Generative Powers of Ten

Xiaojuan Wang, Janne Kontkanen, Brian Curless, Steven M. Seitz, Ira Kemelmacher-Shlizerman, Ben Mildenhall, Pratul Srinivasan, Dor Verbin, Aleksander Holynski; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 7173-7182

We present a method that uses a text-to-image model to generate consistent content across multiple image scales enabling extreme semantic zooms into a scene e.g. ranging from a wide-angle landscape view of a forest to a macro shot of an insect sitting on one of the tree branches. We achieve this through a joint multi-scale diffusion sampling approach that encourages consistency across different scales while preserving the integrity of each individual sampling process. Since each generated scale is guided by a different text prompt our method enables deeper levels of zoom than traditional super-resolution methods that may struggle to create new contextual structure at vastly different scales. We compare our method qualitatively with alternative techniques in image super-resolution and outpainting and show that our method is most effective at generating consistent multi-scale content.