KuaishouSlowUltra

Kling O3 4K Video to Video Reference

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.

4400 credits

per 5s 4K video — billed per second of output, 977/s

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

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "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"
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`prompt`	string	Yes	-	Text prompt. Refer to the reference video as @Video1, element images as @Element1, and style images as @Image1. Max 2500 characters
`video_url`	string	Yes	-	Reference video. .mp4/.mov, 3-15 seconds, 720-3840px, 23-60 fps, max 200MB
`duration`	string	No	5	Output video duration in seconds (3-15). Billed per second 3456789101112131415
`aspect_ratio`	string	No	auto	Aspect ratio of the generated video auto16:99:161:1
`elements`	array	No	-	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	No	-	Style/appearance reference images, cited as @Image1, @Image2. Elements plus image_urls total at most 4
`keep_audio`	boolean	No	true	Keep the original audio from the input video
`enable_safety_checker`	boolean	No	true	Enable the safety checker

How to Provide File Input

There are 3 ways to provide files for the video_urlimage_urls parameters:

Recommended

Image URL

Pass a publicly accessible URL directly. With the Storage API (POST /v1/files/upload-url) the file uploads straight to S3 (50MB per file) and you pass the returned file_url.

{
  "model": "fal-ai/kling-video/o3/4k/video-to-video/reference",
  "input": {
    "prompt": "your prompt here",
    "video_url": "https://example.com/image.jpg"
  }
}

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step, but the bytes pass through the API server so the whole request is capped at 10MB.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=fal-ai/kling-video/o3/4k/video-to-video/reference" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:video_url=@your_file.png"

See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

Watercolor Scene with an Element

Follow the reference video, add an element, and apply a watercolor style

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "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"
  }
}'