Odyssey's banner
Odyssey's profile picture

Odyssey

@odysseyml • 32,228 subscribers

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

Shorts

Calm, even under pressure.

Calm, even under pressure.

218,136 views

Wide enough to breathe.

Wide enough to breathe.

196,299 views

Could leave anytime, still here.

Could leave anytime, still here.

111,160 views

Time isn’t always meant to move.

Time isn’t always meant to move.

88,859 views

Still enough to feel.

Still enough to feel.

121,780 views

Stayed a little longer.

Stayed a little longer.

63,603 views

Nothing special, still the one that stays.

Nothing special, still the one that stays.

25,034 views

Stayed here longer than planned again.

Stayed here longer than planned again.

13,254 views

Just another day out here.

Just another day out here.

16,381 views

A reminder to slow down.

A reminder to slow down.

33,070 views

Feels calm, but it’s already moving.

Feels calm, but it’s already moving.

22,159 views

All of this, and still somewhere else.

All of this, and still somewhere else.

16,326 views

Could go there, just staying here.

Could go there, just staying here.

11,253 views

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

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

71,804 views

Some views change how everything feels.

Some views change how everything feels.

31,648 views

Not stopping. Just resting here.

Not stopping. Just resting here.

12,132 views

This moment carries enough.

This moment carries enough.

22,189 views

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.

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.

31,053 views

Step by step, the structure fills the frame.

Step by step, the structure fills the frame.

11,986 views

Distance turns into structure.

Distance turns into structure.

11,303 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

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

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

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!
1:39
odysseyml's profile picture

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!

Odyssey

897,489 views • 16 days ago

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!
1:08
odysseyml's profile picture

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!

Odyssey

2,178,790 views • 1 month ago

Play god with Odyssey-2.
0:27
odysseyml's profile picture

Play god with Odyssey-2.

Odyssey

817,988 views • 7 months ago

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.
0:45
odysseyml's profile picture

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.

Odyssey

785,654 views • 7 months ago

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.
0:43
odysseyml's profile picture

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.

Odyssey

60,301 views • 22 days ago

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)!
0:32
odysseyml's profile picture

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)!

Odyssey

704,337 views • 1 year ago

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.
0:40
odysseyml's profile picture

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.

Odyssey

284,824 views • 5 months ago

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!
0:52
odysseyml's profile picture

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!

Odyssey

165,653 views • 4 months ago

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.
0:30
odysseyml's profile picture

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

207,684 views • 10 months ago

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.
0:22
odysseyml's profile picture

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.

Odyssey

105,325 views • 7 months ago

This wasn’t on any map.
0:22
odysseyml's profile picture

This wasn’t on any map.

Odyssey

47,486 views • 4 months ago

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.
0:27
odysseyml's profile picture

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.

Odyssey

40,717 views • 4 months ago

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.
1:01
odysseyml's profile picture

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.

Odyssey

100,710 views • 1 year ago

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 🫶
1:24
odysseyml's profile picture

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 🫶

Odyssey

43,083 views • 6 months ago

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.
0:27
odysseyml's profile picture

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.

Odyssey

35,029 views • 6 months ago

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.
1:41
odysseyml's profile picture

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.

Odyssey

32,291 views • 5 months ago

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.
0:57
odysseyml's profile picture

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.

Odyssey

75,255 views • 1 year ago

A machine dreaming video, as you play ✨
0:29
odysseyml's profile picture

A machine dreaming video, as you play ✨

Odyssey

41,576 views • 10 months ago

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.
17:45
odysseyml's profile picture

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.

Odyssey

25,822 views • 6 months ago

No more content to load