Ultrafast is now live for MiniMax H3 in Viggle ⚡
It makes a 10-second 768p video in just 10 seconds, about 1/5 of the time Standard H3 takes. That's the actual user experience on Viggle, from click to video.
You no longer have to wait 3 mins for a 10-second clip.
Try it at viggle.ai/meme/app/video-gen
Same ride, new universe.
Restyle anything with Viggle Remake 👇
Introducing Viggle Remake.
The most powerful video transformation agent. And we’re releasing the weights today.
→ recast every character in a scene, and they stay consistent across cuts
→ swap objects, change the background, restyle or add VFX
→ up to 2 minutes
→ keep chatting to fix any shot until it’s right
From $0.96 per 10 seconds at 720p, less than half of what Higgsfield Genjutsu charges.
Try it now: viggle.ai/meme/app/home?ui=v…
Open weights: huggingface.co/Viggle/Viggle…
Introducing Viggle Remake.
The most powerful video transformation agent. And we’re releasing the weights today.
→ recast every character in a scene, and they stay consistent across cuts
→ swap objects, change the background, restyle or add VFX
→ up to 2 minutes
→ keep chatting to fix any shot until it’s right
From $0.96 per 10 seconds at 720p, less than half of what Higgsfield Genjutsu charges.
Try it now: viggle.ai/meme/app/home?ui=v…
Open weights: huggingface.co/Viggle/Viggle…
JST-2 reconstructs complete 3D environments from sparse real-world observations and expands them from new viewpoints. This opens a path to building robot simulation environments from real places.
Generated scenes render locally, without running the model for every frame.
Generate full-body 3D motion from text or video. From video, JST-2 reconstructs visible movement and infers how unseen body parts move.
JST-2 leads state-of-the-art models on text-to-motion and video-to-motion in blind human evaluations.
Full benchmark: viggle.ai/research/jst2-moti…
From one image to a 3D character with motion built in. Its dynamics are learned from data, without separate rigging and skinning steps.
JST-2 outperforms state-of-the-art models in blind human evaluations of character generation and animation readiness.
Full benchmark: viggle.ai/research/jst2-char…
JST models the world as persistent atoms in 3D space. Each Physics-Native Token has an explicit xyz position and learned vectors for attributes and dynamics.
We spent four years building the full physics-native stack around this representation: tokenization, architecture, the data synthesis engine, pre-training, and post-training.
Today we are releasing JST-2, the world's first full-stack physics-native world foundation model.
Many world models learn in pixel/video space. We went back to first principles and built the entire model stack in 3D.
Generate a 3D scene in seconds and expand it in real time. Create characters with motion built in, all through one general architecture.
AI filmmakers & video creators: want to try our new model Viggle Animate 2 before everyone else?
This weekend only, we‘re opening a limited number of exclusive private beta spots.
Try it, tell us what you think, and share what you make on X.
Reply here or DM us for early access!


