首个专用于流模型的图像概念擦除方法，精准移除不想要的内容。
EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
- 将概念擦除建模为双层优化问题，结合LoRA与注意力图正则化
- 在Stable Diffusion v3等新框架上实现领先性能，保持生成质量
- 适合需要精确控制生成内容的开发者和研究人员
在大规模文本到图像（T2I）扩散模型中，移除不想要的概念同时保持整体生成质量仍是未解难题。这一挑战在新兴范式如Stable Diffusion v3和Flux中尤为突出，它们采用流匹配和基于Transformer的架构，使得原有针对旧范式（如SD v1.4）设计的概念擦除技术难以迁移。本文提出EraseAnything，首个专为最新流基T2I框架设计的概念擦除方法。我们将概念擦除建模为双层优化问题，利用基于LoRA的参数调优和注意力图正则化，选择性抑制不良激活。此外，提出自对比学习策略，确保移除不想要的概念不会意外损害对无关概念的生成性能。实验结果表明，EraseAnything成功填补了早期方法在该新范式下的研究空白，在多种概念擦除任务中达到最先进水平。
原文摘要 · Abstract (English)
Removing unwanted concepts from large-scale text-to-image (T2I) diffusion models while maintaining their overall generative quality remains an open challenge. This difficulty is especially pronounced in emerging paradigms, such as Stable Diffusion (SD) v3 and Flux, which incorporate flow matching and transformer-based architectures. These advancements limit the transferability of existing concept-erasure techniques that were originally designed for the previous T2I paradigm (e.g., SD v1.4). In this work, we introduce EraseAnything, the first method specifically developed to address concept erasure within the latest flow-based T2I framework. We formulate concept erasure as a bi-level optimization problem, employing LoRA-based parameter tuning and an attention map regularizer to selectively suppress undesirable activations. Furthermore, we propose a self-contrastive learning strategy to ensure that removing unwanted concepts does not inadvertently harm performance on unrelated ones. Experimental results demonstrate that EraseAnything successfully fills the research gap left by earlier methods in this new T2I paradigm, achieving state-of-the-art performance across a wide range of concept erasure tasks.
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。