The Emergence of Reproducibility and Consistency in Diffusion Models

arXiv:2310.05264v2 Announce Type: replace
Abstract: In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs. We confirm this phenomenon through comprehensive experiments, implying that different diffusion models consistently reach the same data distribution and scoring function regardless of diffusion model frameworks, model architectures, or training procedures. More strikingly, our further investigation implies …

abstract arxiv consistent cs.cv cs.lg diffusion diffusion models emergence noise reproducibility through type work