Tight Inversion: Image-Conditioned Inversion for Real Image Editing

TL;DR

This paper introduces Tight Inversion, a novel image inversion method for diffusion models that uses the input image itself as a precise condition, improving reconstruction and editability of real images.

Contribution

The work proposes a new inversion technique that leverages the input image as a condition, significantly enhancing inversion quality and editing capabilities.

Findings

Improved reconstruction accuracy over existing methods

Enhanced editability of challenging images

Effective when combined with various editing techniques

Abstract

Text-to-image diffusion models offer powerful image editing capabilities. To edit real images, many methods rely on the inversion of the image into Gaussian noise. A common approach to invert an image is to gradually add noise to the image, where the noise is determined by reversing the sampling equation. This process has an inherent tradeoff between reconstruction and editability, limiting the editing of challenging images such as highly-detailed ones. Recognizing the reliance of text-to-image models inversion on a text condition, this work explores the importance of the condition choice. We show that a condition that precisely aligns with the input image significantly improves the inversion quality. Based on our findings, we introduce Tight Inversion, an inversion method that utilizes the most possible precise condition -- the input image itself. This tight condition narrows the distribution of the model's output and enhances both reconstruction and editability. We demonstrate the effectiveness of our approach when combined with existing inversion methods through extensive experiments, evaluating the reconstruction accuracy as well as the integration with various editing methods.