InfiniteDiffusion: Bridging Learned Fidelity and Procedural Utility for Open-World Terrain Generation

TL;DR

InfiniteDiffusion introduces a training-free method to combine the high fidelity of diffusion models with the infinite, seamless, and real-time properties of procedural noise for open-world terrain generation.

Contribution

It presents a novel unbounded diffusion sampling algorithm and a terrain generation framework that outperforms previous methods in speed and realism, enabling interactive infinite virtual worlds.

Findings

Outperforms orbital velocity by 9 times on a consumer GPU.

Enables realistic terrain generation at interactive rates.

Integrates hierarchical diffusion models with a compact encoding for large-scale terrain.

Abstract

For decades, procedural worlds have been built on procedural noise functions such as Perlin noise, which are fast and infinite, yet fundamentally limited in realism and large-scale coherence. Conversely, diffusion models offer unprecedented fidelity but remain generally confined to bounded canvases. We introduce InfiniteDiffusion, a training-free algorithm that reformulates diffusion sampling for lazy and unbounded generation, bridging the fidelity of diffusion models with the properties that made procedural noise indispensable: seamless infinite extent, seed-consistency, and constant-time random access. To demonstrate the utility of this approach, we present Terrain Diffusion, a framework for learned procedural terrain generation with a procedural noise-like interface. Our framework outpaces orbital velocity by 9 times on a consumer GPU, enabling realistic terrain generation at interactive rates. We integrate a hierarchical stack of diffusion models to couple planetary context with local detail, a compact Laplacian encoding to stabilize outputs across Earth-scale dynamic ranges, and an open-source infinite-tensor framework for constant-memory manipulation of unbounded tensors. Together, these components position diffusion models as a practical foundation for the next generation of infinite virtual worlds.