OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory

TL;DR

OneStory introduces a novel approach for multi-shot video generation that models long-range context using global memory and adaptive conditioning, significantly improving narrative coherence in complex storytelling scenarios.

Contribution

The paper presents a new framework that reformulates multi-shot video generation as a next-shot prediction task, utilizing pretrained models and novel modules for better long-range context modeling.

Findings

Achieves state-of-the-art coherence in multi-shot videos

Effective in both text- and image-conditioned storytelling

Supports controllable, long-form video generation

Abstract

Storytelling in real-world videos often unfolds through multiple shots -- discontinuous yet semantically connected clips that together convey a coherent narrative. However, existing multi-shot video generation (MSV) methods struggle to effectively model long-range cross-shot context, as they rely on limited temporal windows or single keyframe conditioning, leading to degraded performance under complex narratives. In this work, we propose OneStory, enabling global yet compact cross-shot context modeling for consistent and scalable narrative generation. OneStory reformulates MSV as a next-shot generation task, enabling autoregressive shot synthesis while leveraging pretrained image-to-video (I2V) models for strong visual conditioning. We introduce two key modules: a Frame Selection module that constructs a semantically-relevant global memory based on informative frames from prior shots, and an Adaptive Conditioner that performs importance-guided patchification to generate compact context for direct conditioning. We further curate a high-quality multi-shot dataset with referential captions to mirror real-world storytelling patterns, and design effective training strategies under the next-shot paradigm. Finetuned from a pretrained I2V model on our curated 60K dataset, OneStory achieves state-of-the-art narrative coherence across diverse and complex scenes in both text- and image-conditioned settings, enabling controllable and immersive long-form video storytelling.