MOSAIC improves multi-subject personalized image generation by supervising attention maps with semantic point correspondences and a disentanglement loss, and introduces the SemAlign-MS dataset for training.
Blip-diffusion: Pre-trained subject representation for controllable text-to-image generation and editing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement
MOSAIC improves multi-subject personalized image generation by supervising attention maps with semantic point correspondences and a disentanglement loss, and introduces the SemAlign-MS dataset for training.