IdentityStory: Human-Centric Story Generation with Consistent Characters
Analysis
This paper addresses the challenge of generating stories with consistent human characters in visual generative models. It introduces IdentityStory, a framework designed to maintain detailed face consistency and coordinate multiple characters across sequential images. The key contributions are Iterative Identity Discovery and Re-denoising Identity Injection, which aim to improve character identity preservation. The paper's significance lies in its potential to enhance the realism and coherence of human-centric story generation, particularly in applications like infinite-length stories and dynamic character composition.
Key Takeaways
- •Proposes IdentityStory, a framework for human-centric story generation.
- •Employs Iterative Identity Discovery and Re-denoising Identity Injection for character consistency.
- •Demonstrates superior performance in face consistency and multi-character scenarios.
- •Highlights potential for infinite-length story generation and dynamic character composition.
Reference
“IdentityStory outperforms existing methods, particularly in face consistency, and supports multi-character combinations.”