A hybrid of low-resolution backpropagation and high-resolution zeroth-order optimization, scheduled by a dynamic timestep-dependent probability, matches full-resolution fine-tuning quality while cutting training memory.
Multi-concept customization of text-to-image diffusion
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
-
Memory-Efficient Personalization of Text-to-Image Diffusion Models via Selective Optimization Strategies
A hybrid of low-resolution backpropagation and high-resolution zeroth-order optimization, scheduled by a dynamic timestep-dependent probability, matches full-resolution fine-tuning quality while cutting training memory.