Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Siao, Wang, Xin, Chen, Hong, Guan, Chaoyu, Wu, Zewen, Tang, Yansong, Zhu, Wenwu
Format:	Preprint
Published:	2023
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2311.06322