Viggle Games (@ViggleGames) header
Viggle Games (@ViggleGames) profile picture

We add personalized avatars to your game & help gameplay go viral. Try our games here: https://teapaw.org/t.co/nyWroladc1

Joined July 2026
2024: Viggle makes MrBeast dance with AI 2026: MrBeast actually does the dance IRL now: we’re adding it to Talking Viggy the lore continues. #gamedev #screenshotsaturday
2
6
1
44
5,178
Viggle Games retweeted
World Labs released Atlas today. We shipped JST-2 on Oct 19. Both let you expand a 3D world one view at a time. Here they are side by side. Left, JST-2: every expand is native 3D, generated in about a second. Walk through a door and the next room is there. Right, Atlas: every render is a 2D frame, shown as a point cloud. Turning it into 3D splats is a separate step: 5,000 credits and about 15 minutes. JST is physics-native. It models persistent atoms in 3D space, so 3D is the output, not a post-process. World Labs has raised over $1B. Viggle has raised under $30M. Now imagine this architecture at scale. Try it free: viggle.ai/jst2
41
52
4
360
67,794
Viggle Games retweeted
Rebuilt Higgsfield's "Miracle" demo edit by edit with Viggle-remake No private beta, run it locally
7
12
1
134
47,060
Viggle Games retweeted
A casually trained image model for mulit character swap. Still not gpt-image level, but should be top as open-weight model.
2
2
12
1,021
this is perfect for making game trailers 🔥
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…
2
69
Hunt down legendary outlaws and collect rich bounties. - Clear towns for famous outlaws - Detailed limb targeting physics - Weapon customization The game is called "High Noon Showdown"
95
Viggle Games retweeted
One model that generates 3D characters, motion, and scenes. JST-2 is now live in our API. Start building today: viggle.ai/developers
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.
10
7
2
52
7,668
I just made an incredibly addictive tower defense game in just a few prompts using GPT6-Astra... The barriers for entry on gamedev are just getting lower every day👀 Try it here: viggle.ai/games/keep-knight/
4
216
Viggle Games retweeted
I had way too much fun building this Lord of the Rings-inspired Rivendell game with ChatGPT Astra + our JST-2 world model. Generating the scenes made it so much easier to build, and so much prettier. Come explore the valley, the Unseen World and the Council! kdanieldann.github.io/rivend…
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.
3
1
8
557
Viggle Games retweeted
So proud of the new model. All JST-2 capabilities - character, motion, scene, are free to experience in PINOC. What will you build with JST-2 today?
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.
1
11
471
From a floating island to a sea of clouds... take flight in Dream Beyond the Sky. ☁️ Created by one member of our team in just a few minutes using JST-2 environments, characters, and animations. Play it here: hylu-dev.github.io/dream-bey…
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.
7
363
Viggle Games retweeted
Viggle's JST-2 takes one image and gives you an animation-ready character (a Gaussian splat) your agent can call, no rigging or skinning step. if you're vibe-coding a game, that's characters sorted.
🤝 Paid partnership
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.
6
9
95
21,843
Viggle Games retweeted
In the robotics demo for Viggle's JST-2, the model generates the kitchen, the people and what they do, and the robot hands a box to a kid. a new scene takes seconds and under a cent of compute, so you can keep swapping the room and the people until there's enough to train on.
🤝 Paid partnership
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.
14
53
120
28,822
Viggle Games retweeted
Viggle's JST-2 gallery is up, open the village scene. You can fly the lanes and back and the houses stay put, it's all built in 3D. Most world models I've covered this year predict frames and drift. Learned physics comes in JST-3, Viggle says. This one's free to try today.
🤝 Paid partnership
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.
4
4
175
17,827
Viggle Games retweeted
Woww.. Viggle AI just shipped JST-2, and it builds the whole world in 3D instead of pixels. - a 3D scene in about one second of inference, under $0.01 - characters from one image with motion built in - full-body motion from text or video generate it once. walk it forever
🤝 Paid partnership
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.
28
41
3
412
38,347
Viggle Games retweeted
Dream Beyond the Sky 梦越苍穹. Awaken on a floating island and fly through a sea of clouds. An interactive short made entirely using JST-2 environments, characters, and motions. Play: hylu-dev.github.io/dream-bey…
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.
2
6
1
14
1,330
Viggle Games retweeted
Four years ago, we started building a world model in 3D from the ground up. Today, JST-2 generates scenes in seconds and expands them in real time. The same architecture also generates characters and motion. So proud of our team. Can't wait to see what you build.
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.
21
6
65
4,601
Viggle Games retweeted
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.
304
354
362
2,301
1,747,636
I made a skateboarding game with GPT 6 in less than an hour. Play it here: viggle.ai/games/app
5
204
I made a racing game in less than an hour with GPT-Astra. gamedev might be cooked 😂 Try it here: viggle.ai/games/battle-racer…
1
5
323