ACE-LoRA: Adaptive Orthogonal Decoupling for Continual Image Editing

We study continual image editing, which aims to progressively expand the capability boundary of diffusion models while preserving previously acquired editing skills. In this paper, we propose ACE-LoRA, an adaptive regularization framework that captures state-dependent task interference through an online interference vector. To enable scalable continual learning, we introduce a rank-invariant historical information compression strategy that consolidates accumulated LoRA updates into a fixed-rank representation while preserving principal task-relevant subspaces. Moreover, we present CIE-Bench, a benchmark comprising six practical image editing tasks and a domain-aware evaluation protocol. Experiments show that ACE-LoRA not only outperforms existing baselines in instruction fidelity and visual realism, but also demonstrates the strongest robustness over long task sequences.