AI 工作流程画布现在可以生成 3D 世界。这意味着什么。

Google DeepMind has recently launched Project Genie, based on Genie 3 technology, which generates fully interactive 3D worlds from text or image prompts at a frame rate of 20 to 24 frames per second. Users can navigate these worlds in real time, with the AI generating the path ahead as they move. This represents the most impressive demonstration of AI world generation to date. However, Genie is still a research prototype and is only available to AI Ultra subscribers in the US through Google Labs. Users can explore short interactive environments, but they cannot connect it to their creative workflows, feed the output into a video pipeline, or import 3D objects to compose scenes and capture production-ready renders. In the node-based AI canvas space, existing tools only generate flat images, resulting in 2D outputs across all workflows.