kling-v3-omni

Kuaishou’s Kling V3 Omni video generation model. Create videos from text, images, and video references with multi-shot storyboarding.

Kling V3 Omni is Kuaishou’s latest video generation model, available through AnyFast API. The Omni model can achieve various capabilities through prompts combined with elements, images, videos, and other content — supporting text-to-video, image-to-video, video editing, multi-shot storyboarding, and synchronized sound generation.

This page uses Kling’s Legacy API: POST /kling/v1/videos/omni-video with model_name: "kling-3.0-omni". It does not use the upgraded /omni-video/kling-3.0-omni contents/settings/options structure.

Key capabilities

• Text-to-Video — Generate videos from text prompts up to 15 seconds
• Image-to-Video — Use reference images as first/end frames to guide video generation
• Video Editing — Edit existing videos: add/remove elements, change styles, colors, weather, etc.
• Multi-Shot Storyboarding — Create up to 6 storyboard shots with custom prompts and durations
• Sound Generation — Optionally generate synchronized sound effects with the video
• Flexible Aspect Ratios — Support for 16:9, 9:16, and 1:1 output formats
• Multiple Output Modes — std (720p), pro (1080p), and 4k

Quick example

cURL — Text to Video

curl https://www.anyfast.ai/kling/v1/videos/omni-video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "kling-3.0-omni",
    "prompt": "A cat walking gracefully across a sunlit garden, cinematic lighting",
    "duration": "5",
    "mode": "pro",
    "aspect_ratio": "16:9"
  }'

Query task result

After creating a task, query its status using the task ID:

cURL

curl https://www.anyfast.ai/kling/v1/videos/omni-video/{task_id} \
  -H "Authorization: Bearer YOUR_API_KEY"

Parameters

Parameter	Type	Required	Description
model_name	string	Yes	Must be kling-3.0-omni
prompt	string	Conditional	Text prompt (max 2500 chars). Required for single-shot and intelligent storyboard generation
mode	string	No	std (720p), pro (1080p), or 4k. Default: pro
aspect_ratio	string	Conditional	16:9, 9:16, or 1:1. Required without first-frame or video editing
duration	string	No	Video duration 3–15 seconds. Default: 5
image_list	array	No	Reference images (first/end frame, scene, style)
video_list	array	No	Reference videos (editing or style reference)
element_list	array	No	Reference elements from Kling element library
multi_shot	boolean	No	Enable multi-shot storyboarding. Default: false; customized storyboards use multi_prompt, intelligent storyboards use prompt
shot_type	string	Conditional	customize or intelligence. Required when multi_shot is true
multi_prompt	array	Conditional	Storyboard shot info (1–6 shots). Required for customized storyboards
sound	string	No	on or off. Generate sound with video. Default: off
watermark_info	object	No	Set enabled to generate an additional watermarked result

Media and combination rules

• Reference images support URL or raw Base64 in .jpg, .jpeg, or .png, up to 10 MB, with both dimensions at least 300 px and an aspect ratio from 1:2.5 to 2.5:1. A last frame requires a first frame.
• Reference videos support .mp4 and .mov, one video per request, 3–15.5 seconds, up to 200 MB, 24–60 fps. Width and height must be 700–4553 px, total pixels must not exceed 8,294,400, and aspect ratio must be between 1:2.5 and 2.5:1.
• refer_type: "base" edits the input video: duration is ignored, multi-shot and first/last frames are unavailable, and sound must be off.
• refer_type: "feature" uses video content, action, style, or camera movement as a reference. It supports intelligent multi-shot generation, while sound must remain off.
• Without a reference video, reference image and multi-image element totals are limited to 7; with a reference video, the corresponding total is limited to 4. Up to 3 video-character elements are supported without a reference video, and up to 1 with one.

API Reference

View the interactive API playground for Kling V3 Omni.