Qwen Image 2.0

qwen-image-2.0

Qwen Image 2.0

qwen-image-2.0

Qwen Image 2.0 model for text-to-image and image edits. Strong prompt following, multilingual text rendering, and support for up to 3 reference images.

Added Mar 3, 2026

Approx. Price

$0.027 per image

Model Type

both

Settings

Generation controls available for this model.

Images Per Run

Up to 6

Output images

Input Images

Up to 3

Reference/edit images accepted • Route max 30 MB

Output Sizes

Auto
Square
Portrait
Landscape
up to 1,536px

Number of Images

Default

1

Resolution

Default

1024*1024

Options (6)

1024*1024 (Square (1:1)), 1280*720 (Landscape (16:9)), 720*1280 (Portrait (9:16)), 1536*1024 (Landscape (3:2)) +2 more

Seed

Number

Default

-1

Set -1 for random or use a fixed number for reproducible results

Watermark

Toggle

Default

No

Add an AI generation watermark to the output image.

Benchmarks

Human preference benchmarks sourced from Artificial Analysis.

Text to Image

#67 / 148

ELO

1105.0

Appearances

3,966

95% CI

-9/9

Image Editing

#47 / 68

ELO

1129.0

Appearances

4,015

95% CI

-10/10

Release Date 2026-03 · Matched as Qwen Image 2.0 (2026-03-03)

Artificial Analysis API

Examples

Loading examples…