ACE: Anti-Editing Concept Erasure in Text-to-Image Models
This addresses the issue of illegal content creation for users of text-to-image models, though it is incremental as it builds on existing concept erasure methods.
The paper tackles the problem of preventing harmful content generation in text-to-image models by proposing an Anti-Editing Concept Erasure (ACE) method that erases target concepts during both generation and editing, with experiments showing it effectively filters out concepts like IP characters, explicit content, and artistic styles compared to state-of-the-art methods.
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.