Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation

TL;DR

This paper introduces Animate-A-Story, a framework that synthesizes coherent storytelling videos by retrieving relevant video clips and customizing their appearances using text prompts, simplifying the video creation process.

Contribution

It presents a novel two-module system combining retrieval and guided synthesis for controllable, plot-aligned video generation from existing clips.

Findings

Outperforms existing baselines in coherence and customization.

Enables flexible control over characters and structure.

Produces visually consistent storytelling videos.

Abstract

Generating videos for visual storytelling can be a tedious and complex process that typically requires either live-action filming or graphics animation rendering. To bypass these challenges, our key idea is to utilize the abundance of existing video clips and synthesize a coherent storytelling video by customizing their appearances. We achieve this by developing a framework comprised of two functional modules: (i) Motion Structure Retrieval, which provides video candidates with desired scene or motion context described by query texts, and (ii) Structure-Guided Text-to-Video Synthesis, which generates plot-aligned videos under the guidance of motion structure and text prompts. For the first module, we leverage an off-the-shelf video retrieval system and extract video depths as motion structure. For the second module, we propose a controllable video generation model that offers flexible controls over structure and characters. The videos are synthesized by following the structural guidance and appearance instruction. To ensure visual consistency across clips, we propose an effective concept personalization approach, which allows the specification of the desired character identities through text prompts. Extensive experiments demonstrate that our approach exhibits significant advantages over various existing baselines.