WonderWorld can be used to create interactive 3D scenes from a single image. It is the result of research at Stanford University and MIT. WonderWorld allows users to define scene content and layouts in real time and explore the resulting 3D worlds with low latency. At its core is a new rendering method called Fast LAyered Gaussian Surfels (FLAGS), which allows for rapid generation in less than 10 seconds. Unlike previous methods, WonderWorld requires only one input image and optimizes geometry more efficiently. Users can specify new content via text and define where to generate new scenes by moving the camera.