DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior

TL;DR

DreamShot is a novel video diffusion-based storyboard synthesis framework that generates coherent, narrative-driven shot sequences with consistent characters and scenes, supporting flexible text and reference inputs.

Contribution

It introduces a controllable multi-shot storyboard generation method leveraging video diffusion priors and a role-conditioning module for character identity consistency.

Findings

Outperforms state-of-the-art models in scene coherence and role consistency.

Supports both text-to-shot and reference-to-shot generation.

Produces visually and semantically coherent story sequences.

Abstract

Storyboard synthesis plays a crucial role in visual storytelling, aiming to generate coherent shot sequences that visually narrate cinematic events with consistent characters, scenes, and transitions. However, existing approaches are mostly adapted from text-to-image diffusion models, which struggle to maintain long-range temporal coherence, consistent character identities, and narrative flow across multiple shots. In this paper, we introduce DreamShot, a video generative model based storyboard framework that fully exploits powerful video diffusion priors for controllable multi-shot synthesis. DreamShot supports both Text-to-Shot and Reference-to-Shot generation, as well as story continuation conditioned on previous frames, enabling flexible and context-aware storyboard generation. By leveraging the spatial-temporal consistency inherent in video generative models, DreamShot produces visually and semantically coherent sequences with improved narrative fidelity and character continuity. Furthermore, DreamShot incorporates a multi-reference role conditioning module that accepts multiple character reference images and enforces identity alignment via a Role-Attention Consistency Loss, explicitly constraining attention between reference and generated roles. Extensive experiments demonstrate that DreamShot achieves superior scene coherence, role consistency, and generation efficiency compared to state-of-the-art text-to-image storyboard models, establishing a new direction toward controllable video model-driven visual storytelling.