Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xu, Pengcheng, Jiang, Boyuan, Hu, Xiaobin, Luo, Donghao, He, Qingdong, Zhang, Jiangning, Wang, Chengjie, Wu, Yunsheng, Ling, Charles, Wang, Boyu
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917967558606848
author Xu, Pengcheng
Jiang, Boyuan
Hu, Xiaobin
Luo, Donghao
He, Qingdong
Zhang, Jiangning
Wang, Chengjie
Wu, Yunsheng
Ling, Charles
Wang, Boyu
author_facet Xu, Pengcheng
Jiang, Boyuan
Hu, Xiaobin
Luo, Donghao
He, Qingdong
Zhang, Jiangning
Wang, Chengjie
Wu, Yunsheng
Ling, Charles
Wang, Boyu
contents Leveraging the large generative prior of the flow transformer for tuning-free image editing requires authentic inversion to project the image into the model's domain and a flexible invariance control mechanism to preserve non-target contents. However, the prevailing diffusion inversion performs deficiently in flow-based models, and the invariance control cannot reconcile diverse rigid and non-rigid editing tasks. To address these, we systematically analyze the \textbf{inversion and invariance} control based on the flow transformer. Specifically, we unveil that the Euler inversion shares a similar structure to DDIM yet is more susceptible to the approximation error. Thus, we propose a two-stage inversion to first refine the velocity estimation and then compensate for the leftover error, which pivots closely to the model prior and benefits editing. Meanwhile, we propose the invariance control that manipulates the text features within the adaptive layer normalization, connecting the changes in the text prompt to image semantics. This mechanism can simultaneously preserve the non-target contents while allowing rigid and non-rigid manipulation, enabling a wide range of editing types such as visual text, quantity, facial expression, etc. Experiments on versatile scenarios validate that our framework achieves flexible and accurate editing, unlocking the potential of the flow transformer for versatile image editing.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15843
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing
Xu, Pengcheng
Jiang, Boyuan
Hu, Xiaobin
Luo, Donghao
He, Qingdong
Zhang, Jiangning
Wang, Chengjie
Wu, Yunsheng
Ling, Charles
Wang, Boyu
Computer Vision and Pattern Recognition
Machine Learning
Leveraging the large generative prior of the flow transformer for tuning-free image editing requires authentic inversion to project the image into the model's domain and a flexible invariance control mechanism to preserve non-target contents. However, the prevailing diffusion inversion performs deficiently in flow-based models, and the invariance control cannot reconcile diverse rigid and non-rigid editing tasks. To address these, we systematically analyze the \textbf{inversion and invariance} control based on the flow transformer. Specifically, we unveil that the Euler inversion shares a similar structure to DDIM yet is more susceptible to the approximation error. Thus, we propose a two-stage inversion to first refine the velocity estimation and then compensate for the leftover error, which pivots closely to the model prior and benefits editing. Meanwhile, we propose the invariance control that manipulates the text features within the adaptive layer normalization, connecting the changes in the text prompt to image semantics. This mechanism can simultaneously preserve the non-target contents while allowing rigid and non-rigid manipulation, enabling a wide range of editing types such as visual text, quantity, facial expression, etc. Experiments on versatile scenarios validate that our framework achieves flexible and accurate editing, unlocking the potential of the flow transformer for versatile image editing.
title Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.15843