Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hou, Xinyu, Yue, Zongsheng, Li, Xiaoming, Loy, Chen Change
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912494224670720
author Hou, Xinyu
Yue, Zongsheng
Li, Xiaoming
Loy, Chen Change
author_facet Hou, Xinyu
Yue, Zongsheng
Li, Xiaoming
Loy, Chen Change
contents In this work, we show that we only need a single parameter $ω$ to effectively control granularity in diffusion-based synthesis. This parameter is incorporated during the denoising steps of the diffusion model's reverse process. This simple approach does not require model retraining or architectural modifications and incurs negligible computational overhead, yet enables precise control over the level of details in the generated outputs. Moreover, spatial masks or denoising schedules with varying $ω$ values can be applied to achieve region-specific or timestep-specific granularity control. External control signals or reference images can guide the creation of precise $ω$ masks, allowing targeted granularity adjustments. Despite its simplicity, the method demonstrates impressive performance across various image and video synthesis tasks and is adaptable to advanced diffusion models. The code is available at https://github.com/itsmag11/Omegance.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17769
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis
Hou, Xinyu
Yue, Zongsheng
Li, Xiaoming
Loy, Chen Change
Computer Vision and Pattern Recognition
In this work, we show that we only need a single parameter $ω$ to effectively control granularity in diffusion-based synthesis. This parameter is incorporated during the denoising steps of the diffusion model's reverse process. This simple approach does not require model retraining or architectural modifications and incurs negligible computational overhead, yet enables precise control over the level of details in the generated outputs. Moreover, spatial masks or denoising schedules with varying $ω$ values can be applied to achieve region-specific or timestep-specific granularity control. External control signals or reference images can guide the creation of precise $ω$ masks, allowing targeted granularity adjustments. Despite its simplicity, the method demonstrates impressive performance across various image and video synthesis tasks and is adaptable to advanced diffusion models. The code is available at https://github.com/itsmag11/Omegance.
title Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17769