UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Fanghua, Gu, Jinjin, Hu, Jinfan, Li, Zheyuan, Dong, Chao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915217841061888
author Yu, Fanghua
Gu, Jinjin
Hu, Jinfan
Li, Zheyuan
Dong, Chao
author_facet Yu, Fanghua
Gu, Jinjin
Hu, Jinfan
Li, Zheyuan
Dong, Chao
contents We introduce UniCon, a novel architecture designed to enhance control and efficiency in training adapters for large-scale diffusion models. Unlike existing methods that rely on bidirectional interaction between the diffusion model and control adapter, UniCon implements a unidirectional flow from the diffusion network to the adapter, allowing the adapter alone to generate the final output. UniCon reduces computational demands by eliminating the need for the diffusion model to compute and store gradients during adapter training. Our results indicate that UniCon reduces GPU memory usage by one-third and increases training speed by 2.3 times, while maintaining the same adapter parameter size. Additionally, without requiring extra computational resources, UniCon enables the training of adapters with double the parameter volume of existing ControlNets. In a series of image conditional generation tasks, UniCon has demonstrated precise responsiveness to control inputs and exceptional generation capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17221
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models
Yu, Fanghua
Gu, Jinjin
Hu, Jinfan
Li, Zheyuan
Dong, Chao
Computer Vision and Pattern Recognition
We introduce UniCon, a novel architecture designed to enhance control and efficiency in training adapters for large-scale diffusion models. Unlike existing methods that rely on bidirectional interaction between the diffusion model and control adapter, UniCon implements a unidirectional flow from the diffusion network to the adapter, allowing the adapter alone to generate the final output. UniCon reduces computational demands by eliminating the need for the diffusion model to compute and store gradients during adapter training. Our results indicate that UniCon reduces GPU memory usage by one-third and increases training speed by 2.3 times, while maintaining the same adapter parameter size. Additionally, without requiring extra computational resources, UniCon enables the training of adapters with double the parameter volume of existing ControlNets. In a series of image conditional generation tasks, UniCon has demonstrated precise responsiveness to control inputs and exceptional generation capabilities.
title UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.17221