残差空间适配实现扩散模型持续概念个性化
Continual Concept Personalization in Diffusion Models via Residual-Space Adaptation
教扩散模型学你的新概念还不忘旧的，这套残差适配方法保真度最高，参数还能砍 72%，玩个性化生成的看看。
arXiv 论文提出在扩散模型的随机适配过程中引入残差空间适配，解决概念按时间顺序到来时的持续个性化问题。方法在对比的持续个性化方法中取得最高概念保真度，同时保持接近零的遗忘。通过分析残差空间动态，可定位扩散模型中适配容量集中的层，仅限制这些层训练即可保持接近相同性能，可训练参数最多减少 72%。
Continual Concept Personalization in Diffusion Models via Residual-Space Adaptation
Text-to-image personalization aims to equip pretrained diffusion models with the ability to learn user-specific concepts from only a few reference images. Existing methods, however, typically train each concept independently or assume that all concepts are available simultaneously. In practical applications, concepts often arrive sequentially, requiring models to continually learn new subjects, objects, or styles while minimizing interference with previously acquired concepts. We address this continual concept personalization setting by extending residual-space adaptation to the stochastic adaptation process of pretrained diffusion models. Our work achieves the highest concept fidelity among competing continual personalization methods while maintaining near-zero forgetting. Beyond these empirical gains, the learned residual-space dynamics reveal where adaptation capacity is concentrated within the diffusion model. Restricting adaptation to the identified layers by our method preserves nearly the same performance while reducing the number of trainable parameters by up to 72\%, demonstrating that residual-space dynamics can identify the layers that contribute most to continual concept personalization and directly guide more parameter-efficient adaptation.
