Alibaba’s Qwen open-sources Qwen-Image-2.1 for unified image generation and editing

Alibaba has appointed senior AI researcher Dayiheng Liu as the head of its Qwen large language models, providing leadership clarity following several reorganizations. Simultaneously, the Qwen team released Qwen-Image-2.1, an open-source model with 7 billion parameters. This model integrates text-to-image generation and image editing into one workflow. It natively supports local edits, transparent image generation, and composition utilizing up to 10 reference images, streamlining the overall process for visual content creation and modification.