LEDITS：结合 DDPM 反演与语义引导的真实图像编辑
LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance
AI总结：
本文提出 LEDITS，一种结合 Edit Friendly DDPM 反演与 Semantic Guidance 的轻量级真实图像编辑方法，无需优化或扩展架构即可实现细微、广泛及风格构图等多种编辑。
摘要：
近期的大规模文本引导扩散模型提供了强大的图像生成能力。目前，人们投入大量精力以实现仅使用文本修改这些图像，从而提供直观且通用的编辑。然而，对于这些生成模型而言，编辑被证明是困难的，这是由于编辑技术的固有性质，即需要保留原始图像的某些内容。相反，在基于文本的模型中，即使对文本提示进行微小的修改也经常导致完全不同的结果，使得准确符合用户意图的一次性生成极具挑战性。此外，要使用这些最先进的工具编辑真实图像，必须首先将图像反演到预训练模型域——这增加了另一个影响编辑质量以及延迟的因素。在这份探索性报告中，我们提出 LEDITS——一种用于真实图像编辑的轻量级组合方法，将 Edit Friendly DDPM 反演技术与 Semantic Guidance 相结合，从而将 Semantic Guidance 扩展到真实图像编辑，同时利用 DDPM 反演的编辑能力。该方法实现了通用的编辑，包括细微和广泛的编辑以及构图和风格的改变，同时无需优化或扩展架构。
英文摘要：
Recent large-scale text-guided diffusion models provide powerful image-generation capabilities. Currently, a significant effort is given to enable the modification of these images using text only as means to offer intuitive and versatile editing. However, editing proves to be difficult for these generative models due to the inherent nature of editing techniques, which involves preserving certain content from the original image. Conversely, in text-based models, even minor modifications to the text prompt frequently result in an entirely distinct result, making attaining one-shot generation that accurately corresponds to the users intent exceedingly challenging. In addition, to edit a real image using these state-of-the-art tools, one must first invert the image into the pre-trained models domain - adding another factor affecting the edit quality, as well as latency. In this exploratory report, we propose LEDITS - a combined lightweight approach for real-image editing, incorporating the Edit Friendly DDPM inversion technique with Semantic Guidance, thus extending Semantic Guidance to real image editing, while harnessing the editing capabilities of DDPM inversion as well. This approach achieves versatile edits, both subtle and extensive as well as alterations in composition and style, while requiring no optimization nor extensions to the architecture.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
