Improving Tuning-Free Real Image Editing with Proximal Guidance

TL;DR

This paper introduces proximal guidance to improve real image editing with diffusion models, enhancing artifact reduction, layout control, and editing quality without additional training.

Contribution

It proposes a novel proximal guidance method integrated with null-text inversion, enabling high-quality, artifact-free, and geometry-aware real image editing with minimal overhead.

Findings

Reduces artifacts in real image editing.

Enables geometry and layout modifications.

Maintains efficiency with minimal computational cost.

Abstract

DDIM inversion has revealed the remarkable potential of real image editing within diffusion-based methods. However, the accuracy of DDIM reconstruction degrades as larger classifier-free guidance (CFG) scales being used for enhanced editing. Null-text inversion (NTI) optimizes null embeddings to align the reconstruction and inversion trajectories with larger CFG scales, enabling real image editing with cross-attention control. Negative-prompt inversion (NPI) further offers a training-free closed-form solution of NTI. However, it may introduce artifacts and is still constrained by DDIM reconstruction quality. To overcome these limitations, we propose proximal guidance and incorporate it to NPI with cross-attention control. We enhance NPI with a regularization term and reconstruction guidance, which reduces artifacts while capitalizing on its training-free nature. Additionally, we extend the concepts to incorporate mutual self-attention control, enabling geometry and layout alterations in the editing process. Our method provides an efficient and straightforward approach, effectively addressing real image editing tasks with minimal computational overhead.