During the ongoing World Artificial Intelligence Conference,quick workerSenior Vice President and Head of Main Site Business and Community Science Gai Kun announced that KuaishouVincent Figure Large ModelKetuformalOpen Source, hoping to build a more prosperous Wenshengtu large model community ecology together.
Kuaishou's "KeTu" model was opened to the public in May this year. It has now been launched in web version and WeChat mini-program, supporting two types of functions: text-generated images and image-generated images. It can be used for AI image creation and AI image customization.
It was found that in the AI creation module, users only need to enter the description text and select the desired painting style to quickly obtain exclusive AI paintings. Among them, the painting style can be selected from default, Pixar, cartoon blind box, Shinkai Makoto, anime 3D, nostalgic anime, video games, watercolor illustrations, Monet oil paintings, high-definition realism, etc.
In addition, users can also upload reference images, and KeTu will refer to the style theme of the uploaded image to generate works that match the text description.
Kuaishou's large-scale literary image model "Ketu" announced to be open source, now available on WeChat applet and web version
In terms of AI image customization, it supports two modes: stylized and realistic. After uploading the avatar, users can choose from modes such as Red Diamond Noble, My Childhood, Clay World, Colorful Glass, Dreamy Monet, Sweet Valentine's Day, Spring Cartoon, and Watercolor Romance. Interested friends can try it by themselves.