ZMIME
Alibaba (Qwen) · image model · Release date unconfirmed

Qwen-Image (2512)

Qwen-Image (2512) is an image model from Alibaba (Qwen). It handles text to image.

  • Image model
  • Open weights
  • Text to image
Arena score
1,125#45 of 82 · text to image
Starting price
—Not published
Largest size
—Not published
References
—Text prompts only
Quality & price

How it rates and what it costs

Text to image arena
1,125 ±3#45 of 82 · 98,272 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.

Specifications

The details

Lab
Alibaba (Qwen)
Type
Image model
Released
—
Inputs
Text prompts
Output
Images
Can do
Text to image
Weights
Open weights · Apache 2.0
Availability
Not on the API hosts we track

Arena listing

Same lab

More image models from Alibaba (Qwen)

Questions

About Qwen-Image (2512)

How good is Qwen-Image (2512)?

In blind side-by-side votes, Qwen-Image (2512) scores 1,125 for text to image (#45 of 82). Higher is better; scores within about 6 points of each other are effectively tied.

Who makes Qwen-Image (2512)?

Qwen-Image (2512) is an image model from Alibaba (Qwen).

What can Qwen-Image (2512) do?

Qwen-Image (2512) accepts text prompts and produces images. In practice: text to image.

Is Qwen-Image (2512) open source?

Yes. Alibaba (Qwen) publishes the weights under the Apache 2.0, so you can run it on your own hardware.

Where can I use Qwen-Image (2512)?

None of the API hosts we track list it yet.