Alibaba's Qwen team has open-sourced Qwen-Image-2.1, a 7-billion parameter visual model that integrates text-to-image generation and image editing into a single architecture. The release combines both capabilities natively, streamlining workflows for creators and developers working with AI-generated visuals. The model supports transparent image generation and editing, accepts up to 10 reference images for multi-image composition, and enables local editing through selection and inpainting tools. It also delivers enhanced fidelity for portrait and product editing alongside improved text layout rendering.