# StoryState: Agent-Based State Control for Consistent and Editable Storybooks

Source: [StoryState: Agent-Based State Control for Consistent and Editable Storybooks](<https://www.sota2.com/research/paper/69818145a8b01e76cc8e2449>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-04T05:00:15.039Z

Authors: Ayushman Sarkar, Zhenyu Yu, Wei Tang, Chu Chen, Kangning Cui, Mohd Yamani Idna Idris

Published: 2026-02-01T16:06:10.000Z

## Abstract

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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Storybook Generation Evaluation on User Study Storybook Generation 1.0 (test)](<https://www.sota2.com/research/sota/storybook-generation-evaluation-on-user-study-storybook-generation-1-0-test.md>): Storybook Generation Evaluation; User Study Storybook Generation 1.0 (test); Consistency: 36.

- [Story Editing on ConsiStory+ protocol](<https://www.sota2.com/research/sota/story-editing-on-consistory-plus-protocol.md>): Story Editing; ConsiStory+ protocol; Consistency: 83.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.01305>)

[PDF](<https://arxiv.org/pdf/2602.01305.pdf>)