Collected sources and patterns will appear here. Add from search or the patterns library.
TextPrompt -> Mesh
Convert a text prompt to a 3D mesh by chaining a text-to-image generator with an image-conditioned multi-view 3D reconstruction pipeline.
Problem it solves
Direct text-to-3D generation suffers from poor text alignment and lack of fine details compared to mature 2D text-to-image models.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.