Co-Director: Agentic Generative Video Storytelling

• URL: http://arxiv.org/abs/2604.24842v1
• Date: Mon, 27 Apr 2026 18:00:00 GMT
• Title: Co-Director: Agentic Generative Video Storytelling
• Abstract summary: Co-Director is a hierarchical multi-agent framework formalizing video storytelling as a global optimization problem.<n>We introduce hierarchical parameterization: a multi-armed bandit globally identifies promising creative directions, while a local multimodal self-refinement loop mitigates identity drift.<n>Experiments demonstrate that Co-Director significantly outperforms state-of-the-art baselines.
• Score: 26.442992342618496
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While diffusion models generate high-fidelity video clips, transforming them into coherent storytelling engines remains challenging. Current agentic pipelines automate this via chained modules but suffer from semantic drift and cascading failures due to independent, handcrafted prompting. We present Co-Director, a hierarchical multi-agent framework formalizing video storytelling as a global optimization problem. To ensure semantic coherence, we introduce hierarchical parameterization: a multi-armed bandit globally identifies promising creative directions, while a local multimodal self-refinement loop mitigates identity drift and ensures sequence-level consistency. This balances the exploration of novel narrative strategies with the exploitation of effective creative configurations. For evaluation, we introduce GenAD-Bench, a 400-scenario dataset of fictional products for personalized advertising. Experiments demonstrate that Co-Director significantly outperforms state-of-the-art baselines, offering a principled approach that seamlessly generalizes to broader cinematic narratives. Project Page: https://co-director-agent.github.io/

Related papers

• Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation [53.27387848819395]
  Long-form narrative-to-film generation requires shot-level controllability and cross-clip consistency.<n>We introduce a structured orchestration layer for film-oriented script-to-video generation.
  arXiv  Detail & Related papers  (2026-09-07T16:33:14Z)
• ViMax: Agentic Video Generation [55.546794487716646]
  Long-form video generation requires systematic narrative planning and visual consistency.<n>Our framework employs a hierarchical narrative engine with retrieval-augmented generation for global story coherence.<n>VLM-guided agents continuously monitor and refine both narrative coherence and visual fidelity.
  arXiv  Detail & Related papers  (2026-06-02T12:55:41Z)
• SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control [14.692728579474169]
  We propose SmartDirector, a framework that enhances the narrative capacity of video generation models.<n>SmartDirector supports flexible generation scenarios including single-shot generation, multi-shot narrative synthesis, and video extension.
  arXiv  Detail & Related papers  (2026-05-27T03:16:09Z)
• OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space [66.35177674346156]
  OccDirector generates 4D occupancy dynamics conditioned solely on natural language.<n>OccDirector achieves state-of-the-art generation quality and unprecedented instruction-following capabilities.
  arXiv  Detail & Related papers  (2026-04-24T05:30:35Z)
• The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation [95.18045807704284]
  We introduce an end-to-end agentic framework for dialogue-to-cinematic-video generation.<n> ScripterAgent is trained to translate coarse dialogue into a fine-grained, executable cinematic script.<n>Our framework significantly improves script faithfulness and temporal fidelity across all tested video models.
  arXiv  Detail & Related papers  (2026-01-25T08:10:28Z)
• CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation [9.91271343855315]
  CoAgent is a framework for coherent video generation that formulates the process as a plan-synthesize-verify pipeline.<n>A Storyboard Planner decomposes the input into structured shot-level plans with explicit entities, spatial relations, and temporal cues.<n>A Global Context Manager maintains entity-level memory to preserve appearance and identity consistency across shots.<n>A pacing-aware editor refines temporal rhythm and transitions to match the desired narrative flow.
  arXiv  Detail & Related papers  (2025-12-27T09:38:34Z)
• CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine [4.644735042881366]
  CreAgentive addresses four key limitations of contemporary large language models in writing stories, drama and other categories of creatives.<n>At its core, CreAgentive employs a Story Prototype, which is a genre-agnostic, knowledge graph-based narrative representation.<n>In extensive experiments, CreAgentive generates thousands of chapters with stable quality and low cost.
  arXiv  Detail & Related papers  (2025-09-30T16:12:32Z)
• AniMaker: Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation [50.63646953706144]
  We introduce AniMaker, a framework enabling efficient multi-candidate clip generation and storytelling-aware clip selection.<n>AniMaker achieves superior quality as measured by popular metrics including VBench and our proposed AniEval framework.
  arXiv  Detail & Related papers  (2025-06-12T10:06:21Z)
• StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration [88.94832383850533]
  We propose a multi-agent framework designed for Customized Storytelling Video Generation (CSVG) StoryAgent decomposes CSVG into distinct subtasks assigned to specialized agents, mirroring the professional production process. Specifically, we introduce a customized Image-to-Video (I2V) method, LoRA-BE, to enhance intra-shot temporal consistency. Our contributions include the introduction of StoryAgent, a versatile framework for video generation tasks, and novel techniques for preserving protagonist consistency.
  arXiv  Detail & Related papers  (2024-11-07T18:00:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.