IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generation

TL;DR

IdentityStory introduces a novel framework for human-centric story generation that maintains consistent character identities across multiple images, improving face consistency and enabling complex multi-character stories.

Contribution

The paper proposes a new method combining iterative identity discovery and re-denoising identity injection to enhance human face consistency in story generation.

Findings

Outperforms existing methods on ConsiStory-Human benchmark

Achieves superior face consistency across images

Supports multi-character story generation

Abstract

Recent visual generative models enable story generation with consistent characters from text, but human-centric story generation faces additional challenges, such as maintaining detailed and diverse human face consistency and coordinating multiple characters across different images. This paper presents IdentityStory, a framework for human-centric story generation that ensures consistent character identity across multiple sequential images. By taming identity-preserving generators, the framework features two key components: Iterative Identity Discovery, which extracts cohesive character identities, and Re-denoising Identity Injection, which re-denoises images to inject identities while preserving desired context. Experiments on the ConsiStory-Human benchmark demonstrate that IdentityStory outperforms existing methods, particularly in face consistency, and supports multi-character combinations. The framework also shows strong potential for applications such as infinite-length story generation and dynamic character composition.