A dual-level decoupling module with contrastive losses and a mixture-of-experts fusion layer improves identity preservation in subject-driven text-to-image generation.
Multimodal garment designer: Human-centric latent diffusion models for fashion image editing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion
A dual-level decoupling module with contrastive losses and a mixture-of-experts fusion layer improves identity preservation in subject-driven text-to-image generation.