Alibaba Tongyi releases Wan2.7-Image, a unified model for image generation and editing

Coin-world Network news: According to monitoring by 1M AI News, Alibaba Tongyi Lab has released a unified image generation and editing model, Wan2.7-Image, positioning itself with the slogan “more realistic people, steadier text, and more accurate colors.” The model supports directly inputting Hex Color Codes to define a color palette. The official summary page states that it can control colors using 8 Hexcodes. On the text rendering side, it supports output of 4,000 English characters, and it also supports multiple languages such as Simplified Chinese, Traditional Chinese, English, Japanese, and Korean, as well as mixed layouts of tables and mathematical formulas. Continuous creation is another key focus of this update. Wan2.7-Image supports generating up to 12 images in a group, and supports up to 9 reference images as input, which can be used for storyboarding, series posters, and consistent character generation. On the editing side, it adds precise lasso-style selection editing and full transparency PNG generation, allowing selected elements to be separated from the background. The official landing scenarios include e-commerce listing images, short-drama storyboards, educational charts, children’s picture books, poster and invitation design. The website and API are already live.