AccDiffusion: An Accurate Method for Higher-Resolution Image Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lin, Zhihang, Lin, Mingbao, Zhao, Meng, Ji, Rongrong
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914876227584000
author Lin, Zhihang
Lin, Mingbao
Zhao, Meng
Ji, Rongrong
author_facet Lin, Zhihang
Lin, Mingbao
Zhao, Meng
Ji, Rongrong
contents This paper attempts to address the object repetition issue in patch-wise higher-resolution image generation. We propose AccDiffusion, an accurate method for patch-wise higher-resolution image generation without training. An in-depth analysis in this paper reveals an identical text prompt for different patches causes repeated object generation, while no prompt compromises the image details. Therefore, our AccDiffusion, for the first time, proposes to decouple the vanilla image-content-aware prompt into a set of patch-content-aware prompts, each of which serves as a more precise description of an image patch. Besides, AccDiffusion also introduces dilated sampling with window interaction for better global consistency in higher-resolution image generation. Experimental comparison with existing methods demonstrates that our AccDiffusion effectively addresses the issue of repeated object generation and leads to better performance in higher-resolution image generation.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10738
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
Lin, Zhihang
Lin, Mingbao
Zhao, Meng
Ji, Rongrong
Computer Vision and Pattern Recognition
This paper attempts to address the object repetition issue in patch-wise higher-resolution image generation. We propose AccDiffusion, an accurate method for patch-wise higher-resolution image generation without training. An in-depth analysis in this paper reveals an identical text prompt for different patches causes repeated object generation, while no prompt compromises the image details. Therefore, our AccDiffusion, for the first time, proposes to decouple the vanilla image-content-aware prompt into a set of patch-content-aware prompts, each of which serves as a more precise description of an image patch. Besides, AccDiffusion also introduces dilated sampling with window interaction for better global consistency in higher-resolution image generation. Experimental comparison with existing methods demonstrates that our AccDiffusion effectively addresses the issue of repeated object generation and leads to better performance in higher-resolution image generation.
title AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.10738