Qwen-Image-2.1 packs image generation and editing into a 7B model
Qwen-Image-2.1: Compact, efficient, and unified image creation
Qwen-Image-2.1 is an open-source image model that unifies text-to-image generation and editing in a single 7B visual generation component. It natively generates and edits transparent images, accepts up to 10 reference images for composition, supports local edits via circles, painted annotations, or masks, and preserves portrait identity and product details. A mixed-granularity attention architecture with KV cache reuse speeds up multi-image editing while improving typography and portrait realism.
With a compact 7B visual generation component, Qwen-Image-2.1 brings image generation, transparency, and a wide range of editing capabilities together in one model.