STORYANCHORS: Generating Consistent Multi-Scene Story Frames for Long-Form Narratives

TL;DR

StoryAnchors is a novel framework for generating multi-scene story frames with high temporal consistency, character continuity, and scene diversity, enabling more coherent and rich long-form narratives.

Contribution

It introduces a unified bidirectional story generator with novel training techniques for improved narrative coherence and scene diversity in story frame generation.

Findings

Outperforms existing models in consistency and narrative coherence.

Supports manual editing and expansion of story frames.

Achieves comparable performance to GPT-4o in story richness.

Abstract

This paper introduces StoryAnchors, a unified framework for generating high-quality, multi-scene story frames with strong temporal consistency. The framework employs a bidirectional story generator that integrates both past and future contexts to ensure temporal consistency, character continuity, and smooth scene transitions throughout the narrative. Specific conditions are introduced to distinguish story frame generation from standard video synthesis, facilitating greater scene diversity and enhancing narrative richness. To further improve generation quality, StoryAnchors integrates Multi-Event Story Frame Labeling and Progressive Story Frame Training, enabling the model to capture both overarching narrative flow and event-level dynamics. This approach supports the creation of editable and expandable story frames, allowing for manual modifications and the generation of longer, more complex sequences. Extensive experiments show that StoryAnchors outperforms existing open-source models in key areas such as consistency, narrative coherence, and scene diversity. Its performance in narrative consistency and story richness is also on par with GPT-4o. Ultimately, StoryAnchors pushes the boundaries of story-driven frame generation, offering a scalable, flexible, and highly editable foundation for future research.