Qwen's latest text-to-image model with strong prompt understanding and high-fidelity text rendering. Supports flexible sizing and reproducible seeds.
Added Dec 22, 2025
Approx. Price
$0.025 per image
Model Type
text-to-image
Settings
Generation controls available for this model.
Images Per Run
Up to 4
Output images
Input Images
N/A
No reference/edit image input
Output Sizes
Number of Images
Default
1
Output Format
Default
jpeg
Options (3)
JPEG, PNG, WebP
Choose the output image format
Resolution
Default
1024x1024
Options (8)
1024x1024 (Square (1:1)), 1024x1536 (Portrait (2:3)), 1536x1024 (Landscape (3:2)), 1536x1536 (Max square (1536x1536)) +4 more
Seed
Default
-1
Set -1 for random or use a fixed number for reproducible results
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Image
#56 / 151
ELO
1172.0
Appearances
3,833
95% CI
-9/9
Release Date 2025-12 · Matched as Qwen Image Max 2512
Artificial Analysis APIExamples
Loading examples…
Related image models
Compare Qwen Image 2512 with similar models from the same provider or model family.
Qwen Image 3 Pro
qwen-image-3-proAlibaba's professional Qwen Image 3 model for high-quality 1K or 2K text-to-image generation and precise edits with up to 3 reference images.
Qwen Image 3
qwen-image-3Alibaba's Qwen Image 3 for text-to-image generation and precise edits with up to 3 reference images. Supports Chinese and English prompts, strong text rendering, and automatic prompt expansion.
Qwen Image 2.0 Pro
qwen-image-2.0-proPremium Qwen Image 2.0 Pro model for high-fidelity text-to-image and advanced image editing workflows.
Qwen Image 2.0
qwen-image-2.0Qwen 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.
Qwen Image 2.0 Pro (2026-03-03)
qwen-image-2.0-pro-2026-03-03Dated March 3, 2026 Qwen Image 2.0 Pro model for high-fidelity text-to-image and advanced image editing workflows.
Qwen Image Max
qwen-image-maxQwen Image Max is a text-to-image model with high-quality image generation supporting Chinese and English prompts.