DreamBooth fine-tuning updates are low-rank, so post-hoc SVD with energy-based truncation compresses personalized models by up to 270x with mild quality loss.
In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
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
-
Delta-SVD: Efficient Compression for Personalized Text-to-Image Models
DreamBooth fine-tuning updates are low-rank, so post-hoc SVD with energy-based truncation compresses personalized models by up to 270x with mild quality loss.