Independently trained LoRAs composed as sequential layers with frozen conditioning preserve multi-subject identity better than weight-space fusion, reaching 0.861 ArcFace detection rate.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models
Independently trained LoRAs composed as sequential layers with frozen conditioning preserve multi-subject identity better than weight-space fusion, reaching 0.861 ArcFace detection rate.