alibaba/qwen-image-3

Qwen-Image-3.0 generates and edits images with accurate text rendering, complex layouts, and photographic detail.

9 runs

Readme

Qwen-Image-3.0

Qwen-Image-3.0 is Alibaba’s image generation and editing model, with a focus on accurate text rendering and complex layouts.

What it’s good at

  • Accurate text. Renders small, legible text and handles native rendering across many languages and fonts.
  • Complex layouts. Generates posters, infographics, and multi-element compositions in a single pass.
  • Photographic detail. Produces sharp, detailed images.
  • Image editing. Pass a reference image to edit, restyle, or transform it.

Inputs

  • prompt — what to generate or how to edit the image.
  • image — optional reference image for editing and image-to-image.
  • aspect_ratio — output aspect ratio (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2).
  • match_input_image — when editing, keep the input image’s aspect ratio.
  • negative_prompt — elements to avoid.
  • enable_prompt_expansion — automatically expand and optimize your prompt.
  • seed — set for reproducible results.

Pricing

$0.03 per output image.

Model created
Model updated