Search papers, labs, and topics across Lattice.
The paper introduces CANVAS, a multi-agent framework for generating coherent visual storyboards by explicitly planning for visual continuity across multiple shots. CANVAS uses separate agents to enforce character consistency, maintain persistent background anchors, and plan location-aware scene transitions. Experiments on three benchmarks, including a new HardContinuityBench, demonstrate that CANVAS significantly improves background, character, and prop consistency compared to existing generative models.
Generating consistent visual narratives is now possible: CANVAS outperforms existing methods by explicitly planning character, background, and scene continuity across multiple shots.
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%.