Papers
arxiv:2605.18736

Spectral Progressive Diffusion for Efficient Image and Video Generation

Published on May 20
Authors:
,
,
,

Abstract

Spectral Progressive Diffusion accelerates diffusion model generation by progressively increasing resolution along the denoising trajectory using spectral noise expansion and optimal scheduling derived from the model's power spectrum.

Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later timesteps. This structure offers a natural opportunity for efficient generation, as high-resolution computation on noise-dominated frequencies is largely redundant. We propose Spectral Progressive Diffusion, a general framework that progressively grows resolution along the denoising trajectory of pretrained diffusion models. To this end, we develop a spectral noise expansion mechanism and derive an optimal resolution schedule from the model's power spectrum. Our framework supports training-free acceleration and a novel fine-tuning recipe that further improves efficiency and quality. We demonstrate significant speedups on state-of-the-art pretrained image and video generation models while preserving visual quality.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.18736
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.18736 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.18736 in a dataset README.md to link it from this page.

Spaces citing this paper 1

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.