Understand this story
Viggle AI announced that the JST-2 model is now available on its API, and that the model can generate 3D characters, motions, and scenes within a single architecture. Previously, on October 20, 2026, Viggle released JST-2, building the entire model stack in 3D space and representing the world with Physics-Native Tokens that carry xyz coordinates, attribute vectors, and dynamics vectors, rather than implicitly inferring physical laws from video pixels; the architecture is divided into three parts: the JST encoder, the JST generator, and the JST decoder, and a single forward inference generates a complete 3D scene in about 1 second at a cost of less than $0.01 (B200), and supports up to 64 input views as a spatial context window. Blind human preference tests published by Viggle show that for character generation it achieves a 58.4% win rate against Meshy 7.1 and a 73.2% win rate against Tripo H3.1, and for video-generated motion it achieves an 89.1% win rate against DeepMotion. Viggle AI previously described JST-2 as a "full-stack physics-native world foundation model" that can generate 3D scenes in seconds and extend them in real time. JST-2 is currently available externally through the API.
AI-generated from public reports
Latest development · Report
Viggle AI's JST-2 model is now available via APIDevelopments
2 confirmed developments
- Source:Viggle AI
- Source:Shao Meng
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 21
Viggle AI
Viggle AI's JST-2 model is now available via API
Viggle AI announced that the JST-2 model is now available on its API; the model can generate 3D characters, motion, and scenes under a single architecture. Viggle AI previously called JST-2 a "full-stack physics-native world foundation model," with the entire model stack built in 3D space, capable of generating 3D scenes in seconds and expanding them in real time.
Oct 20
Shao Meng
Viggle Releases JST-2, a 3D-Native World Model
Viggle has released JST-2, building its entire model stack in 3D space and representing the world with Physics-Native Tokens that carry xyz coordinates, attribute vectors, and dynamics vectors, rather than implicitly inferring physical laws from video pixels. The architecture consists of three parts: the JST encoder, JST generator, and JST decoder. A single forward inference generates a complete 3D scene in about 1 second, at a cost below $0.01 (B200), and supports up to 64 input views as a spatial context window. Blind human preference tests published by Viggle show that character generation wins 58.4% against Meshy 7.1 and 73.2% against Tripo H3.1, while video-generated motion wins 89.1% against DeepMotion. JST-3 plans to extend the learned dynamics to object interaction.