用一致性模型四步完成高质量图像编辑，又快又准。
Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models
- 用循环一致性优化提升图像逆向重建质量。
- 四步完成编辑，性能媲美全步扩散模型。
- 适合需要快速精准编辑的视觉应用。
基于扩散模型的图像编辑虽有良好效果，但因迭代过程计算量大。尽管蒸馏模型可加速推理，但编辑能力受限于逆向重建质量不佳。本文提出新框架，利用一致性模型增强图像逆向，实现仅四步即可高保真编辑。通过循环一致性优化策略，显著提升重建精度，并在可编辑性与内容保留间实现可控权衡。在多个图像编辑任务和数据集上达到当前最佳表现，性能匹配甚至超越完整步数扩散模型，同时大幅提高效率。代码已开源：https://github.com/ControlGenAI/Inverse-and-Edit。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。