ACE：文本到图像模型中的抗编辑概念擦除
ACE: Anti-Editing Concept Erasure in Text-to-Image Models
AI总结：
本文提出ACE方法，通过在条件与无条件噪声预测中注入擦除引导并引入随机校正引导，同时解决文本到图像模型在生成和编辑阶段的概念擦除问题，实验证明其在IP角色、显式概念和艺术风格擦除上优于现有方法。
摘要：
文本到图像扩散模型的最新进展显著促进了高质量图像的生成，但也引发了对有害内容（如受版权保护的图像）非法创建的担忧。现有的概念擦除方法在防止根据提示生成被擦除概念方面取得了优异效果，但在防止不希望发生的编辑方面通常表现不佳。为了解决这一问题，我们提出了一种抗编辑概念擦除（ACE）方法，该方法不仅在生成过程中擦除目标概念，还在编辑过程中将其过滤掉。具体而言，我们提出将擦除引导注入条件噪声预测和无条件噪声预测中，使模型能够在编辑和生成过程中有效防止擦除概念的创建。此外，在训练过程中引入随机校正引导，以解决无关概念被侵蚀的问题。我们使用代表性编辑方法（即LEDITS++和MasaCtrl）进行了擦除编辑实验，以擦除IP角色，结果表明我们的ACE在两类编辑中都能有效过滤目标概念。针对显式概念和艺术风格擦除的额外实验进一步表明，我们的ACE相比最先进的方法表现优异。我们的代码将在 https://github.com/120L020904/ACE 公开提供。
英文摘要：
Recent advance in text-to-image diffusion models have significantly facilitated the generation of high-quality images, but also raising concerns about the illegal creation of harmful content, such as copyrighted images. Existing concept erasure methods achieve superior results in preventing the production of erased concept from prompts, but typically perform poorly in preventing undesired editing. To address this issue, we propose an Anti-Editing Concept Erasure (ACE) method, which not only erases the target concept during generation but also filters out it during editing. Specifically, we propose to inject the erasure guidance into both conditional and the unconditional noise prediction, enabling the model to effectively prevent the creation of erasure concepts during both editing and generation. Furthermore, a stochastic correction guidance is introduced during training to address the erosion of unrelated concepts. We conducted erasure editing experiments with representative editing methods (i.e., LEDITS++ and MasaCtrl) to erase IP characters, and the results indicate that our ACE effectively filters out target concepts in both types of edits. Additional experiments on erasing explicit concepts and artistic styles further demonstrate that our ACE performs favorably against state-of-the-art methods. Our code will be publicly available at https://github.com/120L020904/ACE.
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。
