Large scale datasets of images with text descriptions have enabled powerful models that represent and generate pixels. But progress in 3D generation has been slow due to the lack of 3D data and efficient architectures. In this talk, I’ll present DreamFields and DreamFusion: two approaches that enable 3D generation from 2D priors using no 3D data. By turning 2D priors into loss functions, we can optimize 3D models (NeRFs) from scratch via gradient descent. These methods enable high-quality generation of 3D objects from diverse text prompts. Finally, I’ll discuss a fundamental problem with our approach and how progress on pixel-space priors like Imagen Video and 3DiM may unlock new 3D capabilities.