MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
- 5 December 2024
- book chapter
- Published by Springer Nature
- p. 285-302
Abstract
No abstract availableKeywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Human Preference Score: Better Aligning Text-to-image Models with Human Preference2023
- Q-Diffusion: Quantizing Diffusion Models2023
- On Distillation of Guided Diffusion Models2023
- Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- CLIPScore: A Reference-free Evaluation Metric for Image Captioning2021
- HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision2019
- HAQ: Hardware-Aware Automated Quantization With Mixed Precision2019
- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference2018
- Microsoft COCO: Common Objects in Context2014