We've just put out an awesome new paper on text-to-3D using Stable Diffusion, Collaborative Control and Geometry Images! check it out! :D
Does 3D generation always have to be either slow or complex and data-hungry?π€ We donβt think so! With Geometry Image Diffusion, weβre all about reusing (and recycling β»οΈ) what already works β making it faster and easier by reducing complexity and data needs π(1/10)