# CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboarding

arXiv: https://arxiv.org/abs/2604.13452 · HTML: https://mlsanity.com/paper/2604.13452/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 21 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 18 of 18)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [WorldMem: Long-term Consistent World Simulation with Memory](https://mlsanity.com/paper/2504.12369/) (2025)
- [Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models](https://mlsanity.com/paper/2306.00973/) (2023)
- [SEED-Story: Multimodal Long Story Generation with Large Language Model](https://mlsanity.com/paper/2407.08683/) (2024)
- [HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives](https://mlsanity.com/paper/2510.20822/) (2025)
- [StoryMem: Multi-shot Long Video Storytelling with Memory](https://mlsanity.com/paper/2512.19539/) (2025)
- [OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory](https://mlsanity.com/paper/2512.07802/) (2025)
- [FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation](https://mlsanity.com/paper/2506.18899/) (2025)
- [VideoMemory: Toward Consistent Video Generation via Memory Integration](https://mlsanity.com/paper/2601.03655/) (2026)
- [STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative](https://mlsanity.com/paper/2512.12372/) (2025)
- [AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation](https://mlsanity.com/paper/2406.01388/) (2024)
- [TheaterGen: Character Management with LLM for Consistent Multi-turn Image Generation](https://mlsanity.com/paper/2404.18919/) (2024)
- [Story2Board: A Training-Free Approach for Expressive Storyboard Generation](https://mlsanity.com/paper/2508.09983/) (2025)
- [Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization](https://mlsanity.com/paper/2410.06244/) (2024)
- [Lost in Stories: Consistency Bugs in Long Story Generation by LLMs](https://mlsanity.com/paper/2603.05890/) (2026)
- [The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systems](https://mlsanity.com/paper/2510.24831/) (2025)
- [Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning](https://mlsanity.com/paper/2603.06688/) (2026)

## Built on by (most cited first, 3 of 3)

- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [PACE: Precise AI Cinematic Expression](https://mlsanity.com/paper/2609.19853/) (2026)
- [Memory-Guided B-Roll Generation from User Video Collections](https://mlsanity.com/paper/2610.01884/) (2026)

## Abstract (arXiv)

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%.