# Kling O3 4K Video to Video Reference - Core.Today AI API

> Kling O3 native 4K video-to-video reference via Fal.AI. Generates a new 4K shot that follows a reference video (cited as @Video1) — its camera motion, pacing, and framing — while integrating characters/objects from element images (@Element1) and style images (@Image1). Outputs 4K directly with no upscaling pass, 3-15 seconds.

- **Provider**: Kuaishou
- **Model ID**: fal-ai/kling-video/o3/4k/video-to-video/reference
- **Category**: Video Generation
- **Credits**: 4890 per 5s 4K video — billed per second of output, 977/s
- **Speed**: Slow
- **Quality**: Ultra

## Features
- Follows a reference video's camera motion, pacing, and framing
- Integrates characters/objects from element images (@Element1)
- Style transfer from reference images (@Image1)
- Native 4K output in one step — no upscaling pass
- 3-15 second output, keeps the reference audio optionally

## Use Cases
- Re-shooting a reference shot with a new character or product
- Matching camera moves across a series of 4K ad shots
- Turning live-action reference footage into a stylized 4K scene
- Previs-to-final: block a move on cheap footage, render it in 4K

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - Text prompt. Refer to the reference video as @Video1, element images as @Element1, and style images as @Image1. Max 2500 characters
- **video_url**: string - Reference video. .mp4/.mov, 3-15 seconds, 720-3840px, 23-60 fps, max 200MB

### Optional
- **duration**: string (default: 5) - Output video duration in seconds (3-15). Billed per second
  Options: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
- **aspect_ratio**: string (default: auto) - Aspect ratio of the generated video
  Options: auto, 16:9, 9:16, 1:1
- **elements**: array - Characters/objects to include, each with a frontal_image_url and 1-3 reference_image_urls; cited as @Element1, @Element2. Elements plus image_urls total at most 4
- **image_urls**: array - Style/appearance reference images, cited as @Image1, @Image2. Elements plus image_urls total at most 4
- **keep_audio**: boolean (default: true) - Keep the original audio from the input video
- **enable_safety_checker**: boolean (default: true) - Enable the safety checker

## Examples

### Watercolor Scene with an Element
Follow the reference video, add an element, and apply a watercolor style
```json
{
  "model": "fal-ai/kling-video/o3/4k/video-to-video/reference",
  "input": {
    "prompt": "Integrate @Element1 in the scene. Style video should be following watercolor style of @Image1",
    "video_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/video_reference.mp4",
    "elements": [
      {
        "frontal_image_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/element1_front.png",
        "reference_image_urls": [
          "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/element1_reference1.png"
        ]
      }
    ],
    "image_urls": [
      "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-reference/image_url1.jpg"
    ],
    "duration": "5",
    "aspect_ratio": "auto"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- 4K is billed at 977 credits per second — iterate on shorter durations first
- Reference clips must be 3-15 seconds, at least 720px per side, and 23-60 fps
- Elements plus image_urls may total at most 4 references
- duration is a string enum ("3"-"15"); it defaults to "5" when omitted

## Documentation
https://fal.ai/models/fal-ai/kling-video/o3/4k/video-to-video/reference