kling-v3-omni

Kling Omni video model, supports multiple reference images, duration, mode (std/pro), and optional audio. Suitable for highly controlled video synthesis tasks.

Overview

Field	Value
Model ID	`kling-v3-omni`
CLI	`dlazy kling-v3-omni`
MCP	`kling-v3-omni` (Claude Code surfaces this as `mcp__dlazy__kling-v3-omni`)
Type	`video`
Execution	Async task; the CLI polls until completion (`--no-wait` returns `generateId` immediately)
Batch	Supports `--batch <n>` parallel fan-out

Parameters

Arg	Type	Required	Notes
`prompt`	string	Yes	Prompt
`generation_mode`	"frames" \| "components"	No	Generation Mode（frames=Frames; components=Components）; default `"frames"`
`images`	array<url>	No	Images; image (accepts URL, local path, or data: URL); max 7 items
`subjects`	array<string>	No	Subjects; max 3 items; only when !(generation_mode="frames")
`videos`	array<url>	No	Videos; video (accepts URL, local path, or data: URL); max 1 items; only when !(generation_mode="frames")
`video_refer_type`	"feature" \| "base"	No	Video Refer Type; default `"feature"`; only when videos is non-empty
`keep_original_sound`	string	No	Keep Original Sound; default `false`; only when videos is non-empty
`aspect_ratio`	"16:9" \| "9:16" \| "1:1"	No	Aspect Ratio; default `"16:9"`; only when !(videos is non-empty && video_refer_type="base")
`duration`	"3" \| "4" \| "5" \| "6" \| "7" \| "8" \| "9" \| "10" \| "11" \| "12" \| "13" \| "14" \| "15"	No	Duration (s); default `"5"`; only when !(videos is non-empty && video_refer_type="base")
`mode`	"std" \| "pro"	No	Mode; default `"std"`
`sound`	string	No	Sound Effect; default `false`

--input @file.json or --input '{...}' can supply all args at once; flags take precedence over --input keys.

CLI Examples

dlazy kling-v3-omni --help
dlazy kling-v3-omni --prompt "Write your prompt here" --images "https://example.com/reference1.jpg" "https://example.com/reference2.jpg"
dlazy kling-v3-omni --prompt "Write your prompt here" --images "./local-image.png"
dlazy kling-v3-omni --prompt "Write your prompt here" --images "https://example.com/reference1.jpg" "https://example.com/reference2.jpg" --dry-run
dlazy kling-v3-omni --prompt "Write your prompt here" --images "https://example.com/reference1.jpg" "https://example.com/reference2.jpg" --no-wait
dlazy kling-v3-omni --prompt "Write your prompt here" --images "https://example.com/reference1.jpg" "https://example.com/reference2.jpg" --batch 4

Compose with a pipeline

dlazy gpt-image-2 --prompt "reference visual" \
  | dlazy kling-v3-omni --images - --prompt "Write your prompt here"

MCP is consumed by AI clients, not handwritten. Once dLazy is registered as an MCP server the tool appears in the client's tool list — Claude Code surfaces it as mcp__dlazy__kling-v3-omni; generic clients (e.g. OpenClaw) call it as kling-v3-omni.

See MCP setup for how to add the server.

Output

{
  "outputs": [
    { "type": "video", "id": "o_...", "url": "https://files.dlazy.com/result.mp4", "mimeType": "video/mp4" }
  ]
}

Media tools emit image / video / audio / file outputs. Use --output url to print only the URLs on stdout.