---
title: Kling VIDEO 3.0 Omni 4K | Runware Docs
url: https://runware.ai/docs/models/klingai-video-3-0-omni-4k
description: 4K unified multimodal video generation with native audio, editing, and higher-end narrative control
---
# Kling VIDEO 3.0 Omni 4K

![Kling VIDEO 3.0 Omni 4K](https://assets.runware.ai/covers/klingai-video-o3-4k.jpg)

Kling VIDEO 3.0 Omni 4K is the 4K variant of Kling VIDEO 3.0 Omni for text-to-video and image-to-video workflows. It raises the 3.0 Omni line from 720p Standard and 1080p Pro to 4K output while preserving the series strengths: native audio generation, reference-guided video creation, prompt-based editing, multi-shot structure, and stable subject consistency for more demanding cinematic and advertising workflows.

- **Status**: live
- **ID**: `klingai:kling-video@o3-4k`
- Try in Playground
- **Creator**: Kling AI
- **Release Date**: April 23, 2026
- **Capabilities**: Text to Video, Image to Video, Video to Video, Checkpoint, Audio

## Pricing

$0.42 per second · ~3m 11s per request

**7 example generations**

- [first-frame](https://runware.ai/docs/models/klingai-video-3-0-omni-4k/examples#example-aquaculture-sensor-cleaning-demo) · 5s: `$2.10` (~1m 42s)
- [text-to-video](https://runware.ai/docs/models/klingai-video-3-0-omni-4k/examples#example-fountain-pen-restoration-social-reel) · 2160p · 6s: `$2.52` (~1m 49s)
- [video-edit](https://runware.ai/docs/models/klingai-video-3-0-omni-4k/examples#example-bauhaus-acoustic-panel-social-reel) · 4k: `$2.52` (~3m 11s)
- [reference-to-video](https://runware.ai/docs/models/klingai-video-3-0-omni-4k/examples#example-urban-bat-ecologist-update) · 2160p · 7s: `$2.94` (~3m 25s)
- [first-last-frame](https://runware.ai/docs/models/klingai-video-3-0-omni-4k/examples#example-portable-manuscript-scanner-explainer) · 8s: `$3.36` (~2m 45s)
- [multi-shot](https://runware.ai/docs/models/klingai-video-3-0-omni-4k/examples#example-cathedral-pipe-organ-maintenance-b-roll) · 2160p · 9s: `$3.78` (~7m 16s)
- [elements](https://runware.ai/docs/models/klingai-video-3-0-omni-4k/examples#example-mushroom-forager-workwear-fashion-reel) · 2880×2880 · 10s: `$4.20` (~4m 45s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Provide at least one of `inputs.frameImages` and `inputs.video`, or `width/height`, but not both.

---

Provide exactly one of: `positivePrompt`, `providerSettings.klingai.multiPrompt`.

---

Inside `inputs`, `video` cannot be used with `referenceVideos`.

---

Inside `inputs`, `frameImages` cannot be used with `video`.

---

When `inputs.elements.frontalImage` or `inputs.elements.images` is provided, `inputs.elements.frontalImage` and `inputs.elements.images` are required.

---

When `inputs.elements.frontalImage` or `inputs.elements.images` or `inputs.elements.videos` is provided, `inputs.elements.description` is required.

---

When `inputs.frameImages` is provided, `inputs.referenceImages` is limited to 6 items and `inputs.elements` is limited to 3 items.

---

When `inputs.frameImages` and `inputs.referenceVideos` are provided, `inputs.referenceImages` is limited to 3 items.

---

When `inputs.referenceImages` or `inputs.referenceVideos` is provided, `inputs.frameImages` is limited to 1 item.

---

When `inputs.referenceVideos` is provided, `inputs.elements` is limited to 4 items.

---

When `inputs.video` is provided, `duration` cannot be used.

---

When `inputs.video` or `inputs.referenceVideos` is provided, `providerSettings.klingai.sound` and `providerSettings.klingai.multiPrompt` cannot be used.

---

When `inputs.video` or `inputs.referenceVideos` is provided, `inputs.referenceImages` is limited to 4 items.

---

`positivePrompt` cannot be used with `providerSettings.klingai.multiPrompt`.

---

When `providerSettings.klingai.keepOriginalSound` is provided, `inputs.video` or `inputs.referenceVideos` is required.

---

`resolution` cannot be used with `width/height`.

---

When `resolution` is provided, `inputs.video` is required.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `4K (16:9)` | `3840x2160` |
| `4K (9:16)` | `2160x3840` |
| `4K (1:1)` | `2880x2880` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-outputformat)

- **Type**: `string`
- **Default**: `MP4`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP4\`: Widely supported video container (H.264), recommended for general use.
- \`WEBM\`: Optimized for web delivery.
- \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem).

**Allowed values**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [referenceImages](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `7`
- **Size (each)**: `300 px or more`

List of reference images (UUID, URL, Data URI, or Base64).

### [frameImages](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`
- **Size (each)**: `300 px or more`

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.

When the `frame` parameter is omitted, automatic distribution rules apply:

- **1 image**: Used as the first frame.
- **2 images**: First and last frames.

**Examples**:

**Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]
```

**First and last frames:** With two images, they automatically become the first and last frames of the video sequence. You can mix shorthand and object formats.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [frame](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. Supports first and last frame.

**Allowed values**:

- `first` First frame of the video.
- `last` Last frame of the video.
- `0` Frame index 0 (first frame).
- `-1` Frame index -1 (last frame).

### [video](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-video)

- **Path**: `inputs.video`
- **Type**: `string`
- **Size**: `700 px to 4553 px`
- **Aspect ratio**: `1:2.5 to 2:1`
- **Area**: `up to 8.29 MP`
- **Duration**: `3s to 15.5s`

Video input (UUID or URL). Source video for prompt-based editing. Dimensions and duration match the input video.

### [referenceVideos](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-referencevideos)

- **Path**: `inputs.referenceVideos`
- **Type**: `array of strings`
- **Min items**: `items: 1`
- **Size (each)**: `700 px to 4553 px`
- **Aspect ratio (each)**: `1:2.5 to 2:1`
- **Area (each)**: `up to 8.29 MP`
- **Duration (each)**: `3s to 15.5s`

List of reference videos (UUID or URL).

### [elements](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-elements)

- **Path**: `inputs.elements`
- **Type**: `array of objects (7 properties)`
- **Min items**: `1`
- **Max items**: `7`

Elements allow you to include reusable assets in your generation. Each element is identified by an `id` and can be referenced in the prompt using `<<<element_1>>>`, `<<<element_2>>>`, etc. in order of appearance.

An element can contain:

- **Images** via `frontalImage` plus `images` (1 to 3 additional angles).
- **Videos** via `videos`, on video models only (cannot be combined with images).
- **Voices** via `voices`, on video models only (can only be combined with images, not videos).

**Examples**:

**Create a new element with an image:**

```json
"positivePrompt": "<<<element_1>>> walking through a futuristic city",
"inputs": {
  "elements": [
    {
      "id": "my-character-id",
      "description": "A young woman with red hair",
      "frontalImage": "c64351d5-4c59-42f7-95e1-eace013eddab",
      "images": ["8f2a9c3e-1b4d-4e6f-a7c8-9d0e1f2a3b4c"],
      "tags": ["Character"]
    }
  ]
}
```

**Reuse a previously created element by ID:**

```json
"positivePrompt": "<<<element_1>>> sitting in a coffee shop, reading a book",
"inputs": {
  "elements": [
    {
      "id": "my-character-id"
    }
  ]
}
```

#### [id](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-elements-id)

- **Path**: `inputs.elements.id`
- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `20`

Unique identifier for this element. Use to create a new element or reference a previously created one.

#### [description](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-elements-description)

- **Path**: `inputs.elements.description`
- **Type**: `string`
- **Min**: `1`
- **Max**: `100`

Description of the element.

#### [frontalImage](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-elements-frontalimage)

- **Path**: `inputs.elements.frontalImage`
- **Type**: `string`

Frontal reference image for the element. Required when using image-based elements.

#### [images](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-elements-images)

- **Path**: `inputs.elements.images`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `3`

Reference images for the element. Up to 3 images. Requires frontalImage.

#### [videos](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-elements-videos)

- **Path**: `inputs.elements.videos`
- **Type**: `array of strings`
- **Min items**: `items: 1`

Reference video for the element. Cannot be combined with images or voices.

#### [voices](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-elements-voices)

- **Path**: `inputs.elements.voices`
- **Type**: `array of strings`
- **Min items**: `items: 1`

Voice audio for the element. Can only be combined with images, not videos.

#### [tags](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-inputs-elements-tags)

- **Path**: `inputs.elements.tags`
- **Type**: `array of strings`
- **Min items**: `1`

Classification tags for the element.

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `klingai:kling-video@o3-4k`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-positiveprompt)

- **Type**: `string`
- **Min**: `2`
- **Max**: `2500`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.video are not provided
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.video are not provided
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [resolution](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-resolution)

- **Type**: `string`

Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

**Allowed values**: `4k`

### [duration](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-duration)

- **Type**: `integer`
- **Min**: `3`
- **Max**: `15`
- **Step**: `1`
- **Default**: `5`

Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

**Provider Settings**

Parameters specific to this model provider. These must be nested inside the \`providerSettings.klingai\` object.

### [keepOriginalSound](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-providersettings-klingai-keeporiginalsound)

- **Path**: `providerSettings.klingai.keepOriginalSound`
- **Type**: `boolean`

Maintain the original sound from the reference video.

### [multiPrompt](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-providersettings-klingai-multiprompt)

- **Path**: `providerSettings.klingai.multiPrompt`
- **Type**: `array of objects (2 properties)`
- **Max items**: `6`

Sequential prompt segments for multi-shot generation. The sum of all segment durations must equal the root-level duration.

#### [prompt](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-providersettings-klingai-multiprompt-prompt)

- **Path**: `providerSettings.klingai.multiPrompt.prompt`
- **Type**: `string`
- **Required**: true
- **Min**: `3`
- **Max**: `512`

Text prompt describing the content for this segment.

#### [duration](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-providersettings-klingai-multiprompt-duration)

- **Path**: `providerSettings.klingai.multiPrompt.duration`
- **Type**: `integer`
- **Required**: true
- **Min**: `1`

Duration in seconds for this segment.

### [sound](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#request-providersettings-klingai-sound)

- **Path**: `providerSettings.klingai.sound`
- **Type**: `boolean`

Enable native audio generation.

## Response Parameters

### [taskType](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [NSFWContent](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/klingai-video-3-0-omni-4k#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-omni-4k/faf5f4c0-ed5f-4632-a1d1-c3fafc0f2b0d.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "9bc9674e-1c15-4266-9d79-04be70e30fe1",
  "model": "klingai:kling-video@o3-4k",
  "positivePrompt": "A polished 6-second cinematic social media ad for a specialist fountain pen restoration workshop, composed for 16:9 landscape. Grounded luxury with cool graphite, cobalt blue, silver, and restrained amber task lighting; extreme macro detail, shallow depth of field, crisp metal textures, no logos, captions, or visible writing. Open on a gloved craftsperson placing a tarnished vintage gold fountain pen nib beneath a jeweler's loupe on a dark precision workbench; the loupe clicks into position and a tiny bench lamp switches on with a soft mechanical snap. Cut to an extreme macro side angle as the nib glides over ultra-fine polishing film, shedding a trace of dark residue; synchronize a delicate metallic whisper and the faint creak of the leather work mat. Finish with the restored nib touching textured cream paper and laying down one smooth ribbon of deep cobalt ink; synchronize the gentle scratch of nib on paper, a tiny breath from the craftsperson, and the quiet room tone of a meticulous workshop. Slow controlled camera movement, elegant match cuts, photorealistic hands and tools, premium editorial product cinematography, satisfying ASMR sound design, no music.",
  "width": 3840,
  "height": 2160,
  "duration": 6,
  "providerSettings": {
    "klingai": {
      "sound": true
    }
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-omni-4k/e0a2841c-d364-433d-b1da-d32cb0160e15.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "112ebde6-8d8f-4f98-aefb-47f880e293ab",
  "model": "klingai:kling-video@o3-4k",
  "positivePrompt": "Continue naturally from the supplied first frame in one uninterrupted five-second technical product-demo shot. Preserve the exact sensor, underwater installation, framing, lighting, and kelp-nursery environment. The camera makes a very slow, stable macro push toward the circular optical window as the built-in wiper activates and sweeps smoothly across the glass once, visibly removing the thin green biofilm and revealing a clean reflective optical surface beneath. A few loosened particles drift away in the current; tiny bubbles rise, suspended matter moves gently, and the background kelp fronds sway naturally. Keep the sensor body rigidly mounted while only the wiper mechanism and waterborne elements move. Crisp photorealistic 4K marine engineering cinematography, physically accurate underwater motion, premium industrial explainer aesthetic, shallow depth of field, no cuts, no hands, no added components, no transformation, no logos, no captions, no interface graphics.",
  "duration": 5,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/7c83d7c8-2c60-4f6f-b4b3-f0db484232eb.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

### first-last-frame (first-last-frame)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-omni-4k/d2244b73-97cd-4257-988e-b59a8a2be2cf.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "ffedf028-fe1d-4ef1-8115-8379071fce04",
  "model": "klingai:kling-video@o3-4k",
  "positivePrompt": "Create a coherent eight-second product explainer in one continuous, locked three-quarter overhead shot, transitioning exactly from the supplied first frame to the supplied last frame. Preserve the precise identity and position of the portable hyperspectral scanner, parchment, table, copper fittings, rails, gloves, and lighting. After a brief moment of stillness, the narrow optical head glides smoothly from the near edge toward the far edge along its twin rails at a controlled laboratory pace. A thin cyan scanning line travels directly beneath the moving head. In the completed area behind it, the parchment gradually changes into a restrained cyan-and-amber multispectral visualization, revealing a second layer of erased handwriting while retaining realistic fibers, wrinkles, stains, and original surface detail. The reveal must remain physically attached to the parchment and follow the scanner head with exact spatial continuity; it is not a floating hologram. The gloved hands stay still and safely clear of the document. Add minute optical reflections across the charcoal housing and copper corners, subtle dust motes in the warm task light, and a gentle increase in the cyan status light as the pass completes. End with the head settled at the far edge and the hidden manuscript layer fully visible, matching the supplied final frame. Premium conservation-equipment demonstration, calm scientific confidence, dark teal, parchment cream, copper, and cyan palette, crisp 4K material detail, realistic mechanics, no camera movement, no cuts, no people entering, no logos, no captions, no interface, no floating text.",
  "duration": 8,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/4df2952b-2879-4fac-ad54-ac6d1a3ea7c1.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/1a480113-62c1-41f6-af5e-1905b57c9e30.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

### reference-to-video (reference-to-video)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-omni-4k/0ddc7e23-470d-444b-8dcf-9c15249b8c98.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "0e470b03-f5e7-4f0d-b9f6-efabeb8bfcf6",
  "model": "klingai:kling-video@o3-4k",
  "positivePrompt": "Create a completely new 7-second vertical talking-head scene guided by the reference presenter's appearance, facial performance, calm delivery, and gesture timing; do not reuse or edit the reference footage or studio background. She is now an urban bat ecologist delivering a concise municipal wildlife update from a rooftop acoustic-monitoring station at blue hour. Medium close-up, direct eye contact, presenter dominant in frame. She wears a practical charcoal field jacket with a small orange safety tab and no branding. Behind her, softly defocused ultrasonic detector equipment, antenna cables, planted roof trays, and a distant city skyline establish the real working location. Art direction is polished nocturnal documentary: deep indigo sky, muted concrete gray, restrained sodium-amber practical lights, soft cool key light on her face, realistic skin texture, subtle evening breeze moving a few loose hairs. Match the reference motion: start composed, point briefly toward a detector over her shoulder, transition into an open-palm public-guidance gesture, then settle. Stable locked camera with very slight natural documentary drift, shallow depth of field, crisp 4K detail. Generate synchronized natural female speech, spoken exactly once: “These rooftop detectors logged three migrating bat species tonight. Keep exterior lights low, and leave grounded bats undisturbed.” Quiet rooftop ambience beneath the clean voice, with distant traffic and a faint breeze. No music, captions, on-screen text, logos, jump cuts, extra people, or exaggerated gestures.",
  "width": 2160,
  "height": 3840,
  "duration": 7,
  "providerSettings": {
    "klingai": {
      "keepOriginalSound": true
    }
  },
  "inputs": {
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/901da59f-bca6-47ad-80e8-84959f2755f1.mp4"
    ]
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-omni-4k/9713fb93-24ff-4f75-9322-699243b2ed33.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "8df4984e-ec8f-40a7-9730-5d0a925eefd1",
  "model": "klingai:kling-video@o3-4k",
  "positivePrompt": "Prompt-based edit of the source video for a premium architectural acoustics social reel. Preserve the exact vertical composition, camera push-in, drummer, drum kit, body motion, stick movement, lighting direction, performance timing, and all cuts or lack of cuts. Keep the person and instruments photorealistic and unchanged. Apply a clearly visible environment transformation synchronized with the drum performance: the bare concrete walls progressively refit themselves into precisely manufactured three-dimensional acoustic felt panels, spreading outward from behind the drummer with each major beat. Use a sophisticated Bauhaus installation of large circles, arches, ribs, and staggered rectangular panels in saturated cobalt blue, vermilion, warm ochre, and small accents of mint green. Show convincing dense felt fibers, beveled edges, shallow relief, accurate wall attachment, contact shadows, and subtle parallax as the camera advances. By the final moments, the room is fully treated and visually polished, with balanced geometric symmetry framing the drummer. Energetic, design-led, tactile, contemporary commercial art direction; crisp 4K material detail and natural motion. Do not add text, captions, logos, interfaces, extra people, extra instruments, surreal objects, or changes to the performer.",
  "resolution": "4k",
  "providerSettings": {
    "klingai": {
      "keepOriginalSound": true
    }
  },
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/2fd1ba5c-dea2-446f-b7fb-0f0a50935ae6.mp4"
  }
}
```

---

### elements (elements)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-omni-4k/0f6f9a2a-320c-4e48-9210-c1d6a0b8037c.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "f0ebe2b2-5a49-4dfa-88c0-022fdb8cf1fe",
  "model": "klingai:kling-video@o3-4k",
  "positivePrompt": "Create a polished 10-second square fashion showcase reel for specialist mushroom-growing workwear. Preserve the exact faces, body types, garments, colors and accessories of <<<element_1>>> and <<<element_2>>> throughout. Set the reel inside a pristine architectural mushroom fruiting room: long stainless shelving filled with ivory oyster mushrooms, translucent humidity drifting through precise shafts of cool light, wet graphite floor with restrained reflections. Sophisticated editorial art direction in saffron, cobalt, fungal cream and brushed steel; tactile fabric detail and premium commercial realism.\n\nOpen with a symmetrical full-body two-shot as <<<element_1>>> enters from the left and <<<element_2>>> enters from the right, both walking toward camera at a measured pace. Cut to crisp waist-level tracking details: the saffron coat pockets and basket harness, then the cobalt coverall zipper, reinforced knees and mesh sampling pouches. They meet beside a shelf, turn to face one another in clear three-quarter profile, and perform one practical interaction: <<<element_1>>> lifts a shallow harvest basket while <<<element_2>>> selects an oyster mushroom and places it inside. Hold a clean moment showing both faces and both outfits unobstructed. Finish with them standing back-to-back, then pivoting toward camera for a balanced full-length hero pose. Controlled camera movement, natural garment motion, accurate hands, consistent wardrobe construction, sharp 4K textile texture, subtle humidity, calm assured mood. No logos, captions, lettering or interface graphics.",
  "width": 2880,
  "height": 2880,
  "duration": 10,
  "inputs": {
    "elements": [
      {
        "id": "saffron_forager_look",
        "description": "Male model wearing the saffron waxed-canvas mushroom-foraging outfit.",
        "frontalImage": "https://assets.runware.ai/assets/inputs/013058f5-727d-435f-9653-37715b1503ae.jpg",
        "images": [
          "https://assets.runware.ai/assets/inputs/ab5ae8c2-b5b7-49ae-a4c8-42da3536f064.jpg"
        ],
        "tags": [
          "Costume"
        ]
      },
      {
        "id": "cobalt_grower_look",
        "description": "Female model wearing the cobalt ripstop mushroom-cultivation outfit.",
        "frontalImage": "https://assets.runware.ai/assets/inputs/0e25fe42-c7db-469b-9281-a735e5e0a9e3.jpg",
        "images": [
          "https://assets.runware.ai/assets/inputs/cc50da0a-03fe-4c8d-8b8e-7c6eef5ba19a.jpg"
        ],
        "tags": [
          "Costume"
        ]
      }
    ]
  }
}
```

---

### multi-shot (multi-shot)

[Watch video](https://assets.runware.ai/examples/klingai-video-3-0-omni-4k/6e7dbf8c-fee7-4dfd-a590-9c07969ccda3.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "7b3d3238-447f-44d2-bf86-7e4c176c42b4",
  "model": "klingai:kling-video@o3-4k",
  "width": 3840,
  "height": 2160,
  "duration": 9,
  "providerSettings": {
    "klingai": {
      "sound": true,
      "multiPrompt": [
        {
          "prompt": "Wide establishing shot of a small paper boat entering a rain-filled city gutter, with rainfall and distant traffic audible.",
          "duration": 3
        },
        {
          "prompt": "Low tracking shot following the paper boat as it accelerates through rippling water, with splashes synchronized to its movement.",
          "duration": 3
        },
        {
          "prompt": "Close-up as the paper boat reaches a warm pool of reflected storefront light and slows, while the rain softens.",
          "duration": 3
        }
      ]
    }
  }
}
```