Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection
Yuhang Ma, Wenting Xu, Chaoyi Zhao, Keqiang Sun, Qinfeng Jin, Xiaoda Yang, Zeng Zhao, Changjie Fan
Abstract
Recent advances in text-to-image diffusion models have spurred significant interest in continuous story image generation. In this paper, we introduce Storynizor, a model capable of generating coherent stories with strong inter-frame character consistency, effective foreground-background separation, and diverse pose variation. The core innovation of Storynizor lies in its key modules: ID-Synchronizer and ID-Injector. The ID-Synchronizer employs an auto-mask self-attention module and a mask perceptual loss across inter-frame images to improve the consistency of character generation, vividly representing their postures and backgrounds. The ID-Injector utilize a Shuffling Reference Strategy (SRS) to integrate ID features into specific locations, enhancing ID-based consistent character generation. Additionally, to facilitate the training of Storynizor, we have curated a novel dataset called StoryDB comprising 100, 000 images. This dataset contains single and multiple-character sets in diverse environments, layouts, and gestures with detailed descriptions. Experimental results indicate that Storynizor demonstrates superior coherent story generation with high-fidelity character consistency, flexible postures, and vivid backgrounds compared to other character-specific methods.
BibTeX
@article{Ma_Xu_Zhao_Sun_Jin_Yang_Zhao_Fan_Hu_2025, title={Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32644}, DOI={10.1609/aaai.v39i6.32644}, abstractNote={Recent advances in text-to-image diffusion models have spurred significant interest in continuous story image generation. In this paper, we introduce Storynizor, a model capable of generating coherent stories with strong inter-frame character consistency, effective foreground-background separation, and diverse pose variation. The core innovation of Storynizor lies in its key modules: ID-Synchronizer and ID-Injector. The ID-Synchronizer employs an auto-mask self-attention module and a mask perceptual loss across inter-frame images to improve the consistency of character generation, vividly representing their postures and backgrounds. The ID-Injector utilize a Shuffling Reference Strategy (SRS) to integrate ID features into specific locations, enhancing ID-based consistent character generation. Additionally, to facilitate the training of Storynizor, we have curated a novel dataset called StoryDB comprising 100, 000 images. This dataset contains single and multiple-character sets in diverse environments, layouts, and gestures with detailed descriptions. Experimental results indicate that Storynizor demonstrates superior coherent story generation with high-fidelity character consistency, flexible postures, and vivid backgrounds compared to other character-specific methods.}, number={6}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Ma, Yuhang and Xu, Wenting and Zhao, Chaoyi and Sun, Keqiang and Jin, Qinfeng and Yang, Xiaoda and Zhao, Zeng and Fan, Changjie and Hu, Zhipeng}, year={2025}, month={Apr.}, pages={6027-6035} }