StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Tao, Ming, Bao, Bing-Kun, Tang, Hao, Wang, Yaowei, Xu, Changsheng
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911832615157760
author Tao, Ming
Bao, Bing-Kun
Tang, Hao
Wang, Yaowei
Xu, Changsheng
author_facet Tao, Ming
Bao, Bing-Kun
Tang, Hao
Wang, Yaowei
Xu, Changsheng
contents Story visualization aims to generate a series of realistic and coherent images based on a storyline. Current models adopt a frame-by-frame architecture by transforming the pre-trained text-to-image model into an auto-regressive manner. Although these models have shown notable progress, there are still three flaws. 1) The unidirectional generation of auto-regressive manner restricts the usability in many scenarios. 2) The additional introduced story history encoders bring an extremely high computational cost. 3) The story visualization and continuation models are trained and inferred independently, which is not user-friendly. To these ends, we propose a bidirectional, unified, and efficient framework, namely StoryImager. The StoryImager enhances the storyboard generative ability inherited from the pre-trained text-to-image model for a bidirectional generation. Specifically, we introduce a Target Frame Masking Strategy to extend and unify different story image generation tasks. Furthermore, we propose a Frame-Story Cross Attention Module that decomposes the cross attention for local fidelity and global coherence. Moreover, we design a Contextual Feature Extractor to extract contextual information from the whole storyline. The extensive experimental results demonstrate the excellent performance of our StoryImager. The code is available at https://github.com/tobran/StoryImager.
format Preprint
id arxiv_https___arxiv_org_abs_2404_05979
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion
Tao, Ming
Bao, Bing-Kun
Tang, Hao
Wang, Yaowei
Xu, Changsheng
Computer Vision and Pattern Recognition
Story visualization aims to generate a series of realistic and coherent images based on a storyline. Current models adopt a frame-by-frame architecture by transforming the pre-trained text-to-image model into an auto-regressive manner. Although these models have shown notable progress, there are still three flaws. 1) The unidirectional generation of auto-regressive manner restricts the usability in many scenarios. 2) The additional introduced story history encoders bring an extremely high computational cost. 3) The story visualization and continuation models are trained and inferred independently, which is not user-friendly. To these ends, we propose a bidirectional, unified, and efficient framework, namely StoryImager. The StoryImager enhances the storyboard generative ability inherited from the pre-trained text-to-image model for a bidirectional generation. Specifically, we introduce a Target Frame Masking Strategy to extend and unify different story image generation tasks. Furthermore, we propose a Frame-Story Cross Attention Module that decomposes the cross attention for local fidelity and global coherence. Moreover, we design a Contextual Feature Extractor to extract contextual information from the whole storyline. The extensive experimental results demonstrate the excellent performance of our StoryImager. The code is available at https://github.com/tobran/StoryImager.
title StoryImager: A Unified and Efficient Framework for Coherent Story Visualization and Completion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.05979