All models

Image generation & editing

Qwen Image 2.1 Turbo

Create Qwen Image 2.1 Turbo drafts from text or visual references.

Loading model settings…

Your prompt, settings, and references stay together in a new Canvas.

01 / Meet the model

What can Qwen Image 2.1 Turbo do?

Qwen Image 2.1 Turbo offers prompt-led still-image creation with optional references. Select a supported aspect ratio and resolution, then describe the subject, setting and desired visual style. Compare the generated image with the supplied references before using it as a final asset.

02 / Choose it for

Where Qwen Image 2.1 Turbo fits best

Text-led exploration

turn a written brief into a still image.

Reference revisions

provide images to guide a new composition.

Format selection

choose among the available ratios and sizes.

03 / Before you create

Qwen Image 2.1 Turbo specifications

Model settings. Availability, input mode, and references can narrow the choices offered in Canvas.

Inputs on this page
Text prompt · optional reference images
Aspect ratios
1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3 · 21:9
Resolution
1K · 2K
Duration
Still image; no clip duration
Audio
Not applicable to still images
Reference images
0–10

04 / A closer look

Questions about Qwen Image 2.1 Turbo

Can I use Qwen Image 2.1 Turbo without reference images?

Yes. References are optional, so you can begin with a prompt and add images when you want to guide the subject or composition. Available settings appear in the composer.

What can I use as input for Qwen Image 2.1 Turbo?

Text prompt · optional reference images. The input controls above show the options available for your selected mode.

Which formats does Qwen Image 2.1 Turbo support?

1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3 · 21:9. 1K · 2K.

How do I choose settings for Qwen Image 2.1 Turbo?

Start with the format you intend to publish, then choose the available output settings. Changing inputs can change the choices. Review the current Gem estimate before Generate; availability and cost can vary.

Explore another approach

Browse all models →