TIME Best Inventions 2025
First Real-Time Interactive World Model

Genie 3: Generate Interactive 3D Worlds from Text

Google DeepMind's breakthrough foundation world model – The first real-time interactive general-purpose world model. Creating dynamic 3D environments at 720p resolution, 24fps with world memory up to 1 minute. Built on Veo 3's physics understanding and self-supervised learning. A crucial stepping stone toward AGI.

Read Official Blog

Featured In

TechCrunchEngadgetThe VergeBGRAnalytics India

What is Genie 3?

Genie 3 is the first real-time interactive general-purpose world model developed by Google DeepMind. Released on August 5, 2025, it transforms text prompts into fully interactive, consistent 3D environments that you can navigate in real time at 720p resolution and 24fps.

Building on Genie 2 and DeepMind's video generation model Veo 3, Genie 3 uses self-supervised learning to teach itself physics, rather than relying on hard-coded physics engines. A key innovation is world memory – environments retain changes you make, with visual memory extending up to one minute for physically coherent long-horizon generation.

"Genie 3 is the first real-time interactive general-purpose world model. World models are key on the path to AGI, specifically for embodied agents, where simulating real world scenarios is particularly challenging."

- Shlomi Fruchter, Research Director at Google DeepMind

See Genie 3 in Action

Real-time recordings from Google DeepMind showing Genie 3 generating interactive worlds from text prompts

Click anywhere to enable autoplay

Prompt: First person perspective navigating difficult terr...

Click anywhere to enable autoplay

Prompt: Jetski during the festival of lights

Click anywhere to enable autoplay

Prompt: Running by the shores of a glacial lake, exploring...

Click anywhere to enable autoplay

Prompt: An adorable, fluffy creature bounding across a vib...

Videos courtesy of Google DeepMind

How Genie 3 Works

Understanding the technical innovations behind Genie 3

Auto-Regressive Generation

Generates one frame at a time based on user input, managing growing trajectories while processing new inputs multiple times per second for real-time responsiveness.

World Memory

Environments retain changes you introduce. Return to an area and find it exactly as you left it. Visual memory extends up to one minute for consistent generation.

Self-Supervised Physics

Unlike hard-coded physics engines, Genie 3 learns how physics works through self-supervised learning, discovering patterns from unlabeled data.

Technical Specifications

Pushing the boundaries of AI world modeling technology

Resolution
720p HD
Frame Rate
24 FPS
Duration
Multiple Minutes
Model Type
Auto-regressive
Memory
Up to 1 minute
Improvement
2x vs Genie 2

Genie 3 vs Genie 2

See how Genie 3 advances beyond its predecessor

FeatureGenie 2Genie 3
Resolution360p720p
Duration10-20 secondsMultiple minutes
Frame RateVariable24 FPS
Promptable EventsLimitedFull Support
Memory ConsistencyBasicUp to 1 minute

Key Features & Capabilities of Genie 3

Experience the cutting-edge capabilities that make Genie 3 a game-changer in AI world modeling

Real-time Generation

Generate interactive worlds at 24 frames per second with instant response to text prompts

World Consistency

Maintain environmental coherence for several minutes with auto-regressive frame generation

720p Resolution

High-quality visual output at 720p resolution for detailed and immersive environments

Physics Simulation

Accurately model physical properties and natural laws within generated environments

Promptable Events

Dynamically modify environments with text prompts to create custom world events

Responsible AI

Developed with safety and ethics in mind, featuring controlled access and responsible deployment

Frequently Asked Questions

Everything you need to know about Genie 3

When will Genie 3 be publicly available?

Genie 3 was announced on August 5, 2025 and is currently available as a limited research preview to select academics and creators. Google DeepMind plans to expand access gradually, but no public release date has been announced yet.

What is world memory in Genie 3?

World memory is a key innovation in Genie 3. Generated environments retain changes introduced by the user – if you alter an object or leave a mark, returning to that area shows the environment unchanged since your last interaction. Visual memory extends up to one minute.

What are the current limitations of Genie 3?

Current limitations include: restricted action space for direct agent control, challenges modeling complex multi-agent interactions, incomplete geographic accuracy for real-world locations, text rendering quality issues, and interaction duration capped at several minutes. Physics inaccuracies and occasional visual hallucinations may also occur.

How does Genie 3 relate to AGI?

DeepMind believes world models like Genie 3 are crucial stepping stones toward AGI. They enable training AI agents in unlimited simulation environments, forcing them to learn from experience similar to how humans learn. Genie 3 has been tested with SIMA agents executing complex multi-step goals.

What makes Genie 3 different from video generators like Veo 3?

Unlike Veo 3 and other AI video generators that create pre-determined videos, Genie 3 is a live simulator allowing real-time interaction. It generates frames based on user input using auto-regressive synthesis, and crucially, it uses self-supervised learning to understand physics rather than hard-coded rules.

What types of environments can Genie 3 generate?

Genie 3 can generate a wide variety of interactive environments including: physical phenomena (water, lighting, environmental interactions), ecosystems with animal behaviors, fantastical and animated scenarios, historical location recreations, and complex terrain navigation scenarios.

What are promptable events in Genie 3?

Promptable events allow you to dynamically modify generated environments through text prompts. You can change weather conditions, introduce new objects, place characters, and create "what-if" counterfactual scenarios – all in real-time while exploring the generated world.

Applications of Genie 3

Unlock new possibilities across multiple domains with Genie 3's world modeling capabilities

Agent Training & Simulation

Create diverse training environments for AI agents and autonomous systems to learn and adapt in controlled scenarios

Robotics Development

Train robots and autonomous systems in simulated environments before real-world deployment

Educational Environments

Generate interactive educational scenarios for immersive learning experiences across various subjects

Creative Media Generation

Amplify human creativity by generating animated and fictional scenarios for entertainment and media

Be Part of the AI Revolution

Limited spots available for academic researchers and creative professionals. Join the waitlist to get early access to Genie 3's world-building capabilities.

Read Research Paper
No credit card required
Join 500+ researchers