CusEnhancer: A Zero-Shot Scene and Controllability Enhancement Method for Photo Customization via ResInversion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ren, Maoye, Vaddamanu, Praneetha, Xu, Jianjin, Frade, Fernando De la Torre
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911175631962112
author Ren, Maoye
Vaddamanu, Praneetha
Xu, Jianjin
Frade, Fernando De la Torre
author_facet Ren, Maoye
Vaddamanu, Praneetha
Xu, Jianjin
Frade, Fernando De la Torre
contents Recently remarkable progress has been made in synthesizing realistic human photos using text-to-image diffusion models. However, current approaches face degraded scenes, insufficient control, and suboptimal perceptual identity. We introduce CustomEnhancer, a novel framework to augment existing identity customization models. CustomEnhancer is a zero-shot enhancement pipeline that leverages face swapping techniques, pretrained diffusion model, to obtain additional representations in a zeroshot manner for encoding into personalized models. Through our proposed triple-flow fused PerGeneration approach, which identifies and combines two compatible counter-directional latent spaces to manipulate a pivotal space of personalized model, we unify the generation and reconstruction processes, realizing generation from three flows. Our pipeline also enables comprehensive training-free control over the generation process of personalized models, offering precise controlled personalization for them and eliminating the need for controller retraining for per-model. Besides, to address the high time complexity of null-text inversion (NTI), we introduce ResInversion, a novel inversion method that performs noise rectification via a pre-diffusion mechanism, reducing the inversion time by 129 times. Experiments demonstrate that CustomEnhancer reach SOTA results at scene diversity, identity fidelity, training-free controls, while also showing the efficiency of our ResInversion over NTI. The code will be made publicly available upon paper acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20775
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CusEnhancer: A Zero-Shot Scene and Controllability Enhancement Method for Photo Customization via ResInversion
Ren, Maoye
Vaddamanu, Praneetha
Xu, Jianjin
Frade, Fernando De la Torre
Computer Vision and Pattern Recognition
Artificial Intelligence
Recently remarkable progress has been made in synthesizing realistic human photos using text-to-image diffusion models. However, current approaches face degraded scenes, insufficient control, and suboptimal perceptual identity. We introduce CustomEnhancer, a novel framework to augment existing identity customization models. CustomEnhancer is a zero-shot enhancement pipeline that leverages face swapping techniques, pretrained diffusion model, to obtain additional representations in a zeroshot manner for encoding into personalized models. Through our proposed triple-flow fused PerGeneration approach, which identifies and combines two compatible counter-directional latent spaces to manipulate a pivotal space of personalized model, we unify the generation and reconstruction processes, realizing generation from three flows. Our pipeline also enables comprehensive training-free control over the generation process of personalized models, offering precise controlled personalization for them and eliminating the need for controller retraining for per-model. Besides, to address the high time complexity of null-text inversion (NTI), we introduce ResInversion, a novel inversion method that performs noise rectification via a pre-diffusion mechanism, reducing the inversion time by 129 times. Experiments demonstrate that CustomEnhancer reach SOTA results at scene diversity, identity fidelity, training-free controls, while also showing the efficiency of our ResInversion over NTI. The code will be made publicly available upon paper acceptance.
title CusEnhancer: A Zero-Shot Scene and Controllability Enhancement Method for Photo Customization via ResInversion
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.20775