Mariana-Iuliana Georgescu

LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models

This work introduces LILAC, a framework that composes independently trained low-rank adapters at inference time: each subject is conditioned on the frozen composite of previously placed subjects, with exactly one adapter active at a time, therefore identities never interfere at the parameter level.