.

How do I replace a subject in the video?

Pass 2–4 images of the new subject in elements with a name, then say what to replace in the prompt as @name. Up to 7 subjects per request.

How is it billed?

Billed by the length of the final output video; see the live prices on the HiAPI pricing page. View pricing

Next steps