CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboarding

TL;DR

CANVAS is a multi-agent framework designed to improve visual continuity in long-form storytelling by maintaining consistent characters, backgrounds, and scene transitions, outperforming existing methods.

Contribution

It introduces a novel multi-agent planning approach that explicitly enforces visual continuity in narrative storyboarding, including a new benchmark for long-range consistency.

Findings

Background continuity improved by 21.6%

Character consistency improved by 9.6%

Props consistency improved by 7.6%

Abstract

Long-form visual storytelling requires maintaining continuity across shots, including consistent characters, stable environments, and smooth scene transitions. While existing generative models can produce strong individual frames, they fail to preserve such continuity, leading to appearance changes, inconsistent backgrounds, and abrupt scene shifts. We introduce CANVAS (Continuity-Aware Narratives via Visual Agentic Storyboarding), a multi-agent framework that explicitly plans visual continuity in multi-shot narratives. CANVAS enforces coherence through character continuity, persistent background anchors, and location-aware scene planning for smooth transitions within the same setting We evaluate CANVAS on two storyboard generation benchmarks ST-BENCH and ViStoryBench and introduce a new challenging benchmark HardContinuityBench for long-range narrative consistency. CANVAS consistently outperforms the best-performing baseline, improving background continuity by 21.6%, character consistency by 9.6% and props consistency by 7.6%.