technologyDevelopingUpdated 6 min ago · since 20 Sept 2026

Alibaba Qwen opensources Qwen-Image-2.1 image model

According to IT Home, Alibaba’s Qianwen today announced Qwen-Image-2.1, an open-source image model that combines text-to-image generation and image editing in one system. The visual generation component has 7B parameters and native support for transparent image generation and editing, with lightweight design and optimized inference to balance quality and cost. The model also supports up to 10 reference images for enhanced local editing and fidelity across editing tasks.

1 source1 country1 article1 independent outletsSource strength 22/100 ⓘAlibaba
Alibaba Qwen opensources Qwen-Image-2.1 image model
coda.news analysis

Key facts

  1. 01Qwen-Image-2.1 combines text-to-image generation and image editing in a single model.
  2. 02The visual generation component uses 7 billion parameters.
  3. 03The model native supports generating and editing transparent images.
  4. 04It supports up to 10 reference images for enhanced local editing and fidelity.

AI-generated from the sources below. Always check the originals.

How each country tells it

So far our sources show coverage from one country. Perspectives appear once we find reports from a second country.

Sources

Summaries are AI-generated from the linked sources and may contain errors; always check the originals. We summarise and link; we never republish articles. Photos come from openly licensed libraries, official publicity material and brand logos, credited to their sources. If you own an image and want it credited differently or removed, email info@coda.news and we will act promptly.