dLazy AIdLazy AI
Model ReferenceVideo Models

happyhorse-1.0

Happy Horse 1.0 video model — one model covers text-to-video (t2v), first-frame-to-video (i2v), reference-to-video (r2v), and video editing (edit). The selected mode is automatically routed to the matching sub-model.

Happy Horse 1.0 video model — one model covers text-to-video (t2v), first-frame-to-video (i2v), reference-to-video (r2v), and video editing (edit). The selected mode is automatically routed to the matching sub-model.

Overview

FieldValue
Model IDhappyhorse-1-0
CLIdlazy happyhorse-1.0
MCPhappyhorse-1.0 (Claude Code surfaces this as mcp__dlazy__happyhorse-1.0)
Typevideo
ExecutionAsync task; the CLI polls until completion (--no-wait returns generateId immediately)
BatchSupports --batch <n> parallel fan-out

Parameters

ArgTypeRequiredNotes
promptstringYesPrompt
generation_mode"t2v" | "r2v" | "i2v" | "edit"NoGeneration Mode(t2v=T2V; r2v=R2V; i2v=I2V; edit=Edit); default "t2v"
firstFrameurlNoFirst Frame; image (accepts URL, local path, or data: URL); only when generation_mode="i2v"
imagesarray<url>NoImages; image (accepts URL, local path, or data: URL); max 9 items; only when generation_mode="r2v" || generation_mode="edit"
videourlNoVideo (URL); video (accepts URL, local path, or data: URL); only when generation_mode="edit"
resolution"720P" | "1080P"NoResolution; default "1080P"
ratio"16:9" | "9:16" | "1:1" | "4:3" | "3:4"NoAspect Ratio; default "16:9"; only when generation_mode="t2v" || generation_mode="r2v"
duration"3" | "4" | "5" | "6" | "7" | "8" | "9" | "10" | "11" | "12" | "13" | "14" | "15"NoDuration (s); default "5"; only when !(generation_mode="edit")
audio_setting"auto" | "origin"NoAudio Setting; default "auto"; only when generation_mode="edit"

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

CLI Examples

dlazy happyhorse-1.0 --help
dlazy happyhorse-1.0 --prompt "Write your prompt here"
dlazy happyhorse-1.0 --prompt "Write your prompt here" --dry-run
dlazy happyhorse-1.0 --prompt "Write your prompt here" --no-wait
dlazy happyhorse-1.0 --prompt "Write your prompt here" --batch 4

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__happyhorse-1.0; generic clients (e.g. OpenClaw) call it as happyhorse-1.0.

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