Meta 3D Gen (3DGen) is the company’s all-new AI tool for text-to-3D asset generation. It’s capable of 3D asset creation with high prompt fidelity and high-quality 3D textures in under a minute, while supporting physically-based rendering (PBR), necessary for 3D asset relighting in real-world applications.
3DGen also supports generative re-texturing of previously generated (or artist-created) 3D shapes using additional textual inputs provided by the user. This AI tool integrates key technical components from Meta 3D AssetGen and Meta 3D TextureGen that were developed exclusively for text-to-3D as well as text-to-texture generation, respectively. Combining the strengths of both allows 3DGen to create 3D objects simultaneously in three ways: in view space, in volumetric space, and in UV (or texture) space.
No products found.
We compare 3DGen to numerous industry baselines, and show that it outperforms them in terms of prompt fidelity and visual quality for complex textual prompts, while being significantly faster,” said Meta.
