New: the Timeline is live. Track world model releases, papers, and benchmark updates in real time.
world-models.io
The Knowledge Hub for AI World Models

GameNGen

GameNGen is a neural game engine developed by Google Research that simulates the classic game DOOM interactively in real-time using a fine-tuned diffusion model.

robotics model-based-rl simulation embodied-ai

Key Attributes

Static HTML snapshot of the model record for crawlers and no-JS readers.

AttributeValue
ModelGameNGen
Lab / OrganizationGoogle
CategoryGenerative World Model
SubtypeNeural Game Engine
World Model TypeDiffusion-based neural game engine
Primary DomainReal-time game simulation
ArchitectureFine-tuned Stable Diffusion 1.4 with action and frame history conditioning
ModalityActions + Frame History → Next Frame
Training MethodTwo-phase: (1) RL agent generates gameplay data, (2) Diffusion model fine-tuned on gameplay sequences
Statusactive
Year2024
Performance Index52/100 (medium confidence, v1.1)

About GameNGen

Main editorial body preserved directly in static HTML.

GameNGen demonstrates that a neural network can fully replace a traditional game engine. It simulates the classic game DOOM in real-time at over 20 FPS with visual quality nearly indistinguishable from the original game. The system uses a fine-tuned Stable Diffusion model conditioned on past frames and player actions, trained via a two-phase approach: first an RL agent generates gameplay data, then the diffusion model learns to simulate the game.

GameNGen is a diffusion-based neural game engine developed by Google Research in 2024 for real-time game simulation.

Editorial Snapshot

Short extractable facts for answer engines and no-JS readers.

SignalValue
DefinitionGameNGen is a diffusion-based neural game engine developed by Google Research in 2024 for real-time game simulation.
Short DescriptionThe first neural model to simulate a complex game (DOOM) in real-time at high quality, making the game engine itself a neural network.
Benchmark Rows1
FAQ Entries1
Related Models3
Related Guides0
Related Research Topics0
Last Updated2026-03-11

Notable Features

Key capabilities associated with this model.

  • Real-time DOOM simulation at 20+ FPS
  • Nearly indistinguishable from original game
  • No traditional game engine needed
  • Based on Stable Diffusion architecture

Use Cases

Representative applications attached to this model record.

Neural game enginesGame simulation researchWorld model demonstrationsInteractive AI systems

Strengths and Limitations

Balanced assessment surfaced in static HTML.

Strengths

  • Impressive visual fidelity
  • Real-time performance
  • Proof-of-concept for neural game engines
  • Playable and interactive

Limitations

  • Single game only
  • No long-term memory/consistency
  • Based on fine-tuning existing model
  • Not generalizable yet

Benchmarks

Published benchmark evidence attached to this model record.

BenchmarkMetricResultSource
DOOM SimulationLPIPS 0.072 LPIPS↓Near-original qualitySource

References and Citations

Primary references preserved in static HTML for citation extraction.

ReferenceLink
Valevski et al., 2024. Diffusion Models Are Real-Time Game Engines. arXiv:2408.14837Open source

Related Models

Nearby models linked from the current editorial record.

ModelCategoryWorld Model TypeIndex v1.1
OASISGenerative World ModelReal-time playable world model66/100
DIAMONDModel-Based RLDiffusion-based environment simulator64/100
Genie 2Generative World ModelGenerative environment model79/100

Direct Comparisons

Side-by-side comparisons already connected to this model.

ComparisonMatchupSummary
OASIS vs GameNGenOASIS (Decart) vs GameNGen (Google Research)OASIS and GameNGen both demonstrate neural networks functioning as real-time game engines, but they target different games and use different architectures. They represent the emerging frontier of neural game engines.
OASIS vs DIAMONDOASIS vs DIAMONDBoth use diffusion models as world models for interactive environments, but OASIS generates real-time playable Minecraft-like worlds while DIAMOND uses diffusion for model-based RL training in Atari.
Pandora vs OASISPandora vs OASISBoth generate interactive game-like worlds, but Pandora produces multi-domain video simulations with narrative control, while OASIS focuses on high-fidelity real-time open-world generation trained on Minecraft.
GameNGen vs DIAMONDGameNGen vs DIAMONDBoth simulate game environments in real-time, but with radically different approaches: GameNGen uses a fine-tuned diffusion model for photorealistic DOOM simulation, while DIAMOND uses a diffusion-based world model for Atari with reinforcement learning.
IRIS vs DIAMONDIRIS vs DIAMONDTwo approaches to learning game simulators: IRIS uses discrete tokenization with a GPT-like transformer, while DIAMOND leverages diffusion models for higher visual fidelity.

Frequently Asked Questions

FAQ answers rendered directly into static HTML for extractable responses.

Can GameNGen run other games besides DOOM?

Currently only DOOM. The approach could theoretically be applied to other games but would require retraining for each game.

Quick Answer

Short extractable summary preserved directly in static HTML.

  • GameNGen is a diffusion-based neural game engine developed by Google Research in 2024 for real-time game simulation.
  • Use this page when you need a fast read on how GameNGen fits into the generative world model landscape, then validate the details in the benchmarks, citations, and related pages.
  • A key strength surfaced in the editorial record is impressive visual fidelity.

Editorial Trust Signals

Editorial provenance and refresh policy preserved directly in static HTML.

Published by world-models.io editorial board.

Lead editor Tyler D. - Technical editor, methodology and benchmark analysis.

This model page synthesizes primary papers, official model pages, benchmark evidence, and related world-models.io context into a reference resource.

Each editorial page is assembled from primary sources, normalized into extractable summaries, checked for factual drift, and reviewed before publication or major refreshes. Last reviewed: 2026-03-11.

Pages are refreshed when a new paper, benchmark, release, architecture update, or stronger primary source materially changes the answer a reader or AI system should retrieve.

Each page links back to relevant primary sources and keeps a stable canonical URL so readers can verify claims, trace context, and reference the most up-to-date version. See the editorial policy.

Primary sources onlyLast reviewed date visibleMethodology documentedSource links included

External Sources

Primary model and lab sources embedded in static HTML.

References

  1. [1] Valevski et al., 2024. Diffusion Models Are Real-Time Game Engines. arXiv:2408.14837