ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation

Diffusion customization methods have achieved impressive results with only a minimal number of user-provided images. However, existing approaches customize concepts collectively, whereas real-world applications often require sequential concept integration. This sequential nature can lead to catastrophic forgetting, where previously learned concepts are lost. In this paper, we investigate concept forgetting and concept confusion in the continual customization. To tackle these challenges, we present a comprehensive approach that combines shift embedding, concept-binding prompts and memory preservation regularization, supplemented by a priority queue which can adaptively update the importance and occurrence order of different concepts. Through comprehensive experiments, we demonstrate that our approach outperforms all the baseline methods consistently and significantly in both quantitative and qualitative analyses.