An early preview with known accuracy problems, since replaced by later Qwen-Image models, so mostly of historical interest.
Kenning's take
What it does
Qwen VLo is a multimodal model from the Qwen team that both understands and creates images, announced in June 2025 as a preview in Qwen Chat. Users could ask it to generate a picture or edit an uploaded one, for example adding objects or changing style. Qwen described it as a preview with known accuracy and consistency problems; later Qwen-Image models have since followed.
- Image generation from text in chat
- Image editing by instruction
- Understands and recreates uploaded images
- Progressive generation for text-heavy images
- Preview in Qwen Chat
Who it suits. Qwen Chat users who want to create or edit images by describing changes.
Key facts
- Category
- AI models
- Part of
- Qwen
- Made by
- Alibaba (Qwen team)
- Based in
- China
- Released
- 26 June 2025
- How to get it
- Preview in Qwen Chat at launch; current availability not confirmed
- Works on
- Web
- Free plan
- Preview in Qwen Chat at launch
FAQ
When was Qwen VLo released?
The Qwen team announced it on 26 June 2025.
How do I use Qwen VLo?
It launched as a preview inside Qwen Chat.
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-2.0
Alibaba's 7-billion-parameter model that both creates and edits images, with strong text rendering at 2K
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