Input-Adaptive Generative Dynamics in Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xing, Yucheng, Liu, Xiaodong, Wang, Xin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910044289761280
author Xing, Yucheng
Liu, Xiaodong
Wang, Xin
author_facet Xing, Yucheng
Liu, Xiaodong
Wang, Xin
contents Diffusion models typically generate data through a fixed denoising trajectory that is shared across all samples. However, generation targets can differ in complexity, suggesting that a single pre-defined diffusion process may not be optimal for every input. In this work, we investigate input-adaptive generative dynamics for diffusion models, where the generation process itself adapts to the conditions of each sample. Instead of relying on a fixed diffusion trajectory, the proposed framework allows the generative dynamics to adjust across inputs according to their generation requirements. To enable this behavior, we train the diffusion backbone under varying horizons and noise schedules, so that it can operate consistently under different input-adaptive trajectories. Experiments on conditional image generation show that diffusion trajectories can vary across inputs while maintaining generation quality and reducing the average number of sampling steps. These results provide a proof of the concept that diffusion processes can benefit from input-adaptive generative dynamics rather than relying on a single fixed trajectory.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15199
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Input-Adaptive Generative Dynamics in Diffusion Models
Xing, Yucheng
Liu, Xiaodong
Wang, Xin
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Diffusion models typically generate data through a fixed denoising trajectory that is shared across all samples. However, generation targets can differ in complexity, suggesting that a single pre-defined diffusion process may not be optimal for every input. In this work, we investigate input-adaptive generative dynamics for diffusion models, where the generation process itself adapts to the conditions of each sample. Instead of relying on a fixed diffusion trajectory, the proposed framework allows the generative dynamics to adjust across inputs according to their generation requirements. To enable this behavior, we train the diffusion backbone under varying horizons and noise schedules, so that it can operate consistently under different input-adaptive trajectories. Experiments on conditional image generation show that diffusion trajectories can vary across inputs while maintaining generation quality and reducing the average number of sampling steps. These results provide a proof of the concept that diffusion processes can benefit from input-adaptive generative dynamics rather than relying on a single fixed trajectory.
title Input-Adaptive Generative Dynamics in Diffusion Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2411.15199