自动化生成连贯的长篇视频

视频扩散领域的最新进展表明，这类模型能够在数秒内生成逼真的场景，实现出色的高保真内容生成。然而，尽管扩散模型可以生成高保真视频片段，将其转变为连贯的长篇叙事引擎仍然颇具挑战。

大多数现有的智能体流水线通过串联模块来自动化这一过程，但由于各模块采用彼此独立、人工设计的提示词，因而容易遭遇语义漂移（例如不同镜头间角色服装或场景出现细微变化）以及级联故障（例如上游资产中的瑕疵破坏下游视频合成）。由于早期错误会不断传播并破坏长时程一致性，这一过程往往需要大量人工干预。从结构上看，这反映了经典的信用分配问题：最终出现的故障很难追溯到具体的提示词。此外，现有方法还存在特征漂移问题，即实体和环境会在无意中逐步改变；或出现内容坍塌，即叙事无法有意义地持续推进。

今天，我们介绍关于 AI 视频联合导演（AI video co-director）的研究：这是一个统一的多智能体框架，能够显式规划多镜头叙事中的视觉连续性。该框架构建于 Gemini 和 Veo 之上的编排层，原生继承了诸如 SynthID 水印等安全机制。我们将长篇内容生成视为全局优化和世界状态追踪问题，并据此开发了一套框架——将在 COLM 2026 发表的 Co-Director、将在 EMNLP 2026 发表的 CANVAS、A²RD 和 VQQA——将人类高层次的创意规格转化为实际执行，通过自动化多模型提示、镜头串联和闭环视觉优化等重复性编排任务来实现这一目标。

我们将这些框架设计为能够快速响应的创意伙伴，抽象掉维持视觉连续性所带来的负担，让用户能够专注于叙事艺术。这一架构通过将质量建模为测试时目标，把创意合成与一致性维护解耦。在全面评估中，我们的框架在多镜头叙事一致性和角色持续性方面取得了显著提升，能够成功生成分钟级视频，同时缓解视觉漂移和流水线错误传播。

Recent advancements in video diffusion demonstrate remarkable high-fidelity generation with models that can render realistic scenes in seconds. However, while diffusion models generate high-fidelity video clips, transforming them into coherent long storytelling engines remains challenging.

Most existing agentic pipelines automate this process via chained modules but suffer from semantic drift (subtle shifts in character attire or scenery across shots) and cascading failures (e.g., an upstream asset artifact corrupting downstream video synthesis) due to independent, handcrafted prompting. Because early errors propagate and break long-horizon consistency, the process often requires exhaustive manual intervention. From a structural perspective, this reflects the classical credit assignment problem, as terminal failures are difficult to trace back to specific prompts. Furthermore, existing methods suffer from feature drift , where entities and environments gradually change unintentionally, or content collapse , where narratives fail to progress meaningfully.

Today, we introduce our research on an AI video co-director, a unified, multi-agent framework that explicitly plans visual continuity in multi-shot narratives. Built as an orchestration layer on top of Gemini and Veo, this framework natively inherits safety mechanisms like SynthID watermarking. By treating long-form generation as a global optimization and world-state tracking problem, we have developed a suite of frameworks — Co-Director (to appear at COLM 2026), CANVAS (to appear at EMNLP 2026), A²RD, and VQQA —that translate high-level human creative specification into execution by automating repetitive orchestration tasks, from multi-model prompting and shot chaining to closed-loop visual refinement.

We designed these frameworks to act as responsive creative partners that abstract away the burdens of maintaining visual continuity, freeing users to concentrate on the art of storytelling. This architecture decouples creative synthesis from consistency by modeling quality as a test-time objective. Across comprehensive evaluations, our framework demonstrates substantial gains in multi-shot narrative consistency and character persistence, successfully generating minutes-long videos while mitigating visual drift and pipeline error propagation.