逆轉與編輯：基於循環一致性的高效快速圖像編輯模型

摘要

近期，基於擴散模型的圖像編輯技術取得了顯著進展，提供了對生成過程的精細控制。然而，由於其迭代性質，這些方法在計算上相當耗費資源。雖然蒸餾擴散模型能夠實現更快的推理，但其編輯能力仍然受限，主要原因是反演質量不佳。高保真度的反演與重建對於精確的圖像編輯至關重要，因為它們能保持源圖像的結構與語義完整性。在本研究中，我們提出了一種新穎的框架，利用一致性模型增強圖像反演，僅需四步即可實現高質量的編輯。我們的方法引入了一種循環一致性優化策略，顯著提高了重建精度，並在可編輯性與內容保留之間實現了可控的權衡。我們在多種圖像編輯任務與數據集上達到了最先進的性能，證明我們的方法在效率大幅提升的同時，能夠匹配甚至超越全步擴散模型。我們的方法代碼已於GitHub上公開，網址為https://github.com/ControlGenAI/Inverse-and-Edit。

English

Recent advances in image editing with diffusion models have achieved impressive results, offering fine-grained control over the generation process. However, these methods are computationally intensive because of their iterative nature. While distilled diffusion models enable faster inference, their editing capabilities remain limited, primarily because of poor inversion quality. High-fidelity inversion and reconstruction are essential for precise image editing, as they preserve the structural and semantic integrity of the source image. In this work, we propose a novel framework that enhances image inversion using consistency models, enabling high-quality editing in just four steps. Our method introduces a cycle-consistency optimization strategy that significantly improves reconstruction accuracy and enables a controllable trade-off between editability and content preservation. We achieve state-of-the-art performance across various image editing tasks and datasets, demonstrating that our method matches or surpasses full-step diffusion models while being substantially more efficient. The code of our method is available on GitHub at https://github.com/ControlGenAI/Inverse-and-Edit.

逆轉與編輯：基於循環一致性的高效快速圖像編輯模型

Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models

摘要

Support