Enhanced diffusion model guidance via multi-denoiser mixing

Abstract

Diffusion models are machine learning algorithms implemented as neural network-based denoisers that are uniquely trained to generate high-quality data from an input lower-quality data. However, for complex datasets, the samples generated by a diffusion model can still fail to reproduce the quality and diversity of the training data, due to approximation errors made by the finite-capacity network. Diffusion guidance addresses this issue by steering the sampling process away from a less desired model, toward a preferred one. However, current guidance methods rely on a single additional denoiser and manual tuning of guidance weights, which is suboptimal for large, complex models and leads to inefficiencies. The present disclosure employs a mixture of denoisers to guide a diffusion model, which can increase the expressiveness of the guidance and substantially improve sample quality and diversity in the output of the diffusion model.

Dependencies are inferred from the claim text.