Odyssey

@odysseyml • 33,787 subscribers

We’re an AI lab pioneering world models—AI to understand and simulate the world.

Shorts

19,638 views

219,224 views

198,613 views

124,475 views

112,738 views

89,898 views

64,928 views

19,000 views

34,719 views

12,754 views

25,633 views

24,838 views

71,804 views

17,109 views

15,522 views

17,246 views

31,648 views

11,981 views

22,189 views

31,483 views

Videos

sweetdream.ai

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Private Show

Join now for exclusive access

Free preview available • Premium content

2,183,089 views • 2 months ago

478,428 views • 1 month ago

911,043 views • 2 months ago

817,988 views • 8 months ago

785,691 views • 8 months ago

704,677 views • 1 year ago

285,081 views • 7 months ago

166,093 views • 5 months ago

63,845 views • 2 months ago

207,705 views • 1 year ago

105,325 views • 8 months ago

100,710 views • 1 year ago

47,486 views • 6 months ago

40,935 views • 5 months ago

43,083 views • 7 months ago

75,278 views • 1 year ago

35,029 views • 7 months ago

32,420 views • 7 months ago

41,576 views • 11 months ago

25,871 views • 7 months ago

Live Cam

Odyssey

Shorts

Still connecting the dots.

Calm, even under pressure.

Wide enough to breathe.

Still enough to feel.

Could leave anytime, still here.

Time isn’t always meant to move.

Stayed a little longer.

Still deciding where to go first.

A reminder to slow down.

Back in a minute.

Nothing special, still the one that stays.

Feels calm, but it’s already moving.

It’s time for a generative model that can imagine something entirely new in entertainment.

Just another day out here.

Stayed here longer than planned again.

All of this, and still somewhere else.

Some views change how everything feels.

Could go there, just staying here.

This moment carries enough.

And like most things with AI, interactive video will rapidly get more realistic and compelling from here. Our next-gen model is already on the way.

Videos

Watch Anya Live

It’s time to go beyond language models. Introducing Odyssey-2 Max, our most powerful world model yet. It materially advances the SOTA in physical accuracy. This is a big step toward models that simulate and interact with the world in real time. A new intelligence entirely!

We’ve raised a $310M Series B to accelerate world models! We believe AI that can understand and simulate the world will be one of the most important technologies of our time. We're excited to partner with Natural Capital, Amazon, GV, AMD, IQT, and others to bring this to life.

Introducing Agora-1, a multi-agent world model. Multiple participants—human or AI—can now interact inside the same world simulation, all in real-time. Try our playable research preview today, with Agora-1 simulating a multiplayer GoldenEye deathmatch!

Play god with Odyssey-2.

Odyssey-2 is live! It’s instant, interactive AI video. You type a few words, hit “stream”, and video you can interact with is instantly imagined by AI. It's so fun, and feels like magic.

Introducing AI video you can watch and interact with, in real-time! Powering this is a new world model that imagines and streams video frames every 40ms(!). No game engine in sight. We call it interactive video, and it's free for anyone to try right now (GPUs permitting)!

Say hi to Odyssey-2 Pro—our most intelligent, interactive, and general-purpose world model yet. Every pixel is generated in real-time, and frame-by-frame the model simulates the world forward. Today for minutes, soon for hours. Available to developers and our API very soon.

Introducing Odyssey-2 Pro—a frontier world model that generates long-running, interactive simulations in 720p! We're also launching the first world model API, to enable devs to build magical apps. We're now in the GPT-2 era of world models. Let the explosion of apps commence!

Introducing PROWL! We’ve built RL agents that explore game environments, tasked with discovering failures in world models across physics, visuals, and actions. Those failures then become training data in an automated loop that advances world model performance.

Today we’re excited to share a peek at our next-gen model. Hope you like it 🥹 Imagine a video model you can play like a game, all in real-time. That’s what we’re building. We call it interactive video, and there's no game engine in sight, just a model’s imagination.

Odyssey-2 generates video instantly. Not quick. Not fast. Instant! Click "start streaming" and AI-imagined video appears on your screen in less than a second. All for free.

There was a time when films and games felt like pure magic. New technology made it possible. The possibilities felt endless. Then the magic faded. Let’s bring that magic back—with AI. Coming soon from Odyssey.

This wasn’t on any map.

We’re giving away 1,000,000 simulations of reality, powered by our newest world model, Odyssey-2 Pro. Grab an API key, call /simulate, and get back a beautiful MP4. All free. The GPT-2 era rapidly explored language models. Now it’s time we explore world models together.

The dawn of pixel intelligence. Odyssey-2 is a glimpse of video that feels sentient. You type and intelligent pixels react instantly. Soon video will talk to you, play music with you, teach you, help you learn new languages, improve your health, and much more. Total sci-fi 🫶

Today is a big day at Odyssey. We're sharing Explorer, our first generative world model. We think world models are the next frontier for AI, enabling wonderful new things. To help shape this, Ed Catmull, the iconic founder of Pixar, is joining our board and investing.

Meet Odyssey-2. It’s not like any other AI video model you’ve used before. Type anything and instantly watch a personalized stream of beautiful AI video. No more waiting minutes for 5-10 second clips, and you can interact with the video in real-time.

It’s easy to watch this video and see a pre-recorded clip, but what you’re really watching is a frame-by-frame, interactive simulation of the world. Odyssey-2 Pro—a general-purpose world model—is prompted and then rolls out a minutes-long, open-ended simulation.

A machine dreaming video, as you play ✨

The next frontier after language models is world models, and learning to predict the next state of a world. Hear from our researchers how these models really work at a low-level and the mountain we're climbing. A general-purpose world simulator (AKA sci-fi) is now in sight.