Good for posters and slides heavy with text, but there are no open weights and API pricing is unconfirmed.
Kenning's take
What it does
Qwen-Image-2.0 is a single model for generating and editing images, released by Alibaba's Qwen team in February 2026. It outputs native 2048 x 2048 images, handles prompts up to 1,000 tokens and is aimed at text-heavy work such as slides, posters and infographics. At launch it was available as a free demo in Qwen Chat and through an invite-only Alibaba Cloud API, without open weights.
- Text-to-image and image editing in one model
- 7 billion parameters, down from 20 billion
- Native 2K (2048 x 2048) output
- Prompts up to 1,000 tokens
- Accurate text including Chinese calligraphy
Who it suits. Designers and marketers who need images with accurate built-in text, such as posters and slides.
Key facts
- Category
- AI models
- Part of
- Qwen
- Made by
- Alibaba (Qwen team)
- Based in
- China
- Launched
- 2026
- How to get it
- Free demo in Qwen Chat; Alibaba Cloud API (invite-only beta at launch)
- Works on
- Web, API
- Free plan
- Free demo in Qwen Chat
Reviews and write-ups
- The Decoder 2026-02-11
FAQ
When was Qwen-Image-2.0 released?
Alibaba's Qwen team released it in February 2026; The Decoder reported it on 11 February 2026.
Is Qwen-Image-2.0 free?
It can be tried free in Qwen Chat. At launch the weights were not public.
How big is Qwen-Image-2.0?
7 billion parameters.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
MAI-UI
Alibaba Tongyi research models that operate smartphone apps by looking at the screen and tapping
Qwen-Image-Layered
Open Alibaba model that splits an image into separate transparent layers so each part can be edited alone
Qwen-Image-3.0
Alibaba's hosted image model built for text-heavy layouts, taking prompts up to 4,500 tokens
Qwen VLo
Preview multimodal model from Alibaba that understands images and generates or edits them from chat prompts