谷歌近日宣布推出一款名为Genie的AI基础世界模型，该模型能够通过一张图片生成一个交互式的虚拟世界。这一突破性技术被谷歌定义为“生成式AI的一种新模式”。Genie模型拥有110亿参数，能够生成高度互动的环境，用户可以在其中以逐帧方式进行操作。谷歌表示，Genie的发布标志着“图/文生成交互世界”新时代的开启，并有望成为推动通用AI Agent发展的重要力量。
英文标题：Google Unveils Genie, an AI Model That Generates Interactive Worlds from a Single Image
英文关键词：AI Foundation Model, Interactive Generation, Genie
英文新闻内容：
Google has recently announced the launch of Genie, an AI foundation model that can create interactive virtual worlds from a single image. This groundbreaking technology is defined by Google as “a new mode of generative AI.” Genie, which boasts 11 billion parameters, generates highly interactive environments where users can operate frame by frame. Google states that the release of Genie signals the onset of a new era in “image/text-to-interactive world generation” and is expected to serve as a catalyst for the development of general AI agents.
【来源】https://www.chinastarmarket.cn/detail/1604953
Views: 1