PQCAD-DM combines progressive two-stage quantization with calibration-assisted distillation to halve the sampling steps of a quantized diffusion model while keeping FID scores close to baseline.
Generative adversarial networks,
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
background 1representative citing papers
citing papers explorer
-
PQCAD-DM: Progressive Quantization and Calibration-Assisted Distillation for Extremely Efficient Diffusion Model
PQCAD-DM combines progressive two-stage quantization with calibration-assisted distillation to halve the sampling steps of a quantized diffusion model while keeping FID scores close to baseline.