Persistent Story World Simulation with Continuous Character Customization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911522032189440 |
|---|---|
| author | Zhang, Jinlu Wang, Qiyun Du, Baoxiang Ji, Jiayi He, Jing Zhang, Rongsheng Lv, Tangjie Sun, Xiaoshuai Ji, Rongrong |
| author_facet | Zhang, Jinlu Wang, Qiyun Du, Baoxiang Ji, Jiayi He, Jing Zhang, Rongsheng Lv, Tangjie Sun, Xiaoshuai Ji, Rongrong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16285 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Persistent Story World Simulation with Continuous Character Customization Zhang, Jinlu Wang, Qiyun Du, Baoxiang Ji, Jiayi He, Jing Zhang, Rongsheng Lv, Tangjie Sun, Xiaoshuai Ji, Rongrong Computer Vision and Pattern Recognition 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. |
| title | Persistent Story World Simulation with Continuous Character Customization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.16285 |