News for hackers. Stuff that matters.

A comment on GALA3D: Towards Text-to-3D Complex Scene Generation. Parent comment

Re:GALA3D: Towards Text-to-3D Complex Scene Generation by yorwba on Tuesday February 20, 2024 @03:37AM (#39439167)
When you want a very specific shape, text is probably not the right input modality. See also image generation, where to get very specific outputs, you're better off defining the large-scale structure spatially with a controlnet and only using text for the visual style and decorative details that do not need to be precisely controlled.

What shapes would you ask a text-to-3D model to create for you?

[ Parent | on HN ]
Re:GALA3D: Towards Text-to-3D Complex Scene Generation by alpaca128 on Tuesday February 20, 2024 @05:27AM (#39439649)
That makes me wonder whether an LLM for code generation could actually work for OpenSCAD-style designs as well, especially as it has a quite small set of functions. The only thing that makes me doubtful is that the coordinates have to correctly map to 3D space.
[ Parent | on HN ]