dLazy AIdLazy AI
Model ReferenceImage Models

seedream-5.0-pro

Professional tier of Seedream 5.0, stronger on fine detail, typography and complex composition. Suited to commercial key visuals and demanding brand assets.

Professional tier of Seedream 5.0, stronger on fine detail, typography and complex composition. Suited to commercial key visuals and demanding brand assets.

Overview

FieldValue
Model IDdoubao-seedream-5-0-pro
CLIdlazy seedream-5.0-pro
MCPseedream-5.0-pro (Claude Code surfaces this as mcp__dlazy__seedream-5.0-pro)
Typeimage
ExecutionAsync task; the CLI polls until completion (--no-wait returns generateId immediately)
BatchSupports --batch <n> parallel fan-out

Parameters

ArgTypeRequiredNotes
promptstringYesPrompt
imagesarray<url>NoImages; image (accepts URL, local path, or data: URL); max 10 items
resolution"2k"NoResolution; default "2k"
size"1:1" | "4:3" | "3:4" | "16:9" | "9:16" | "3:2" | "2:3" | "21:9"NoSize; default "16:9"

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

CLI Examples

dlazy seedream-5.0-pro --help
dlazy seedream-5.0-pro --prompt "Write your prompt here" --resolution "2k" --size "16:9"
dlazy seedream-5.0-pro --prompt "Write your prompt here" --resolution "2k" --size "16:9" --dry-run
dlazy seedream-5.0-pro --prompt "Write your prompt here" --resolution "2k" --size "16:9" --no-wait
dlazy seedream-5.0-pro --prompt "Write your prompt here" --resolution "2k" --size "16:9" --batch 4

Compose with a pipeline

dlazy gpt-image-2 --prompt "reference visual" \
  | dlazy seedream-5.0-pro --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__seedream-5.0-pro; generic clients (e.g. OpenClaw) call it as seedream-5.0-pro.

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