Story2Board: A Training-Free Approach for Expressive Storyboard Generation

TL;DR

Story2Board is a training-free framework that enhances visual storytelling by generating coherent, diverse, and engaging storyboards from natural language, using novel consistency mechanisms without model fine-tuning.

Contribution

It introduces a training-free, lightweight consistency framework with novel attention mechanisms for improved storyboard coherence and diversity, along with a new benchmark and metrics for evaluation.

Findings

Produces more coherent and diverse storyboards than baselines.

Enhances visual storytelling without model fine-tuning.

Outperforms existing methods in user studies and quantitative metrics.

Abstract

We present Story2Board, a training-free framework for expressive storyboard generation from natural language. Existing methods narrowly focus on subject identity, overlooking key aspects of visual storytelling such as spatial composition, background evolution, and narrative pacing. To address this, we introduce a lightweight consistency framework composed of two components: Latent Panel Anchoring, which preserves a shared character reference across panels, and Reciprocal Attention Value Mixing, which softly blends visual features between token pairs with strong reciprocal attention. Together, these mechanisms enhance coherence without architectural changes or fine-tuning, enabling state-of-the-art diffusion models to generate visually diverse yet consistent storyboards. To structure generation, we use an off-the-shelf language model to convert free-form stories into grounded panel-level prompts. To evaluate, we propose the Rich Storyboard Benchmark, a suite of open-domain narratives designed to assess layout diversity and background-grounded storytelling, in addition to consistency. We also introduce a new Scene Diversity metric that quantifies spatial and pose variation across storyboards. Our qualitative and quantitative results, as well as a user study, show that Story2Board produces more dynamic, coherent, and narratively engaging storyboards than existing baselines.