According to 1M AI News monitoring, Alibaba Tongyi Laboratory has released Wan2.7-Image, a unified model for image generation and editing, focusing on “more real people, steadier text, and more accurate colors.”
The model supports directly inputting a Hex Color Code to define a color palette. The official summary page states it can be used to control 8 types of Hexcode. On the text rendering side, it supports outputting 4,000 English characters, and 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 highlight of this update. Wan2.7-Image supports generating up to 12-image group compositions, and accepts up to 9 reference images, which can be used for storyboarding, series posters, and character-consistent generation. On the editing side, it has added precise lasso selection editing and full transparent channel PNG generation, allowing the selected elements to be separated from the background. The official provided real-world scenarios include e-commerce product listing images, short drama storyboards, educational charts, children’s picture books, poster and invitation design. The website and API have been launched.
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
