Full and standing for Pixar founder and Odyssey board member Ed Catmull at ACM SIGGRAPH in Vancouver. Incredible. #siggraph2025

We’re on a path to video of any kind being imagined by a model in real-time. Because it’s real-time generated, each video becomes fully interactive & personalized. Type or speak into the model, and the video will respond in real-time. A revolutionary form of media is emerging!

come play in the Odyssey latent space

Just wait until you see what we’ve been cooking at Odyssey 😮‍💨

Odyssey 2 drops this Monday 🔥

At 10AM PT tomorrow, we launch Odyssey-2! It's a different exploration than our previous models. There's no WASD control. But it feels like something totally new, and like AI video for the rest of us. Instant, interactive, fun. Proud of the team & really hope you enjoy it 🥹

10AM PT tomorrow: Odyssey-2 launches! GPUs scaling up as we speak.

Introducing Odyssey-2: instant, interactive AI video! This is a general-purpose model that instantly imagines 20FPS video you can interact with in open-ended ways. It feels like true sci-fi. Type a few words, and AI instantly imagines a video that feels alive.

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.

OK it turns out you all really want to try Odyssey-2. Apologies if you can't get in right now. We're bringing online more GPUs!

Tell me this isn’t magic.

Some recent coverage of our work at Odyssey on BBC news. I've been a big fan of the BBC's tech and science coverage for years so loved to see this. linkedin.com/feed/update/ur…

A deepdive into interactive video and world models

Odyssey-2 now streams 16:9 video if you're on a big screen, and shows an awesome advantage of interactive video models. Unlike pre-recorded video, real-time generated video intelligently adapts to the screen, viewer, and input device. Really sci-fi when you think about it!

There is something relaxing about watching an infinite stream of imagined world drift by Odyssey experience.odyssey.ml/VTZRAiVUuL

Language models predict the next token. Interactive video models predict the next video frame. We're in the 2022-era of these models, but video feeling sentient is imminent, along with an explosion of applications.

On the back of an insane Odyssey launch, we're growing the team on all fronts, and fast. If you're in product, research, research engineering, or infra, and are passionate about pioneering interactive video models with an exceptional team, please DM me ASAP. I really can't