Image generation

Qwen Image 3.0 Pro

Generate an original image from a text prompt using Alibaba Qwen Image 3.0 Pro, at 1K or 2K.

Text to image only. Returns the URL of the generated image. That URL is temporary: Goro holds a run's results for 24 hours and nothing guarantees the file outlives that, so collect what you need within 24 hours.

When to use it

Use for structured layouts, posters and infographics with a lot of legible text, and for realistic scenes described in Chinese or English. A negative prompt is available for the things you do not want in the frame. Text to image only: this model bills every reference image, so editing is not offered here.

Inputs

Qwen Image 3.0 Pro takes 5 fields, 1 of them required. Anything you leave out falls back to the tool's own default.

How to call it

Connect once and your agent can reach Qwen Image 3.0 Pro the same way it reaches everything else in the catalog. Add Goro as an MCP connector, or paste the setup line into an agent that reads skills.

Or plain HTTP

POST /v1/run

{
  "endpoint": "image.qwen",
  "input": {
    "prompt": "A poster for a jazz night, art deco lettering reading 'Blue Hour', navy and gold.",
    "image_size": "1:1",
    "resolution": "2K",
    "output_format": "png"
  }
}