Static HTML snapshot of the model record for crawlers and no-JS readers.
| Attribute | Value |
|---|---|
| Model | GameNGen |
| Lab / Organization | |
| Category | Generative World Model |
| Subtype | Neural Game Engine |
| World Model Type | Diffusion-based neural game engine |
| Primary Domain | Real-time game simulation |
| Architecture | Fine-tuned Stable Diffusion 1.4 with action and frame history conditioning |
| Modality | Actions + Frame History → Next Frame |
| Training Method | Two-phase: (1) RL agent generates gameplay data, (2) Diffusion model fine-tuned on gameplay sequences |
| Status | active |
| Year | 2024 |
| Performance Index | 52/100 (medium confidence, v1.1) |
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.
Short extractable facts for answer engines and no-JS readers.
| Signal | Value |
|---|---|
| Definition | GameNGen is a diffusion-based neural game engine developed by Google Research in 2024 for real-time game simulation. |
| Short Description | The first neural model to simulate a complex game (DOOM) in real-time at high quality, making the game engine itself a neural network. |
| Benchmark Rows | 1 |
| FAQ Entries | 1 |
| Related Models | 3 |
| Related Guides | 0 |
| Related Research Topics | 0 |
| Last Updated | 2026-03-11 |
Key capabilities associated with this model.
Representative applications attached to this model record.
Balanced assessment surfaced in static HTML.
Published benchmark evidence attached to this model record.
| Benchmark | Metric | Result | Source |
|---|---|---|---|
| DOOM Simulation | LPIPS 0.072 LPIPS↓ | Near-original quality | Source |
Primary references preserved in static HTML for citation extraction.
| Reference | Link |
|---|---|
| Valevski et al., 2024. Diffusion Models Are Real-Time Game Engines. arXiv:2408.14837 | Open source |
Nearby models linked from the current editorial record.
Side-by-side comparisons already connected to this model.
| Comparison | Matchup | Summary |
|---|---|---|
| OASIS vs GameNGen | OASIS (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 DIAMOND | OASIS vs DIAMOND | Both 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 OASIS | Pandora vs OASIS | Both 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 DIAMOND | GameNGen vs DIAMOND | Both 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 DIAMOND | IRIS vs DIAMOND | Two approaches to learning game simulators: IRIS uses discrete tokenization with a GPT-like transformer, while DIAMOND leverages diffusion models for higher visual fidelity. |
FAQ answers rendered directly into static HTML for extractable responses.
Currently only DOOM. The approach could theoretically be applied to other games but would require retraining for each game.
Short extractable summary preserved directly in static HTML.
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 model and lab sources embedded in static HTML.