AI can now generate an entire 3D world in about a second Viggle just introduced JST-2, a physics-native foundation model that creates 3D environments, rigged characters, and motion using a single model You can explore the generated scene from different angles without regenerating it And the best part? Each scene costs less than $0.01 in compute costs
A snowy 3D village scene with cloaked characters is generated from one input image using JST-2.
- 21 likes
- 1 reposts
- 3 replies
This video is Amira Zairi’s work, shown from their public post. See it on Threads.
