Persistent Story World Simulation with Continuous Character Customization

TL;DR

EverTale is a novel story world simulation framework that enables continuous character customization and high-quality multi-character story visualization through integrated modules and quality control mechanisms.

Contribution

The paper introduces EverTale, a comprehensive story visualization system with a unified character integrator, a quality gate, and a region-focus sampling strategy, advancing multi-character storytelling.

Findings

Outperforms existing methods in story visualization quality

Ensures consistent character fidelity during story progression

Efficiently manages multi-character interactions and layout conflicts

Abstract

Story visualization has gained increasing attention in computer vision. However, current methods often fail to achieve a synergy between accurate character customization, semantic alignment, and continuous integration of new identities. To tackle this challenge, in this paper we present EverTale, a story world simulator for continuous story character customization. We first propose an All-in-One-World Character Integrator to achieve continuous character adaptation within unified LoRA module, eliminating the need for per-character optimization modules of previous methods. Then, we incorporate a Character Quality Gate via MLLM-as-Judge to ensure the fidelity of each character adaptation process through chain-of-thought reasoning, determining whether the model can proceed to the next character or require additional training on the current one. We also introduce a Character-Aware Region-Focus Sampling strategy to address the identity degradation and layout conflicts in existing multi-character visual storytelling, ensuring natural multi-character generation by harmonizing local character-specific details with global scene context with higher efficiency. Experimental results show that our EverTale achieves superior performance against a wider range of compared methods on both single- and multi-character story visualization. Codes will be available.