CSM AI Reviews

3D content creation is a time-consuming and complex task for graphic designers, digital artists, and game developers. It can take hours, or even days, to create a moderately complicated 3D object. Stability AI is proud to announce a private preview for Stable 3D. This automatic process generates concept-quality, textured 3D models. It eliminates much of the complexity and allows non-experts to create a draft-quality 3D design in minutes by selecting an illustration or image, or by writing a text prompt. Stable 3D objects are delivered as ".obj" files, which can be edited and improved with 3D tools such as Blender and Maya or imported into a game engine like Unreal Engine 5 and Unity.

Recent breakthroughs in text to image synthesis were driven by diffusion models that have been trained on billions and billions of image/text pairs. To adapt this approach to 3D, large datasets of labeled 3D asset and efficient architectures for denoising 3D data would be required. In this work, these limitations are circumvented by using a 2D text to image diffusion model that has been pre-trained. We introduce a loss that is based on probability densities distillation, which allows a 2D diffusion to be used as a prior in the optimization of a parameterized image generator. We optimize a randomly initialized 3D model, a Neural Radiance field, or NeRF, via gradient descent using this loss. This allows us to achieve low losses in 2D renderings of the model from random angles. The 3D model can be viewed at any angle and lit by any illumination. It can also be composited into any 3D environment.