EasyInv: Toward Fast and Better DDIM Inversion

TL;DR

EasyInv is a novel, efficient approach for DDIM inversion that improves accuracy and speed by focusing on initial latent states and simple aggregation, outperforming traditional iterative methods especially under resource constraints.

Contribution

EasyInv introduces a simple, effective method for DDIM inversion that enhances accuracy and efficiency without complex optimization, compatible with existing methods.

Findings

Achieves approximately threefold speedup over iterative methods.

Maintains or exceeds the accuracy of traditional DDIM inversion.

Easily integrates with existing inversion techniques with minimal code.

Abstract

This paper introduces EasyInv, an easy yet novel approach that significantly advances the field of DDIM Inversion by addressing the inherent inefficiencies and performance limitations of traditional iterative optimization methods. At the core of our EasyInv is a refined strategy for approximating inversion noise, which is pivotal for enhancing the accuracy and reliability of the inversion process. By prioritizing the initial latent state, which encapsulates rich information about the original images, EasyInv steers clear of the iterative refinement of noise items. Instead, we introduce a methodical aggregation of the latent state from the preceding time step with the current state, effectively increasing the influence of the initial latent state and mitigating the impact of noise. We illustrate that EasyInv is capable of delivering results that are either on par with or exceed those of the conventional DDIM Inversion approach, especially under conditions where the model's precision is limited or computational resources are scarce. Concurrently, our EasyInv offers an approximate threefold enhancement regarding inference efficiency over off-the-shelf iterative optimization techniques. It can be easily combined with most existing inversion methods by only four lines of code. See code at https://github.com/potato-kitty/EasyInv.