Noise-Level Diffusion Guidance: Well Begun is Half Done

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Mannering, Harvey, Huang, Zhiwu, Prugel-Bennett, Adam
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912590675836928
author Mannering, Harvey
Huang, Zhiwu
Prugel-Bennett, Adam
author_facet Mannering, Harvey
Huang, Zhiwu
Prugel-Bennett, Adam
contents Diffusion models have achieved state-of-the-art image generation. However, the random Gaussian noise used to start the diffusion process influences the final output, causing variations in image quality and prompt adherence. Existing noise-level optimization approaches generally rely on extra dataset construction, additional networks, or backpropagation-based optimization, limiting their practicality. In this paper, we propose Noise Level Guidance (NLG), a simple, efficient, and general noise-level optimization approach that refines initial noise by increasing the likelihood of its alignment with general guidance - requiring no additional training data, auxiliary networks, or backpropagation. The proposed NLG approach provides a unified framework generalizable to both conditional and unconditional diffusion models, accommodating various forms of diffusion-level guidance. Extensive experiments on five standard benchmarks demonstrate that our approach enhances output generation quality and input condition adherence. By seamlessly integrating with existing guidance methods while maintaining computational efficiency, our method establishes NLG as a practical and scalable enhancement to diffusion models. Code can be found at https://github.com/harveymannering/NoiseLevelGuidance.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13936
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Noise-Level Diffusion Guidance: Well Begun is Half Done
Mannering, Harvey
Huang, Zhiwu
Prugel-Bennett, Adam
Computer Vision and Pattern Recognition
Diffusion models have achieved state-of-the-art image generation. However, the random Gaussian noise used to start the diffusion process influences the final output, causing variations in image quality and prompt adherence. Existing noise-level optimization approaches generally rely on extra dataset construction, additional networks, or backpropagation-based optimization, limiting their practicality. In this paper, we propose Noise Level Guidance (NLG), a simple, efficient, and general noise-level optimization approach that refines initial noise by increasing the likelihood of its alignment with general guidance - requiring no additional training data, auxiliary networks, or backpropagation. The proposed NLG approach provides a unified framework generalizable to both conditional and unconditional diffusion models, accommodating various forms of diffusion-level guidance. Extensive experiments on five standard benchmarks demonstrate that our approach enhances output generation quality and input condition adherence. By seamlessly integrating with existing guidance methods while maintaining computational efficiency, our method establishes NLG as a practical and scalable enhancement to diffusion models. Code can be found at https://github.com/harveymannering/NoiseLevelGuidance.
title Noise-Level Diffusion Guidance: Well Begun is Half Done
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.13936