发表机构
UOL; UTHealth Houston; UCAS; Peking University; UTS AAII（利物浦大学; 德克萨斯大学健康科学中心休斯顿分校; 中国科学院大学; 北京大学; 悉尼科技大学澳大利亚人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
DramaAgent提出分层智能体控制框架，通过故事规划、角色条件、场景合成与反思修复，提升长篇视频生成的连贯性与一致性。
AI 中文摘要
最近的扩散模型和自回归模型显著提升了文本到视频的生成能力，然而生成具有一致角色和同步音频的连贯长篇故事视频仍然具有挑战性。现有方法常常在长序列中遭受叙事漂移、角色身份不稳定、跨场景连续性弱以及音视频不匹配的问题。我们提出了DramaAgent，一个分层、智能体式且模型无关的框架，用于长篇文本到视频和音频的生成。DramaAgent并非改进底层视频骨干网络本身，而是引入了一个上层控制层，将生成过程分解为故事规划、持久角色条件、场景级合成以及反思引导的针对性修复。该框架在场景间维护可重用的故事和角色状态，诊断诸如身份漂移、缺失场景语义、时间不连续和跨模态不匹配等故障，并以阶段特定的方式修复有问题的片段。在多个视频生成骨干网络上的实验表明，与直接生成和强基线相比，DramaAgent提高了长时程连贯性、角色一致性、叙事保真度以及场景级音视频一致性。这些结果表明，分层智能体控制是可控长篇视听生成的一个实用方向。代码：此https链接。网站：此https链接。
英文摘要
Recent diffusion and autoregressive models have substantially improved text-to-video generation, yet producing coherent long-form story videos with consistent characters and aligned audio remains challenging. Existing methods often suffer from narrative drift, unstable character identity, weak cross-scene continuity, and audio-visual mismatch over extended sequences. We propose DramaAgent, a hierarchical, agentic, and model-agnostic framework for long-form text-to-video-and-audio generation. Rather than improving the underlying video backbone itself, DramaAgent introduces an upper-level control layer that decomposes generation into story planning, persistent character conditioning, scene-wise synthesis, and reflection-guided targeted repair. The framework maintains reusable story and character states across scenes, diagnoses failures such as identity drift, missing scene semantics, temporal discontinuity, and cross-modal mismatch, and repairs problematic clips in a stage-specific manner. Experiments across multiple video generation backbones show that DramaAgent improves long-horizon coherence, character consistency, narrative fidelity, and scene-level audio-visual consistency over direct generation and strong baselines. These results suggest that hierarchical agentic control is a practical direction for controllable long-form audiovisual generation. Code: https://github.com/AIGeeksGroup/DramaAgent. Website: https://aigeeksgroup.github.io/DramaAgent.
