seedream-4.5
High-quality text-to-image/image-to-image model, suitable for posters, realism, and creative scenes. Supports prompt + multiple reference images, outputting single high-res images (2K/4K).
High-quality text-to-image/image-to-image model, suitable for posters, realism, and creative scenes. Supports prompt + multiple reference images, outputting single high-res images (2K/4K).
Overview
| Field | Value |
|---|---|
| Model ID | doubao-seedream-4-5 |
| CLI | dlazy seedream-4.5 |
| MCP | seedream-4.5 (Claude Code surfaces this as mcp__dlazy__seedream-4.5) |
| Type | image |
| 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 |
images | array<url> | No | Images; image (accepts URL, local path, or data: URL); max 10 items |
resolution | "2k" | "4k" | No | Resolution; default "2k" |
size | "1:1" | "4:3" | "3:4" | "16:9" | "9:16" | "3:2" | "2:3" | "21:9" | No | Size; default "16:9" |
--input @file.jsonor--input '{...}'can supply all args at once; flags take precedence over--inputkeys.
CLI Examples
dlazy seedream-4.5 --help
dlazy seedream-4.5 --prompt "Write your prompt here" --images "https://example.com/reference1.jpg" "https://example.com/reference2.jpg"
dlazy seedream-4.5 --prompt "Write your prompt here" --images "./local-image.png"
dlazy seedream-4.5 --prompt "Write your prompt here" --images "https://example.com/reference1.jpg" "https://example.com/reference2.jpg" --dry-run
dlazy seedream-4.5 --prompt "Write your prompt here" --images "https://example.com/reference1.jpg" "https://example.com/reference2.jpg" --no-wait
dlazy seedream-4.5 --prompt "Write your prompt here" --images "https://example.com/reference1.jpg" "https://example.com/reference2.jpg" --batch 4Compose with a pipeline
dlazy gpt-image-2 --prompt "reference visual" \
| dlazy seedream-4.5 --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__seedream-4.5; generic clients (e.g. OpenClaw) call it as seedream-4.5.
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.
recraft-v4-vector
Text-to-vector model that outputs SVG results. Suitable for logos, icons, and scalable design assets.
seedream-5.0
Full version of the Doubao image model, generating 2K/3K/4K images from prompts and reference images. Suited to key visuals, posters and anything meant for large-format print.