SSI-DM: Singularity Skipping Inversion of Diffusion Models

TL;DR

SSI-DM introduces a novel inversion method for diffusion models that bypasses mathematical singularities, resulting in more accurate, Gaussian-like noise inversion and improved image editing capabilities.

Contribution

It proposes a simple, effective singularity skipping technique for diffusion model inversion that enhances noise Gaussianity and reconstruction quality.

Findings

Achieves superior reconstruction and interpolation results

Produces more natural Gaussian noise in inversion

Compatible with various diffusion models

Abstract

Inverting real images into the noise space is essential for editing tasks using diffusion models, yet existing methods produce non-Gaussian noise with poor editability due to the inaccuracy in early noising steps. We identify the root cause: a mathematical singularity that renders inversion fundamentally ill-posed. We propose Singularity Skipping Inversion of Diffusion Models (SSI-DM), which bypasses this singular region by adding small noise before standard inversion. This simple approach produces inverted noise with natural Gaussian properties while maintaining reconstruction fidelity. As a plug-and-play technique compatible with general diffusion models, our method achieves superior performance on public image datasets for reconstruction and interpolation tasks, providing a principled and efficient solution to diffusion model inversion.