Viggle AI releases 3D world foundation model JST-2 and opens API access
What happened
Viggle AI announced the release of JST-2, a 3D world foundation model, and said it is live in its API, where developers can access it through its developer page. The company says JST-2 is built in 3D space rather than pixel or video space, can generate 3D scenes within seconds and supports real-time expansion, and can use the same architecture to generate 3D characters with built-in motion. The company calls JST-2 the world's first "full-stack physics-native" world foundation model. These performance claims and the "first" claim come from Viggle AI's own announcement and have not been independently verified. Three days after launch, Viggle AI said JST-2 can take text, image, or video input and output 3D characters, motion, and scenes, and showed on X works users have since made with it.
AI-written from the coverage · updated 2026-10-23
Developments
3 developments
- Oct 23 06:41 · 1 reportViggle showcases user creations made with JST-2Viggle AI: Viggle AI's JST-2 world foundation model shows user creations three days after launch
- Oct 21 02:29 · 1 reportJST-2 model goes live on Viggle APIViggle AI: Viggle AI releases JST-2, unifying 3D character, motion and scene generation
- Oct 19 23:20 · 1 reportViggle AI releases JST-2 full-stack physics world foundation modelViggle AI: Viggle AI releases JST-2, a physics-native world foundation model
Coverage timeline
Follow the coverage to see the story from different sides.
- Viggle AIViggle AI's JST-2 world foundation model shows user creations three days after launch
Viggle AI says its JST-2 world foundation model has been live for three days and accepts text, image, or video input to output 3D characters, motion, and scenes. The original post also features a thread of works users have made with JST-2 since launch.
- Viggle AIPickViggle AI releases JST-2, unifying 3D character, motion and scene generation
Viggle AI has released JST-2, a world foundation model that is now live in its API. Developers can get started at https://viggle.ai/developers. The company says JST-2 builds its full model stack in 3D space rather than pixel or video space, generating 3D scenes within seconds and expanding them in real time. The same general architecture can also generate 3D characters with built-in motion.
- Viggle AIPickViggle AI releases JST-2, a physics-native world foundation model
Viggle AI has released JST-2, a full-stack physics-native world foundation model. According to the announcement, its entire model stack is built in 3D rather than in pixel or video space. The company says it can generate 3D scenes within seconds, scale them in real time, and create characters with built-in motion using the same general architecture.