# Storybooth: Training-free Multi-Subject Consistency for Improved Visual Storytelling

arXiv: https://arxiv.org/abs/2504.05800 · HTML: https://mlsanity.com/paper/2504.05800/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 28 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Builds on (most cited first, 26 of 26)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://mlsanity.com/paper/2305.14720/) (2023)
- [ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation](https://mlsanity.com/paper/2302.13848/) (2023)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://mlsanity.com/paper/2401.11708/) (2024)
- [Training-Free Consistent Text-to-Image Generation](https://mlsanity.com/paper/2402.03286/) (2024)
- [VidToMe: Video Token Merging for Zero-Shot Video Editing](https://mlsanity.com/paper/2312.10656/) (2023)
- [MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence](https://mlsanity.com/paper/2407.16655/) (2024)
- [Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models](https://mlsanity.com/paper/2306.00973/) (2023)
- [SEED-Story: Multimodal Long Story Generation with Large Language Model](https://mlsanity.com/paper/2407.08683/) (2024)
- [Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation](https://mlsanity.com/paper/2403.16990/) (2024)
- [The Chosen One: Consistent Characters in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2311.10093/) (2023)
- [Mora: Enabling Generalist Video Generation via A Multi-Agent Framework](https://mlsanity.com/paper/2403.13248/) (2024)
- [Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis](https://mlsanity.com/paper/2312.13834/) (2023)
- [Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Models](https://mlsanity.com/paper/2302.03900/) (2023)
- [Improved Visual Story Generation with Adaptive Context Modeling](https://mlsanity.com/paper/2305.16811/) (2023)

## Built on by (most cited first, 4 of 4)

- [Lay2Story: Extending Diffusion Transformers for Layout-Togglable Story Generation](https://mlsanity.com/paper/2508.08949/) (2025)
- [EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation](https://mlsanity.com/paper/2605.15199/) (2026)
- [ViStoryBench: Comprehensive Benchmark Suite for Story Visualization](https://mlsanity.com/paper/2505.24862/) (2025)
- [LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization](https://mlsanity.com/paper/2603.28082/) (2026)

## Abstract (arXiv)

Training-free consistent text-to-image generation depicting the same subjects across different images is a topic of widespread recent interest. Existing works in this direction predominantly rely on cross-frame self-attention; which improves subject-consistency by allowing tokens in each frame to pay attention to tokens in other frames during self-attention computation. While useful for single subjects, we find that it struggles when scaling to multiple characters. In this work, we first analyze the reason for these limitations. Our exploration reveals that the primary-issue stems from self-attention-leakage, which is exacerbated when trying to ensure consistency across multiple-characters. This happens when tokens from one subject pay attention to other characters, causing them to appear like each other (e.g., a dog appearing like a duck). Motivated by these findings, we propose StoryBooth: a training-free approach for improving multi-character consistency. In particular, we first leverage multi-modal chain-of-thought reasoning and region-based generation to apriori localize the different subjects across the desired story outputs. The final outputs are then generated using a modified diffusion model which consists of two novel layers: 1) a bounded cross-frame self-attention layer for reducing inter-character attention leakage, and 2) token-merging layer for improving consistency of fine-grain subject details. Through both qualitative and quantitative results we find that the proposed approach surpasses prior state-of-the-art, exhibiting improved consistency across both multiple-characters and fine-grain subject details.