dLazy AIdLazy AI
Model ReferenceVideo Models

jimeng-omnihuman-1.5

Jimeng digital human model: combines any-ratio character/subject image with audio to generate high-quality digital human videos.

Jimeng digital human model: combines any-ratio character/subject image with audio to generate high-quality digital human videos.

Overview

FieldValue
Model IDjimeng-omnihuman-1-5
CLIdlazy jimeng-omnihuman-1.5
MCPjimeng-omnihuman-1.5 (Claude Code surfaces this as mcp__dlazy__jimeng-omnihuman-1.5)
Typevideo
ExecutionAsync task; the CLI polls until completion (--no-wait returns generateId immediately)
BatchSupports --batch <n> parallel fan-out

Parameters

ArgTypeRequiredNotes
imagesarray<url>YesImages; image (accepts URL, local path, or data: URL); max 1 items
audioarray<url>YesAudio; audio (accepts URL, local path, or data: URL); max 1 items
promptstringNoPrompt
resolution"720p" | "1080p"NoResolution; default "1080p"
fast_modestringNoFast Mode; default false

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

CLI Examples

dlazy jimeng-omnihuman-1.5 --help
dlazy jimeng-omnihuman-1.5 --images "https://example.com/reference.jpg" --audio "https://example.com/source.mp3" --prompt "Write your prompt here"
dlazy jimeng-omnihuman-1.5 --images "./local-image.png" --audio "https://example.com/source.mp3" --prompt "Write your prompt here"
dlazy jimeng-omnihuman-1.5 --images "https://example.com/reference.jpg" --audio "https://example.com/source.mp3" --prompt "Write your prompt here" --dry-run
dlazy jimeng-omnihuman-1.5 --images "https://example.com/reference.jpg" --audio "https://example.com/source.mp3" --prompt "Write your prompt here" --no-wait
dlazy jimeng-omnihuman-1.5 --images "https://example.com/reference.jpg" --audio "https://example.com/source.mp3" --prompt "Write your prompt here" --batch 4

Compose with a pipeline

dlazy gpt-image-2 --prompt "reference visual" \
  | dlazy jimeng-omnihuman-1.5 --images - --prompt "Write your prompt here"

MCP

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__jimeng-omnihuman-1.5; generic clients (e.g. OpenClaw) call it as jimeng-omnihuman-1.5.

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.

On this page