Qwen-Image

Generate expressive, high-fidelity images with precise text, multilingual prompts, and editing support via the open-weights 20B MMDiT foundation model. Built for accurate Chinese & English text rendering, semantic edits, and rich visual comprehension.
Up to 30 free image generations per day
Trusted by designers at

How to use Qwen-Image

1
Import your image onto the Recraft canvas or generate your own within Recraft
2
Open Edit and choose Qwen-Image, attach up to 1 reference image if needed, and add your prompt
3
Generate or refine the result, then export your file

Create precise, multilingual visuals

Qwen-Image is designed for sharp text rendering, multilingual support, and semantic image editing. Expect layouts that include paragraphs or fine-grained text (English and Chinese), accurate visual edits that preserve objects and context, and deeper visual understanding (object detection, depth, edges) built in.

FAQ

Why choose Qwen-Image in Recraft?

It is an open-source 20B parameter MMDiT foundation model, specializing in precise text rendering (especially complex or multilingual text) and strong semantic editing performance.

Does Qwen support prompt-based image editing?

Yes. The model supports TI2I (text + image→image edits) preserving visual fidelity and semantic meaning. Image editing retains context while allowing changes via text.

What export formats does Recraft support?

PNG, JPG, TIFF, PDF, and SVG for vectors from the Export panel.

Explore more