FireFlow：用於圖像語義編輯的快速矯正流反演

FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing

December 10, 2024

作者: Yingying Deng, Xiangyu He, Changwang Mei, Peisong Wang, Fan Tang

cs.AI

摘要

儘管具有蒸餾功能的矯正流（ReFlows）提供了一種快速取樣的有希望方法，但其快速反演將圖像轉換回結構噪音以進行恢復和後續編輯仍未解決。本文介紹了FireFlow，這是一種簡單而有效的零樣本方法，它繼承了基於ReFlow的模型（如FLUX）在生成方面的驚人能力，同時擴展了其在準確反演和編輯方面的能力，共分為8個步驟。我們首先證明，一個精心設計的數值求解器對於ReFlow反演至關重要，實現了具有二階求解器精度的準確反演和重建，同時保持了一階Euler方法的實用效率。與最先進的ReFlow反演和編輯技術相比，此求解器實現了3倍的運行時間加速，同時在無需訓練的模式下提供更小的重建誤差和優越的編輯結果。代碼可在以下網址找到：https://github.com/HolmesShuan/FireFlow{此URL}。

English

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 3times 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 https://github.com/HolmesShuan/FireFlow{this URL}.