Guiding a diffusion model using sliding windows

TL;DR

This paper introduces M-SWG, a training-free guidance method for diffusion models that enhances sample quality by selectively restricting the receptive field, achieving state-of-the-art results without additional training.

Contribution

The paper proposes M-SWG, a novel, training-free guidance technique that improves diffusion model outputs by leveraging self-guidance with restricted receptive fields.

Findings

M-SWG outperforms previous training-free guidance methods in Inception score.

M-SWG combined with existing methods achieves state-of-the-art Frechet DINOv2 distance on ImageNet.

M-SWG does not require model weight access, additional training, or class conditioning.

Abstract

Guidance is a widely used technique for diffusion models to enhance sample quality. Technically, guidance is realised by using an auxiliary model that generalises more broadly than the primary model. Using a 2D toy example, we first show that it is highly beneficial when the auxiliary model exhibits similar but stronger generalisation errors than the primary model. Based on this insight, we introduce \emph{masked sliding window guidance (M-SWG)}, a novel, training-free method. M-SWG upweights long-range spatial dependencies by guiding the primary model with itself by selectively restricting its receptive field. M-SWG requires neither access to model weights from previous iterations, additional training, nor class conditioning. M-SWG achieves a superior Inception score (IS) compared to previous state-of-the-art training-free approaches, without introducing sample oversaturation. In conjunction with existing guidance methods, M-SWG reaches state-of-the-art Frechet DINOv2 distance on ImageNet using EDM2-XXL and DiT-XL. The code is available at https://github.com/HHU-MMBS/swg_bmvc2025_official.