paper-with-me

홈 › Papers

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

2026-02-01 · Ayushman Sarkar, Zhenyu Yu, Wei Tang, Chu Chen, Kangning Cui, Mohd Yamani Idna Idris arxiv

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

📄 PDF Abstract BibTeX arXiv:2602.01305

Code (0)

등록된 구현이 없습니다.

Tasks

Text-to-Image Generation

Similar Papers 제목 키워드 기반

EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution

2026-02-20 · Tianfu Wang, Leilei Ding, Ziyang Tao, Yi Zhan 외 arxiv

High-fidelity diagram creation requires the complex orchestration of semantic topology, visual styling, and spatial layout, posing a significant challenge for automated systems. Existing methods also suffer from a repres…

MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines

2026-03-03 · Ryan Po, David Junhao Zhang, Amir Hertz, Gordon Wetzstein 외 arxiv

Video world models have shown immense promise for interactive simulation and entertainment, but current systems still struggle with two important aspects of interactivity: user control over the environment for reproducib…

PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs

2026-08-03 · Haojie Hu, Chenhao Dang, Yaojia Liu, Hengrui Kang 외 hf

Scientific poster construction compresses a long multimodal paper into a readable, editable canvas. Existing systems hide request-level failures by scoring only completed outputs; direct image generation is not element-e…

Image Generation

Generating Editable Head Avatars with 3D Gaussian GANs

2024-12-26 · Guohao Li, Hongyu Yang, Yifang Men, Di Huang 외

Generating animatable and editable 3D head avatars is essential for various applications in computer vision and graphics. Traditional 3D-aware generative adversarial networks (GANs), often using implicit fields like Neur…

3DGSNeRF

Cognitive Agent Compilation for Explicit Problem Solver Modeling

2026-05-07 · Hyeongdon Moon, Carolyn Rosé, John Stamper arxiv

Large language models (LLMs) are widely used for tutoring, feedback generation, and content creation, but their broad pretraining makes them hard to constrain and poor substitutes for controllable learners. Educational s…