Kling 3.0 4K Image to Video API

4K · Text to video 4K · Image to video

Endpoint: POST https://api.higgsfield.ai/kling-video/v3.0/4k/image-to-video Endpoint ID: kling-video/v3.0/4k/image-to-video ▶Try Kling 3.0 4K Image to VideoOpen the model in the Higgsfield Playground with your own inputs.↗

Quick Start

import higgsfield_client

result = higgsfield_client.subscribe(
    "kling-video/v3.0/4k/image-to-video",
    arguments={'prompt': 'A cinematic glass pavilion in a misty pine forest at sunrise',
     'image_url': 'https://cdn.example.com/input.jpg',
     'duration': 5,
     'sound': 'on',
     'cfg_scale': 0.5},
)

print(result["video"]["url"])

import { config, higgsfield } from "@higgsfield/client/v2";

config({ credentials: process.env.HF_CREDENTIALS });

const result = await higgsfield.subscribe(
  "kling-video/v3.0/4k/image-to-video",
  {
    input: {
      "prompt": "A cinematic glass pavilion in a misty pine forest at sunrise",
      "image_url": "https://cdn.example.com/input.jpg",
      "duration": 5,
      "sound": "on",
      "cfg_scale": 0.5
    },
    withPolling: true,
  },
);

if (result.isCompleted) console.log(result.jobs[0].results?.raw.url);

curl --request POST \
  --url https://api.higgsfield.ai/kling-video/v3.0/4k/image-to-video \
  --header "Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A cinematic glass pavilion in a misty pine forest at sunrise",
  "image_url": "https://cdn.example.com/input.jpg",
  "duration": 5,
  "sound": "on",
  "cfg_scale": 0.5
}'

Input Schema

string

default:"on"

Enable or disable generated sound. Supported values: on, off.

string

Provide a prompt describing the desired output, as shown in the examples. Kling uses up to the first 2,500 characters.

integer

default:"5"

Output duration in seconds. Supported range: 3–15.

array

Reusable Kling element IDs. Each item must be a string.

number

default:"0.5"

How strongly the generation follows the prompt. Supported range: 0–1 in increments of 0.01.

string

required

Publicly accessible source image URL.

boolean

default:"false"

Enable a multi-shot sequence.

array

Ordered shot definitions used when multi_shots is true. Accepts up to 6 objects; for each shot, provide prompt (up to 512 characters) and duration (1–15 seconds).

string

Optional ending-frame image URL.

Output Schema

string

required

Request state. A newly accepted request returns queued.

string

required

Stable identifier used for polling, cancellation, and support.

string

required

URL to poll until the request reaches a terminal state.

string

required

URL used to cancel a request before processing starts.

object

Completed video output containing its download url.

Input Example

{
  "prompt": "A cinematic glass pavilion in a misty pine forest at sunrise",
  "image_url": "https://cdn.example.com/input.jpg",
  "duration": 5,
  "sound": "on",
  "cfg_scale": 0.5
}

Output Example

{
  "status": "queued",
  "request_id": "d7e6c0f3-6699-4f6c-bb45-2ad7fd9158ff",
  "status_url": "https://api.higgsfield.ai/requests/d7e6c0f3-6699-4f6c-bb45-2ad7fd9158ff/status",
  "cancel_url": "https://api.higgsfield.ai/requests/d7e6c0f3-6699-4f6c-bb45-2ad7fd9158ff/cancel"
}

{
  "status": "completed",
  "request_id": "d7e6c0f3-6699-4f6c-bb45-2ad7fd9158ff",
  "video": {
    "url": "https://cdn.example.com/output.mp4"
  }
}

Use an SDK for automatic polling, or poll the returned status URL.

Get started

Model API reference

Core concepts

SDKs

Organizations

API reference

Resources

Quick Start

Input Schema

Output Schema

Input Example

Output Example

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example