AI engineering glossary · Generative media multimodal
What is text-to-3D generation?
Text-to-3D generation: Producing a 3-D asset from a text prompt, often by optimising a 3-D representation so that its renderings look plausible to a pretrained text-to-image diffusion model, or by generating multiple consistent views first.
Text-to-3D generation: an example
The prompt 'a carved wooden elephant' yields a mesh that can be imported into a game engine.
Related terms
More Generative media multimodal terms
- Text-to-image generation
- Text-to-speech
- Text-to-video generation
- Textual inversion
- Variational autoencoder
- Video generation
- Vision encoder
- Vision-language model
Where you learn it
Text-to-3D generation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.