FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing

TL;DR

FireFlow introduces a fast, accurate, zero-shot inversion method for Rectified Flows that significantly improves image editing speed and quality without additional training.

Contribution

It presents a novel numerical solver for ReFlow inversion, enabling efficient, high-precision image reconstruction and editing in just 8 steps, outperforming existing methods.

Findings

3x faster inversion compared to state-of-the-art techniques

Smaller reconstruction errors and superior editing results

Training-free approach with practical efficiency

Abstract

Though Rectified Flows (ReFlows) with distillation offers a promising way for fast sampling, its fast inversion transforms images back to structured noise for recovery and following editing remains unsolved. This paper introduces FireFlow, a simple yet effective zero-shot approach that inherits the startling capacity of ReFlow-based models (such as FLUX) in generation while extending its capabilities to accurate inversion and editing in $8$ steps. We first demonstrate that a carefully designed numerical solver is pivotal for ReFlow inversion, enabling accurate inversion and reconstruction with the precision of a second-order solver while maintaining the practical efficiency of a first-order Euler method. This solver achieves a $3\times$ runtime speedup compared to state-of-the-art ReFlow inversion and editing techniques, while delivering smaller reconstruction errors and superior editing results in a training-free mode. The code is available at $\href{https://github.com/HolmesShuan/FireFlow}{this URL}$.