Persistent Story World Simulation with Continuous Character Customization

2026-03-17

AI Summary

Existing story visualization methods struggle to simultaneously achieve precise character customization, semantic consistency, and continual integration of new characters. To address this challenge, this work proposes EverTale, a story world simulator that leverages a unified LoRA module for efficient continual character adaptation. EverTale introduces three core mechanisms: an integrated character integrator, a chain-of-thought reasoning quality gate based on multimodal large language models (MLLMs), and a character-aware region-focused sampling strategy. The proposed approach significantly outperforms current methods in both single- and multi-character story generation tasks, effectively mitigating identity degradation and layout conflicts while enabling high-quality, coherent, and scalable story visualization.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Diffusion Models for Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

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.

Problem

• story visualization
• character customization
• identity integration
• multi-character generation
• semantic alignment

Innovation

• continuous character customization
• LoRA-based integration
• MLLM-as-Judge
• multi-character visual storytelling
• region-focus sampling