Latest release (v2509, 25-09). Qwen-Image is an image generation foundation model that excels at complex text rendering and precise image editing, with support for multi-image editing.
Added Aug 7, 2025
Approx. Price
$0.020 per image
Model Type
both
Settings
Generation controls available for this model.
Images Per Run
Up to 4
Output images
Input Images
Up to 3
Reference/edit images accepted • Route max 30 MB
Output Sizes
Enable Safety Checker
Default
Yes
Guidance Scale
Default
2.5
How closely to follow the prompt (1-20)
Inference Steps
Default
30
Number of inference steps (2-50)
Negative Prompt
Default
N/A
Describe what you don't want in the image
Number of Images
Default
1
Resolution
Default
auto
Options (7)
auto (Auto (match input image for edits)), 1024x1024 (Square HD), 512x512 (Square), 768x1024 (Portrait (3:4)) +3 more
Seed
Default
N/A
Random seed to control the stochasticity of image generation.
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Image
#106 / 166
ELO
889.0
Appearances
4,976
95% CI
-7/7
Release Date 2025-08 · Matched as Qwen Image
Artificial Analysis APIExamples
Loading examples…
Related image models
Compare Qwen Image with similar models from the same provider or model family.
Qwen Image 2.1 Edit
wavespeed-ai/qwen-image-2.1/editEdit from up to ten reference images with natural-language instructions, strong subject preservation, flexible framing, and native output up to 2K.
Qwen Image 2.1 Edit LoRA
wavespeed-ai/qwen-image-2.1/edit-loraEdit from up to ten references while applying up to three custom LoRAs for precise identity, product, or style control at up to 2K.
Qwen Image 2.1
wavespeed-ai/qwen-image-2.1/text-to-imageCreate high-quality images with strong prompt following, multilingual text rendering, flexible framing, and native output up to 2K.
Qwen Image 2.1 LoRA
wavespeed-ai/qwen-image-2.1/text-to-image-loraGenerate Qwen Image 2.1 artwork with up to three custom character, product, or style LoRAs and native output up to 2K.
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.