---
title: Kling VIDEO O1 Pro | Runware Docs
url: https://runware.ai/docs/models/klingai-video-o1-pro
description: Unified multimodal video model for precise AI editing
---
# Kling VIDEO O1 Pro

![Kling VIDEO O1 Pro](https://assets.runware.ai/covers/klingai-video-o1-pro.jpg)

Kling VIDEO O1 Pro is a unified multimodal video foundation model for controllable generation and instruction based editing. It supports text prompts, visual references, and video input so developers can build high control pipelines for pacing, transitions, object changes, and style revisions.

- **Status**: live
- **ID**: `klingai:kling@o1`
- Try in Playground
- **Creator**: Kling AI
- **Release Date**: December 1, 2025
- **Capabilities**: Text to Video, Image to Video, Video to Video, Edit, Checkpoint

## Pricing

$0.112 from, per second · ~2m 44s per request

**Rates** (per second)

- 1080p · T2V: `$0.112`
- 1080p · I2V: `$0.112`
- 1080p · R2V: `$0.168`

**5 example generations**

- [first-frame](https://runware.ai/docs/models/klingai-video-o1-pro/examples#example-hydropower-spring-thaw-visualization) · 5s: `$0.56` (~2m 1s)
- [video-edit](https://runware.ai/docs/models/klingai-video-o1-pro/examples#example-historic-cinema-facade-cleanup): `$1.01` (~3m 2s)
- [text-to-video](https://runware.ai/docs/models/klingai-video-o1-pro/examples#example-competitive-shearer-arena-composite) · 1080p · 10s: `$1.12` (~2m 27s)
- [first-last-frame](https://runware.ai/docs/models/klingai-video-o1-pro/examples#example-ocularist-conference-headshot-retouch) · 10s: `$1.12` (~2m 44s)
- [reference-to-video](https://runware.ai/docs/models/klingai-video-o1-pro/examples#example-desert-observatory-nightfall-visualization) · 1080p · 7s: `$1.18` (~5m 59s)

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

## Compatibility & Validation

Provide exactly one of: `inputs.frameImages` or `inputs.video` or `width/height`.

---

When `inputs.frameImages` is provided, `inputs.referenceImages` and `inputs.referenceVideos` cannot be used.

---

When `inputs.frameImages` is provided, `duration` is limited to `5`, `10`.

---

When `inputs.referenceImages` or `inputs.referenceVideos` is provided, `inputs.referenceImages` is limited to 7 items and `duration` must be between `3` and `10`.

---

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

---

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

---

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

---

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `1080p (16:9)` | `1920x1080` |
| `1080p (1:1)` | `1440x1440` |
| `1080p (9:16)` | `1080x1920` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/klingai-video-o1-pro#request-tasktype)

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

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/klingai-video-o1-pro#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-o1-pro#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/klingai-video-o1-pro#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-o1-pro#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-o1-pro#request-webhookurl)

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

Specifies a webhook URL where JSON responses will be sent 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/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/klingai-video-o1-pro#request-deliverymethod)

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

Determines how the API delivers task results.

**Allowed values**:

- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. Required for long-running tasks like video generation.

**Learn more** (1 resource):

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

### [uploadEndpoint](https://runware.ai/docs/models/klingai-video-o1-pro#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-o1-pro#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/klingai-video-o1-pro#request-safety-checkcontent)

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

Enable or disable content safety checking. Increases total generation time.

#### [mode](https://runware.ai/docs/models/klingai-video-o1-pro#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-o1-pro#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-o1-pro#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/klingai-video-o1-pro#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-o1-pro#request-inputs-referenceimages)

- **Path**: `inputs.referenceImages`
- **Type**: `array of strings`
- **Min items**: `1`
- **Max items**: `7`

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

### [frameImages](https://runware.ai/docs/models/klingai-video-o1-pro#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`

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-o1-pro#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-o1-pro#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-o1-pro#request-inputs-video)

- **Path**: `inputs.video`
- **Type**: `string`

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-o1-pro#request-inputs-referencevideos)

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

List of reference videos (UUID, URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/klingai-video-o1-pro#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `klingai:kling@o1`

Identifier of the model to use for generation.

**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-o1-pro#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **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-o1-pro#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.video are not provided or width and height are 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-o1-pro#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages and inputs.video are not provided or width and height are 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)

### [duration](https://runware.ai/docs/models/klingai-video-o1-pro#request-duration)

- **Type**: `integer`
- **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-o1-pro#request-providersettings-klingai-keeporiginalsound)

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

Maintain the original sound from the reference video.

## Response Parameters

### [taskType](https://runware.ai/docs/models/klingai-video-o1-pro#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-o1-pro#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-o1-pro#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/klingai-video-o1-pro#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/klingai-video-o1-pro#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/klingai-video-o1-pro#response-videodatauri)

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

Data URI of the output video.

### [seed](https://runware.ai/docs/models/klingai-video-o1-pro#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/klingai-video-o1-pro#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/klingai-video-o1-pro#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-o1-pro/415b4654-42cf-45ac-8345-e0a3b38cde4b.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "4afc65e0-974f-46db-90f4-98b7d2c70ec8",
  "model": "klingai:kling@o1",
  "positivePrompt": "Create a polished 10-second background-replacement composite for an agricultural sports broadcast. In the foreground, a skilled competitive sheep shearer in a navy singlet and work trousers handles a calm cream-fleeced ewe on a low green shearing platform. Preserve consistent anatomy, clothing, faces, fleece texture, and humane handling throughout. Replace the original surroundings completely with a packed contemporary indoor shearing arena: steep shadowed stands, indistinct cheering spectators, warm amber competition lights, subtle cyan accents, suspended haze, and realistic depth of field. No readable signs, logos, or text. The compositing must look immaculate, with precise moving edges around loose curls of wool, the clipper cable, fingers, boots, and the ewe’s ears; no halos, matte chatter, green spill, or background leakage. Begin in a medium-wide three-quarter view as the shearer smoothly rolls the ewe into position. The camera makes a steady clockwise arc and gradual dolly-in. From seconds 3–7, the shearer guides electric clippers in one confident pass while a broad ribbon of fleece peels away and drops naturally; the arena crowd shifts and lights sweep softly in the deep background with correct parallax. During the final three seconds, move to a close medium framing as the shearer releases the finished fleece onto the platform and briefly looks toward the judges beyond camera. End on a crisp, energetic hero composition. Photorealistic live sports cinematography, natural motion blur, restrained broadcast contrast, warm fleece against deep navy and saturated green, grounded and triumphant mood.",
  "width": 1920,
  "height": 1080,
  "duration": 10
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/klingai-video-o1-pro/bbf4ed0b-3840-40df-8a7e-af6692b6a9ed.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "65cc4f0b-3559-4269-a2f9-28cec8bda609",
  "model": "klingai:kling@o1",
  "positivePrompt": "A slow, stabilized drone push continues toward the hydroelectric spillway as late-winter blue hour advances through a compressed spring thaw. Pale sunrise spills over the ridge, moving warm light across the concrete gates and catwalk while the valley’s cold blue shadows gradually recede. Clouds travel quickly overhead. Fine cracks spread through the reservoir ice, plates separate and drift toward the spillway, then dark meltwater begins flowing between them. Snow withdraws naturally from the rocky banks in irregular patches, revealing wet earth and muted green moss; subtle new buds appear on nearby birches while the evergreen forest remains consistent. By the final moment, the reservoir is mostly open water under a crisp spring morning, with small remaining ice floes and controlled water streaming through the gates. Preserve the exact dam design, valley geography, scale, and documentary realism throughout. Restrained mineral palette shifting from icy blue-gray to soft amber and fresh subdued green, physically accurate reflections and shadows, smooth cinematic motion, no dramatic flooding, no people, no signage, no text.",
  "duration": 5,
  "inputs": {
    "frameImages": [
      "https://assets.runware.ai/assets/inputs/28fb6105-52bc-4bba-9f91-14cc23df8558.jpg"
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/klingai-video-o1-pro/4ae1d00e-3fbc-4023-ab23-610f79da0816.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "54ccb0d5-b5a1-4887-8c59-a688cd5ca0dc",
  "model": "klingai:kling@o1",
  "positivePrompt": "Create a polished 10-second vertical before-and-after headshot retouch film. Begin exactly on the supplied first-frame image and finish exactly on the supplied last-frame image. Keep the ocularist’s identity, facial proportions, expression, gaze, pose, clothing, crop, and camera position perfectly stable throughout. Use a locked-off camera with no zoom or reframing. Make the enhancement unfold coherently and almost imperceptibly: the cool, flat RAW exposure gradually becomes balanced; backdrop creases and uneven tones resolve smoothly; flyaway hairs settle; blouse lint disappears; temporary redness and under-eye discoloration are gently reduced; contrast, catchlights, and hair definition gain refinement. Preserve pores, freckles, fine lines, and realistic skin texture at every moment. The transition should feel like an expert high-end retoucher working in continuous passes, not a face morph, beauty-filter wipe, magical effect, or identity change. Maintain soft studio lighting and a restrained clinical-editorial palette of pale pistachio, navy, aubergine, and natural skin tones. End on a credible, publication-ready conference speaker headshot. No captions, interface elements, split screen, logos, or added objects.",
  "duration": 10,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/dd50c773-2e15-4bc3-9fa7-d7647bc4f036.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/4d5f6173-2ba9-4b84-b414-559b86acfdff.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/klingai-video-o1-pro/136e001b-9aaa-446f-b8d5-539355f3a6c8.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "fe8deb36-2309-4b50-99bf-cf7f7a0c4f76",
  "model": "klingai:kling@o1",
  "positivePrompt": "Create a single uninterrupted 7-second portrait architectural visualization of the desert observatory changing from late afternoon to a clear stargazing night. Use the reference image as the authoritative source for the subject and visual identity: preserve the exact rammed-earth lodge geometry, white hemispherical telescope dome, recessed windows, black basalt courtyard, gravel approach, ochre terrain and distant volcanic ridgeline. Do not redesign, replace or distort the property. Use the reference video only to guide the stabilized forward push, subtle rising arc, lens character, premium architectural-film style and timing of the daylight-to-night transition; do not copy the building or landscape shown in that motion reference.\n\nBegin in dry amber late-afternoon sunlight with hard, credible shadows crossing the courtyard. As the camera advances and rises slightly, let the sun sink naturally: warm light grazes the earthen walls, shadows lengthen, the sky passes through muted coral sunset into saturated cobalt blue hour, then settles into a pristine dark desert night. Recessed pathway lights and soft warm interior lights switch on progressively and cast physically accurate pools of light without overexposure. End with the observatory warmly illuminated beneath a dense but realistic field of stars and a faint Milky Way, while the white dome remains clearly legible.\n\nCompose vertically with the gravel path leading from the lower foreground, the lodge and dome occupying the central lower two-thirds, and generous sky above for the night reveal. Smooth continuous camera motion, seamless temporal relighting, realistic exposure adaptation, consistent architecture and terrain, restrained luxury travel cinematography, natural color science, crisp material detail. No people, vehicles, lettering, logos, cuts, flicker, object morphing or sudden weather changes.",
  "width": 1080,
  "height": 1920,
  "duration": 7,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/38b3fed7-60a2-4ab6-92ec-4f2a965e5ec7.jpg"
    ],
    "referenceVideos": [
      "https://assets.runware.ai/assets/inputs/f5b771a4-a9c1-4bbe-a148-41d6cd4b48b4.mp4"
    ]
  }
}
```

---

### video-edit (video-edit)

[Watch video](https://assets.runware.ai/examples/klingai-video-o1-pro/a6ea9134-4833-4ea2-84f1-96051c8e6350.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "7d3ab848-b6e2-4f1d-a710-1e168ac68ab5",
  "model": "klingai:kling@o1",
  "positivePrompt": "Edit the source video into finished heritage-tourism footage. Completely remove the metal scaffolding, construction sheeting, yellow cherry picker, temporary fencing, orange barriers, loose cables, and all associated restoration clutter from every frame. Use the reference image as visual guidance to reconstruct the cinema architecture hidden behind them: continuous cream sandstone fins, curved canopy edges, brass-framed doors, ribbed glass windows, and precise geometric Art Deco reliefs. The reconstructed facade must remain spatially stable and temporally coherent throughout the moving tracking shot, with correct perspective, parallax, rain-darkened surfaces, reflections, and natural occlusion when pedestrians and the cyclist pass in front. Preserve the source camera path, timing, lens character, pedestrian movement, cyclist movement, rainfall, warm marquee glow, cool blue-hour palette, and wet-pavement reflections. Do not alter or remove people, vehicles, neighboring buildings, or street furniture unrelated to the restoration work. Maintain a polished but realistic architectural-documentary finish with no flicker, warping, texture crawling, or newly invented signage. Preserve the original synchronized sound unchanged.",
  "providerSettings": {
    "klingai": {
      "keepOriginalSound": true
    }
  },
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/0e639ac5-62b9-4f5e-9295-b6e5c9e193fc.mp4",
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/90c9c697-3d98-4c1c-b8fa-552e3f97f0bb.jpg"
    ]
  }
}
```

---

[Watch video](https://assets.runware.ai/examples/klingai-video-o1-pro/ee302686-b6d1-4d45-98fe-a9fab55ed585.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "59e55a01-8a4a-4740-8beb-f08b0a4aa7bc",
  "model": "klingai:kling@o1",
  "positivePrompt": "Using both reference images as the visual foundation, create a cinematic realistic scene inside a polar glassmaking atelier. A solitary glasswright carefully shapes a luminous translucent sphere at the workbench while warm furnace light flickers across ice walls and hanging crystal instruments. Fine breath vapor curls in the cold air, tiny sparks rise, and frost glitters on tools and shelves. Start with a medium-wide establishing shot of the workshop, then slowly push in as the artisan rotates the glowing piece with calm precision. Add subtle environmental motion: swaying suspended tubing, drifting steam, shimmering reflections through glass, and soft snow visible beyond a distant doorway. End on a close view of the finished orb reflecting the entire room like a miniature frozen world. Rich contrast between amber firelight and deep cyan ice, elegant textures, highly controlled motion, premium cinematic detail.",
  "width": 1920,
  "height": 1080,
  "duration": 5,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/eb01611e-0f0d-4572-b567-41db63ee720c.jpg",
      "https://assets.runware.ai/assets/inputs/49f92964-fc1c-418e-a347-38804169bae0.jpg"
    ]
  }
}
```

---

[Watch video](https://assets.runware.ai/examples/klingai-video-o1-pro/746bd1b1-e71d-4d3c-b8f9-d03eb2e740ea.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "f7ad0dfa-6192-43b0-a1e3-47e22afa9dfc",
  "model": "klingai:kling@o1",
  "positivePrompt": "A cinematic transformation sequence inside a colossal cathedral converted into an aquarium. Begin on the first frame composition and evolve smoothly toward the last frame image. Slow floating camera movement through the central aisle, reflections rippling across stone, fish circling through towering tanks, droplets hanging in the air, subtle debris, drifting plants, shifting light rays through stained glass, a dreamlike passage of many years compressed into seconds. Emphasize continuity of architecture and subject placement while gradually changing the environment from pristine aquatic grandeur into suspended watery ruin and overgrown wonder. Highly detailed textures, atmospheric depth, graceful motion, natural physics, epic yet intimate mood.",
  "duration": 5,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/3a29e936-2c6b-4576-adae-e8a1394b6149.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/8846fe54-01e5-4c8b-9488-90bcff8212c6.jpg",
        "frame": "last"
      }
    ]
  }
}
```

---

[Watch video](https://assets.runware.ai/examples/klingai-video-o1-pro/c9443cbf-d7ae-4507-aea5-118c292aec92.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "4b240d50-1ef6-40ef-b186-290cc09b3413",
  "model": "klingai:kling@o1",
  "positivePrompt": "Animate a graceful porcelain automaton ballerina inside an opulent indoor topiary hall. Begin from the supplied frame image and create a dreamy, high-end cinematic sequence with gentle camera orbit and slow push-in movement. The automaton makes delicate rotational dance motions, fingertips and skirt panels moving with precise mechanical elegance. Spiral hedges subtly sway, suspended glass prisms catch shifting light, petals drift through the air, and thin morning haze creates depth beams across marble paths. Emphasize polished ceramic texture, cobalt floral patterns, gold filigree joints, refined fantasy realism, smooth motion, rich depth, lyrical atmosphere, and coherent subject identity throughout the shot.",
  "duration": 5,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/15cc1d41-d463-45ff-833e-2e8d1f28a05c.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

[Watch video](https://assets.runware.ai/examples/klingai-video-o1-pro/44c9b353-7465-4f02-af0c-79d6951f233e.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "3bde4059-ffc8-4afc-b15a-b87c48c8aa51",
  "model": "klingai:kling@o1",
  "positivePrompt": "Transform the source footage into a fantastical clockwork orchard at golden dawn. Replace the farmland with rows of towering fruit trees made of polished brass, copper leaves, and delicate gear-driven branches. The runner becomes a nimble courier in a cream canvas coat carrying a satchel of glowing mechanical pears. As the camera advances, ripe metal fruit clicks open to release tiny paper birds that spiral through the air. Add drifting pollen-like sparks, rotating irrigation wheels, and distant wind-powered harvest machines on the horizon. Preserve the original movement, pacing, and camera trajectory of the source video while enhancing it with cinematic depth, rich atmospheric perspective, elegant mechanical detail, and a sense of playful urgency.",
  "providerSettings": {
    "klingai": {
      "keepOriginalSound": true
    }
  },
  "inputs": {
    "video": "https://assets.runware.ai/assets/inputs/1a0b80d4-34bc-4c77-be12-370f5eb71bf2.mp4"
  }
}
```

---

[Watch video](https://assets.runware.ai/examples/klingai-video-o1-pro/2741f0e4-865c-43c1-8bdc-ff603487a391.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "c48c06bf-4095-4d07-a51a-c914d807c108",
  "model": "klingai:kling@o1",
  "positivePrompt": "On a narrow wind-carved cliff above a roaring black sea, two rival violinists face each other on separate stone platforms connected by a fractured arch bridge. Midnight sky with fast-moving silver clouds and a huge low moon. Their music seems to shape the world: each bow stroke sends visible ripples through the air, scattering pale sparks and bending mist into spirals. One performer wears a tailored ivory coat with long flowing tails, the other a deep crimson coat with metallic embroidery; both move with balletic precision. Start with a wide aerial shot circling the cliff, then push in as the duel intensifies. Waves crash far below, loose pebbles skitter across the rock, fabric whips in the wind, hair and coats react naturally. The bridge begins to crack as the musical contest peaks, small stones falling into the surf. Finish on a close-up of both musicians locking eyes as the final note hangs in the air and the moonlight floods the scene. Ultra-cinematic, dramatic contrast, rich atmosphere, highly detailed textures, fluid character animation, dynamic camera movement, realistic physics, epic and tense mood.",
  "width": 1920,
  "height": 1080,
  "duration": 10
}
```