Kling AI

Kling Omni Video

Kling 3.0 Omni can create a new clip, animate start and end images, use visual references, or edit an existing video from one model entry. Its structured multi-shot prompting is useful when a short sequence needs explicit shot boundaries, while reference roles determine whether source media supplies content, style, camera language, or a base video to edit.

How to use this model

  1. 1

    Decide whether you are generating from scratch, animating images, guiding with references, or editing an existing video.

  2. 2

    Attach only the media required for that workflow and assign each reference a clear role in the prompt.

  3. 3

    For a multi-shot clip, describe each shot in order with its action, framing, camera transition, and sound.

  4. 4

    For video editing, identify the requested change and explicitly name the subjects, motion, framing, and audio that must remain.

  5. 5

    Set duration, output mode, and audio generation, then review continuity across every shot boundary.

3.0 OmniAvailable

3.0 Omni

This version handles text, start/end images, reference images, and base or feature video references in one workflow. The prompt can be structured as multiple ordered shots, and audio generation is controlled separately.

Try now

Properties

  • Supports text, image, reference-image, and reference-video inputs.
  • Supports video editing, multi-shot prompting, and optional native audio.

How to use this model

  1. 1

    Select generation, reference, or editing workflow and add only its required media.

  2. 2

    Assign every image or video reference a role in the prompt.

  3. 3

    Describe multi-shot sequences in order with transitions and sound cues.

  4. 4

    Set duration, mode, and audio, then review cross-shot consistency.

Examples

Wide natural motion generated with Kling Omni Video.

Parameters

Resolution

mode
Optional

'standard' generates 720p, 'pro' generates 1080p, '4k' generates 4K. 4K does not support reference_video.

Default: pro

  • standard

  • pro

  • 4k

Prompt

prompt
Optional

Text prompt for video generation. Supports <<<image_1>>>, <<<video_1>>> template references. Max 2500 characters.

Default:

Duration

duration
Optional

Video duration in seconds (3-15). Ignored for video editing (base).

Default: 5Range: 3 – 15

Start Image

start_image
Optional

First frame image. Supports .jpg/.jpeg/.png, max 10MB, min 300px, aspect ratio 1:2.5 to 2.5:1.

End Image

end_image
Optional

Last frame image. Requires start_image. Supports .jpg/.jpeg/.png, max 10MB, min 300px.

Aspect Ratio

aspect_ratio
Optional

Aspect ratio. Required when not using start frame or video editing.

Default: 16:9

  • 16:9

  • 1:1

  • 9:16

Multi Prompt

multi_prompt
Optional

Structured multi-shot input. Up to 6 shots; each shot has prompt, optional image_url, and duration.

Generate Audio

generate_audio
Optional

Generate native audio. Mutually exclusive with reference video.

Default: false

Reference Video

reference_video
Optional

Reference video (.mp4/.mov). Duration 3-10s, resolution 720-2160px per side, max 200MB.

Reference Images

reference_images
Optional

Reference images for elements, scenes, or styles. Supports .jpg/.jpeg/.png. Max 7 without video, 4 with video.

Keep Original Sound

keep_original_sound
Optional

Keep original sound from reference video.

Default: true

Video Reference Type

video_reference_type
Optional

How to use reference video: 'feature' for style/camera reference, 'base' for video editing.

Default: feature

  • feature

  • base