Alibaba (Qwen) · image model · Released Aug 7, 2025Qwen-Image
Text-to-image foundation model with multilingual text rendering.
- Arena score
- 1,057#66 of 82 · text to image
- Starting price
- —Not published
- Largest size
- —Not published
- References
- —Text prompts only
How it rates and what it costs
- Text to image arena
- 1,057 ±3#66 of 82 · 84,534 votes
Arena scores come from blind, side-by-side human votes on the same prompts (higher is better; ± is the 95% range). Boards updated Oct 26, 2026.
The details
- Lab
- Alibaba (Qwen)
- Type
- Image model
- Released
- Aug 7, 2025
- Inputs
- Text prompts
- Output
- Images
- Can do
- Text to image
- Weights
- Proprietary
- Availability
- 1 API host
More image models from Alibaba (Qwen)
About Qwen-Image
How good is Qwen-Image?
In blind side-by-side votes, Qwen-Image scores 1,057 for text to image (#66 of 82). Higher is better; scores within about 6 points of each other are effectively tied.
Who makes Qwen-Image?
Qwen-Image is an image model from Alibaba (Qwen), released Aug 7, 2025.
What can Qwen-Image do?
Qwen-Image accepts text prompts and produces images. In practice: text to image.
Is Qwen-Image open source?
No. Qwen-Image is proprietary; you use it through an API or partner apps.
Where can I use Qwen-Image?
It is listed by 1 API host we track.
What are the alternatives to Qwen-Image?
The closest image models from other labs, by release date, are Seedream 4.0 (ByteDance Seed, Sep 9, 2025), Lucid Origin (Leonardo.Ai, Jun 1, 2025), GPT-5 Image (OpenAI, Oct 14, 2025) and FLUX.1 Kontext Max (Black Forest Labs, May 29, 2025).