dLazy AIdLazy AI
Model ReferenceImage Models

recraft-v4-pro-vector

High-fidelity text-to-vector model, 4MP-tier quality. Good for production SVG assets and detailed illustrations.

High-fidelity text-to-vector model, 4MP-tier quality. Good for production SVG assets and detailed illustrations.

Overview

FieldValue
Model IDrecraft-v4-pro-vector
CLIdlazy recraft-v4-pro-vector
MCPrecraft-v4-pro-vector (Claude Code surfaces this as mcp__dlazy__recraft-v4-pro-vector)
Typeimage
ExecutionAsync task; the CLI polls until completion (--no-wait returns generateId immediately)
BatchSupports --batch <n> parallel fan-out

Parameters

ArgTypeRequiredNotes
promptstringYesPrompt
aspect_ratio"auto" | "1:1" | "4:3" | "3:4" | "16:9" | "9:16" | "3:2" | "2:3" | "2:1" | "1:2"NoAspect Ratio; default "auto"

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

CLI Examples

dlazy recraft-v4-pro-vector --help
dlazy recraft-v4-pro-vector --prompt "Write your prompt here"
dlazy recraft-v4-pro-vector --prompt "Write your prompt here" --dry-run
dlazy recraft-v4-pro-vector --prompt "Write your prompt here" --no-wait
dlazy recraft-v4-pro-vector --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__recraft-v4-pro-vector; generic clients (e.g. OpenClaw) call it as recraft-v4-pro-vector.

See MCP setup for how to add the server.

Output

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

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

On this page