Main comparison summary preserved directly in static HTML.
Two approaches to learning game simulators: IRIS uses discrete tokenization with a GPT-like transformer, while DIAMOND leverages diffusion models for higher visual fidelity.
Primary editorial conclusion preserved for non-JS crawlers and readers.
DIAMOND produces visually superior game simulations thanks to diffusion, but at the cost of slower generation. IRIS pioneered the transformer-based game simulation approach and remains faster for real-time applications. DIAMOND represents the next evolution toward pixel-perfect learned simulators.
Extractable difference list generated from the comparison table.
Static decision guidance for no-JS readers.
Choose IRIS when its capabilities best match your research or deployment requirements.
Choose DIAMOND when its capabilities best match your research or deployment requirements.
DIAMOND produces visually superior game simulations thanks to diffusion, but at the cost of slower generation. IRIS pioneered the transformer-based game simulation approach and remains faster for real-time applications. DIAMOND represents the next evolution toward pixel-perfect learned simulators.
| Dimension | IRIS | DIAMOND |
|---|---|---|
| Generation Method | Autoregressive discrete tokens | Diffusion-based continuous generation |
| Visual Quality | Good but tokenization artifacts | Superior (near pixel-perfect) |
| Architecture | VQ-VAE + Transformer | Diffusion model |
| Agent Training | 100K steps Atari | Atari + retro games |
| Speed | Fast autoregressive sampling | Slower iterative denoising |
| Year | 2023 | 2024 |
High-level scoring context for the models referenced in this comparison.
| Model | Category | Index v1.1 | Confidence |
|---|---|---|---|
| IRIS | Model-Based RL | 65/100 | medium |
| DIAMOND | Model-Based RL | 64/100 | medium |
| GameNGen | Generative World Model | 52/100 | medium |
| OASIS | Generative World Model | 66/100 | medium |
FAQ answers rendered directly into static HTML for extractable responses.
DIAMOND. Its diffusion-based approach avoids the discrete tokenization artifacts that IRIS sometimes produces, resulting in smoother, more realistic frames.
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 Bernard Grenat.
This comparison page publishes a direct answer, explicit trade-offs, and source-backed evidence that can be validated against primary materials.
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: 2026-06-21.
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 papers and official sources for the models discussed on this comparison page.