Qwen Image 2.0 model for text-to-image and image edits. Strong prompt following, multilingual text rendering, and support for up to 4 reference images.
Added Mar 3, 2026
Approx. Price
$0.027 per image
Model Type
both
Preview Examples
3
Generation controls available for this model.
Images Per Run
Up to 6
Resolution Options
6
1024*1024 (Square (1:1)), 1280*720 (Landscape (16:9)), 720*1280 (Portrait (9:16)) +3 more
Tunable Settings
4
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
Default
-1
Set -1 for random or use a fixed number for reproducible results
Watermark
Default
No
Add an AI generation watermark to the output image.
Human preference benchmarks sourced from LMArena.
Text to Image
#25 / 57
Arena Score
1116.7
Votes
38,447
Confidence Interval
1111.7 - 1121.6
Image Edit
#20 / 45
Arena Score
1257.2
Votes
64,597
Confidence Interval
1252.8 - 1261.6
Published 2026-04-23 · Matched as qwen-image-2.0-2026-03-03
LMArena Dataset
A young woman with short red hair and round glasses wearing a dark green trench coat, standing in a rainy Tokyo street at night. Neon signs reflected in puddles. Cinematic still, anamorphic lens look.
A colossal ancient tree growing through a collapsed cathedral, roots wrapped around gothic pillars, bioluminescent fungi illuminating the darkness, tiny floating spirits drifting upward like embers. Painted in the style of Craig Mullins meets Hayao Miyazaki, rich atmospheric perspective, matte painting quality, 8K resolution, epic scale.
A perfectly isometric view of a modern Japanese minimalist apartment interior. Tatami flooring, low wooden furniture, shoji screens, indoor plants. Natural daylight from large windows. Not a miniature, captured as a real photograph that happens to be perfectly isometric.
