Genie 3: Real‑Time World Model by DeepMind
From a short text prompt, Genie 3 generates a navigable, interactive 3D world in real time (~24 fps) at 720p, with minutes‑long world consistency and promptable dynamic world events during play. This AI world modeling breakthrough enables unlimited virtual environments for training, gaming, and research.
- • Real-time interactivity (~24 fps)
- • 720p output
- • Minutes-scale consistency
- • Text-driven world events
Experience Genie 3's Capabilities
Watch real demonstrations of Genie 3 generating and navigating interactive worlds in real-time
Volcanic Terrain
"The video shows a first person perspective of someone navigating difficult terrain in the middle of a volcanic area. This is a real world video shot from the perspective of a wheeled robot that needs to traverse across a terrain. The vehicle has chunky offroad tires that crunch under the blackened rock. The camera is an egocentric camera mounted to the vehicle, and you can see the front tires just on the bottom of the camera along with the body of the robot. In the distance you can see smoke and lava flowing from the volcano. There are no other visible signs of life. There are lava pools that the agent is trying to avoid and random rock formations. The sky is a vivid blue."
Jetski Festival
"Jetski during the festival of lights"
Deep Sea Jellyfish
"Fast tracking real world video following a jellyfish swimming at high speed through the darkness of the deep sea between canyons covered in densely packed vent mussels with tiny white crabs crawling on them. Blurry hydrothermal vents in the distance spew thick, billowing plumes of vibrant blue, mineral-rich smoke from glowing rocky structures. Very dark, dim deep sea lighting, particles float in the cloudy ocean."
Helicopter Cliff
"A helicopter pilot carefully maneuvering over a coastal cliff with a small waterfall."
Rainbow Bridge Creature
"A vibrant 3D style, an adorable, fluffy creature bounding across a vibrant rainbow bridge in a fantastical landscape. The creature is small and compact, with fur that mimics the warm hues of a sunrise – oranges, yellows, and pinks blending seamlessly together. Its most striking feature is a pair of large, perked ears, shaped like those of a German Shepherd, adding a touch of playful contrast to its otherwise rounded form. As it runs on four short legs across the rainbow, its fur appears to ripple and flow, adding to its sense of dynamism and energy. The rainbow bridge arches gracefully through a whimsical landscape, perhaps filled with floating islands, glowing flora, and swirling clouds. The lighting is bright and cheerful, casting a warm glow on the creature and its surroundings. The overall impression is one of joy, wonder, and boundless energy, capturing the creature's playful spirit and the magical nature of the world it inhabits. This image evokes a sense of childlike whimsy and invites the viewer to imagine the adventures that await this charming creature in its fantastical realm."
Origami Lizard
"Being a lizard, origami style"
Alps Mountain
"A real world mountainous environment in the Alps. The landscape features steep, rocky cliffs and narrow gorges filled with loose scree and debris. The rock is predominantly grey and white, with patches of green vegetation clinging to the cliff faces. The top of the gorge opens up to a vista of dense evergreen forests and meadows. The overall theme is one of rugged, natural beauty and extreme terrain."
Venice by Vaporetto
"Venice by Vaporetto. The canals of Venice are recreated with painstaking detail. The water has realistic reflections and wakes. The buildings show crumbling plaster and centuries of weathering. The scene is populated with other gondolas, water taxis, and barges."
Victorian Portal
"A Victorian street with a grey house. The grey house has a portal ringed by magical sparks. The portal leads to a vast desert filled with dunes, and that desert is visible from the outside. The agent can walk into the portal and is teleported to the desert."
What Genie3 can do
1) Real‑time, playable worlds
Walk, drive, fly, and navigate while the model renders frames on the fly, maintaining continuity from what it previously showed.
2) Long‑horizon consistency & memory
Genie3 keeps track of what was behind you and restores it when you return, with minutes‑long consistency and roughly one minute of visual memory for out‑of‑view details.
3) Promptable world events
Change the world mid‑experience using text—e.g., "make it rain" or "spawn a helicopter"—to broaden what‑if scenarios and creative prototyping.
4) Rich physical phenomena & diverse styles
Examples show water, lighting, collisions, natural ecosystems, and stylized scenes—remaining coherent as you move.
How Genie3 works (high level)
Autoregressive world simulation
Each frame is generated considering your actions and the entire prior trajectory—core to keeping the world consistent when you revisit places later.
No explicit 3D mesh requirement
Unlike NeRFs or Gaussian Splatting, Genie3 learns to render and update the world directly, frame‑by‑frame, trading explicit geometry for richer dynamics and editability.
Genealogy: Genie 1 → Genie 2 → Genie 3
Progression from unlabeled video training and latent actions (Genie 1) to single‑image → playable worlds and longer memory (Genie 2), culminating in real‑time play with minutes‑scale consistency and text‑prompted events (Genie 3).
What's new vs. video generators
Genie 3
Interactive world simulation—not just clip generation. You can navigate inside a persistent scene and cause events that change the environment in real time.
Video Generators
Tools like text/image → video produce footage rather than a closed‑loop, user‑navigable world. Great for storytelling and content creation, not for live world interaction.