Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.

From first person real world scenes, to third person driving environments, Genie 2 generates worlds in 720p 📷. Given an image, Genie 2 simulates world dynamics, creating a consistent environment playable with keyboard and mouse inputs ⌨️.

To illustrate the potential of this for embodied agents, consider the world below, generated using Imagen 3. The SIMA team tested whether their latest agent could follow language instructions, such as going to the red or blue door 🚪.

🤯🤯🤯… And just like that, we have a path to unlimited environments for training and evaluating our embodied agents! We tried creating another world with three arches, and once again Genie 2 was able to simulate the world and SIMA solved the task ✅.

Genie 2 can also turbocharge environment design for humans, making it possible to step in and play from concept art 🎨, such as the beautiful work below from one of our rockstar designers.

Finally, this would not have been possible without the amazing diversity of incredible collaborative people at Google DeepMind 🫶🫶🫶. Shout out to the team that made this possible, from the Genie 2 team, the Generalist Agents team and SIMA. Exciting times ahead!!

All of these clips are suspiciously short. If this thing worked for more than 5 seconds, you'd have included a video of it working for more than 5 seconds.

I dare you to spin the camera 360 degrees

this sucks, thanks

lol show me one video of this thing doing a 360 spin without the world constantly changing all around you.

This is the dumbest fucking bullshit I've ever heard. Go bankrupt, you worthless hacks.