Re:Stable Fast 3D: Rapid 3D Asset Generation from Single Images
by latentsea on Thursday August 01, 2024 @11:51PM
(#41135955)
The movement decisions are also just text from the LLM and are heavily coupled with what's available in the scene. It's not some free autonomous agent. Nor was the movement decisions trained any special type of tokens other than just text.
This is as naive as calling an industrial robot 'just a calculator'.