Text-to-image diffusion models have recently received increasing interest for their astonishing ability to produce high-fidelity images from solely text inputs. Subsequent research efforts aim to exploit and apply their capabilities to real image editing. However, existing image-to-image methods are often inefficient, imprecise, and of limited versatility. They either require time-consuming fine-tuning, deviate unnecessarily strongly from the input image, and/or lack support for multiple, simultaneous edits. To address these issues, we introduce LEDITS++, an efficient yet versatile and precise textual image manipulation technique. LEDITS++'s novel inversion approach requires no tuning nor optimization and produces high-fidelity results with a few diffusion steps. Second, our methodology supports multiple simultaneous edits and is architecture-agnostic. Third, we use a novel implicit masking technique that limits changes to relevant image regions. We propose the novel TEdBench++ benchmark as part of our exhaustive evaluation. Our results demonstrate the capabilities of LEDITS++ and its improvements over previous methods. The project page is available at https://leditsplusplus-project.static.hf.space .

翻译：文本到图像扩散模型因其仅凭文本输入即可生成高保真图像的惊人能力，近期受到越来越多的关注。后续研究工作旨在利用并将其能力应用于真实图像编辑。然而，现有的图像到图像方法通常效率低下、精度不足且通用性有限。它们要么需要耗时的微调，要么不必要地偏离输入图像，或者缺乏对多重同步编辑的支持。为解决这些问题，我们提出了LEDITS++，一种高效、通用且精确的文本图像操作技术。LEDITS++新颖的逆推方法无需调优或优化，通过少量扩散步骤即可产生高保真结果。其次，我们的方法支持多重同步编辑且与架构无关。第三，我们采用一种新型隐式掩码技术，将修改限制在相关图像区域。我们提出新的TEdBench++基准测试作为全面评估的一部分。实验结果展示了LEDITS++的能力及其相比先前方法的改进。项目页面位于https://leditsplusplus-project.static.hf.space。