video
kling-v3-omni-4k
background_tasks

Kling 3 Omni 4K - Generate 4K video from text or image

Generate AI video using Kling 3 Omni at 4K resolution, with the same multi-modal capabilities.

Features:

  • Text-to-video: Generate videos from text prompts
  • Image-to-video: Use start and/or end frame images to guide generation
  • Multi-shot: Create videos with up to 6 shots (max 15s total)
  • Element control: Include reference images for consistent character/style

Duration: 3-15 seconds Quality: 4K is generated natively by the model, it is not an upscale of a lower resolution output. Generation takes longer and is priced differently than Pro and Standard.

Note: For video-to-video generation using a reference video, use the /ai/reference-to-video/kling-v3-omni-pro endpoint instead.

post/v1/ai/video/kling-v3-omni-4k

Request

  • Base URL: https://api.magnific.com
  • URL: https://api.magnific.com/v1/ai/video/kling-v3-omni-4k
  • Auth: API key in header x-magnific-api-key

Request body

webhook_urlstring uri

Optional callback URL that receives asynchronous notifications when the task changes status. The payload includes the task status and result URL when completed.

promptstring

Text prompt describing the desired video content. Maximum 2500 characters.

Usage by mode:

  • Text-to-video: Required unless multi_prompt is provided
  • Image-to-video: Either prompt or multi_prompt must be provided, but not both
multi_promptstring[]

List of prompts for multi-shot video generation. Each item is a string prompt for that shot. Use with shot_type to control multi-shot behavior.

Only effective when shot_type is set. When multi_prompt is provided without an explicit shot_type, it defaults to "customize".

shot_type'customize'

Controls how multi-shot video generation is segmented for Kling 3 Omni.

  • customize: User provides explicit per-shot prompts via the multi_prompt array.

Currently only "customize" is supported for Omni endpoints.

image_urlstring

URL of the start frame image for image-to-video generation. Required for image-to-video mode.

Image requirements:

  • Minimum: 300x300 pixels
  • Maximum: 10MB file size
  • Formats: JPG, JPEG, PNG
start_image_urlstring

Image to use as the first frame of the video. Use together with end_image_url to control both start and end frames in image-to-video mode.

end_image_urlstring

Image to use as the last frame of the video. Optional for image-to-video mode to guide the final frame.

image_urlsstring[]

Reference images for style/appearance guidance. Reference in your prompt as @Image1, @Image2, etc. Maximum 4 reference images.

generate_audioboolean

Whether to generate native audio for the video.

aspect_ratio'auto' | '16:9' | '9:16' | '1:1'

Aspect ratio for Kling V3 Omni video generation:

  • auto: Automatically match the input image aspect ratio (image-to-video only)
  • 16:9: Landscape (widescreen)
  • 9:16: Portrait (vertical)
  • 1:1: Square
duration'3' | '4' | '5' | '6' | '7' | '8' | '9' | '10' | '11' | '12' | '13' | '14' | '15'

Duration of the generated video in seconds.

Range: 3-15 seconds Note: When using multi-shot mode, total duration across all shots cannot exceed 15 seconds.

Response

OK - Task created successfully

unknown required

Changes

No recorded changes to this operation across all 1 revision of this API.