Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.01305 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915767381917696 |
|---|---|
| author | Sarkar, Ayushman Yu, Zhenyu Tang, Wei Chen, Chu Cui, Kangning Idris, Mohd Yamani Idna |
| author_facet | Sarkar, Ayushman Yu, Zhenyu Tang, Wei Chen, Chu Cui, Kangning Idris, Mohd Yamani Idna |
| contents | Large multimodal models have enabled one-click storybook generation, where users provide a short description and receive a multi-page illustrated story. However, the underlying story state, such as characters, world settings, and page-level objects, remains implicit, making edits coarse-grained and often breaking visual consistency. We present StoryState, an agent-based orchestration layer that introduces an explicit and editable story state on top of training-free text-to-image generation. StoryState represents each story as a structured object composed of a character sheet, global settings, and per-page scene constraints, and employs a small set of LLM agents to maintain this state and derive 1Prompt1Story-style prompts for generation and editing. Operating purely through prompts, StoryState is model-agnostic and compatible with diverse generation backends. System-level experiments on multi-page editing tasks show that StoryState enables localized page edits, improves cross-page consistency, and reduces unintended changes, interaction turns, and editing time compared to 1Prompt1Story, while approaching the one-shot consistency of Gemini Storybook. Code is available at https://github.com/YuZhenyuLindy/StoryState |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01305 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | StoryState: Agent-Based State Control for Consistent and Editable Storybooks Sarkar, Ayushman Yu, Zhenyu Tang, Wei Chen, Chu Cui, Kangning Idris, Mohd Yamani Idna Computer Vision and Pattern Recognition Large multimodal models have enabled one-click storybook generation, where users provide a short description and receive a multi-page illustrated story. However, the underlying story state, such as characters, world settings, and page-level objects, remains implicit, making edits coarse-grained and often breaking visual consistency. We present StoryState, an agent-based orchestration layer that introduces an explicit and editable story state on top of training-free text-to-image generation. StoryState represents each story as a structured object composed of a character sheet, global settings, and per-page scene constraints, and employs a small set of LLM agents to maintain this state and derive 1Prompt1Story-style prompts for generation and editing. Operating purely through prompts, StoryState is model-agnostic and compatible with diverse generation backends. System-level experiments on multi-page editing tasks show that StoryState enables localized page edits, improves cross-page consistency, and reduces unintended changes, interaction turns, and editing time compared to 1Prompt1Story, while approaching the one-shot consistency of Gemini Storybook. Code is available at https://github.com/YuZhenyuLindy/StoryState |
| title | StoryState: Agent-Based State Control for Consistent and Editable Storybooks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.01305 |