Given a caption, DreamFusion generates relightable 3D objects with high-fidelity appearance, depth, and normals. Objects are represented as a Neural Radiance Field and leverage a pretrained text-to-image diffusion prior such as Imagen.
This text to content A.I stuff is both wild and exciting. I wonder what the future of these projects look like, I imagine with some refinement you could make entire game assets fairly easy
Product Hunt