Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection

TL;DR

Storynizor is a novel model that generates coherent stories with consistent characters, diverse poses, and vivid backgrounds by employing inter-frame synchronization and ID injection techniques, supported by a new large-scale dataset.

Contribution

The paper introduces Storynizor, a new model with ID-Synchronizer and ID-Injector modules, and a large dataset, enabling high-quality, consistent story image generation.

Findings

Superior character consistency and background fidelity.

Effective pose variation and diversity.

Outperforms existing methods in coherence and quality.

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.