ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kong, Fei, Duan, Jinhao, Sun, Lichao, Cheng, Hao, Xu, Renjing, Shen, Hengtao, Zhu, Xiaofeng, Shi, Xiaoshuang, Xu, Kaidi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910387680575488
author Kong, Fei
Duan, Jinhao
Sun, Lichao
Cheng, Hao
Xu, Renjing
Shen, Hengtao
Zhu, Xiaofeng
Shi, Xiaoshuang
Xu, Kaidi
author_facet Kong, Fei
Duan, Jinhao
Sun, Lichao
Cheng, Hao
Xu, Renjing
Shen, Hengtao
Zhu, Xiaofeng
Shi, Xiaoshuang
Xu, Kaidi
contents Though diffusion models excel in image generation, their step-by-step denoising leads to slow generation speeds. Consistency training addresses this issue with single-step sampling but often produces lower-quality generations and requires high training costs. In this paper, we show that optimizing consistency training loss minimizes the Wasserstein distance between target and generated distributions. As timestep increases, the upper bound accumulates previous consistency training losses. Therefore, larger batch sizes are needed to reduce both current and accumulated losses. We propose Adversarial Consistency Training (ACT), which directly minimizes the Jensen-Shannon (JS) divergence between distributions at each timestep using a discriminator. Theoretically, ACT enhances generation quality, and convergence. By incorporating a discriminator into the consistency training framework, our method achieves improved FID scores on CIFAR10 and ImageNet 64$\times$64 and LSUN Cat 256$\times$256 datasets, retains zero-shot image inpainting capabilities, and uses less than $1/6$ of the original batch size and fewer than $1/2$ of the model parameters and training steps compared to the baseline method, this leads to a substantial reduction in resource consumption. Our code is available:https://github.com/kong13661/ACT
format Preprint
id arxiv_https___arxiv_org_abs_2311_14097
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models
Kong, Fei
Duan, Jinhao
Sun, Lichao
Cheng, Hao
Xu, Renjing
Shen, Hengtao
Zhu, Xiaofeng
Shi, Xiaoshuang
Xu, Kaidi
Computer Vision and Pattern Recognition
Though diffusion models excel in image generation, their step-by-step denoising leads to slow generation speeds. Consistency training addresses this issue with single-step sampling but often produces lower-quality generations and requires high training costs. In this paper, we show that optimizing consistency training loss minimizes the Wasserstein distance between target and generated distributions. As timestep increases, the upper bound accumulates previous consistency training losses. Therefore, larger batch sizes are needed to reduce both current and accumulated losses. We propose Adversarial Consistency Training (ACT), which directly minimizes the Jensen-Shannon (JS) divergence between distributions at each timestep using a discriminator. Theoretically, ACT enhances generation quality, and convergence. By incorporating a discriminator into the consistency training framework, our method achieves improved FID scores on CIFAR10 and ImageNet 64$\times$64 and LSUN Cat 256$\times$256 datasets, retains zero-shot image inpainting capabilities, and uses less than $1/6$ of the original batch size and fewer than $1/2$ of the model parameters and training steps compared to the baseline method, this leads to a substantial reduction in resource consumption. Our code is available:https://github.com/kong13661/ACT
title ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.14097