qwen-image-2-pro
Alibaba Bailian qwen-image-2.0-pro general image generation. Excels at complex text rendering, multi-line layout, photorealistic detail, and strong semantic adherence — great for mixed text/image designs.
Alibaba Bailian qwen-image-2.0-pro general image generation. Excels at complex text rendering, multi-line layout, photorealistic detail, and strong semantic adherence — great for mixed text/image designs.
Overview
| Field | Value |
|---|---|
| Model ID | qwen-image-2-pro |
| CLI | dlazy qwen-image-2-pro |
| MCP | qwen-image-2-pro (Claude Code surfaces this as mcp__dlazy__qwen-image-2-pro) |
| 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 3 items |
negative_prompt | string | No | Negative Prompt (describe what you don't want in the image); default "" |
size | "26881536" | "15362688" | "20482048" | "23681728" | "1728*2368" | No | Size; default "2048*2048" |
prompt_extend | string | No | Prompt Rewrite; default true |
--input @file.jsonor--input '{...}'can supply all args at once; flags take precedence over--inputkeys.
CLI Examples
dlazy qwen-image-2-pro --help
dlazy qwen-image-2-pro --prompt "Write your prompt here" --images "https://example.com/reference1.jpg" "https://example.com/reference2.jpg"
dlazy qwen-image-2-pro --prompt "Write your prompt here" --images "./local-image.png"
dlazy qwen-image-2-pro --prompt "Write your prompt here" --images "https://example.com/reference1.jpg" "https://example.com/reference2.jpg" --dry-run
dlazy qwen-image-2-pro --prompt "Write your prompt here" --images "https://example.com/reference1.jpg" "https://example.com/reference2.jpg" --no-wait
dlazy qwen-image-2-pro --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 qwen-image-2-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__qwen-image-2-pro; generic clients (e.g. OpenClaw) call it as qwen-image-2-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.