漫画：能动速写喜剧生成

摘要

我们提出了一种全自动人工智能系统，能够制作类似《周六夜现场》等小品节目的短喜剧视频。该系统以角色设定为起点，采用基于真实制片厂职能构建的智能体群体架构，通过迭代竞争、评估与优化机制，确保创意产出的质量与多样性。本研究的核心创新在于引入大语言模型批评家——通过分析YouTube平台喜剧视频语料库，使其与真实观众偏好对齐，实现幽默效果的自动化评估。实验表明，该框架生成的视频质量接近专业制作水准，同时在视频生成领域展现出尖端性能。

English

We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting with character references, the system employs a population of agents loosely based on real production studio roles, structured to optimize the quality and diversity of ideas and outputs through iterative competition, evaluation, and improvement. A key contribution is the introduction of LLM critics aligned with real viewer preferences through the analysis of a corpus of comedy videos on YouTube to automatically evaluate humor. Our experiments show that our framework produces results approaching the quality of professionally produced sketches while demonstrating state-of-the-art performance in video generation.

漫画：能动速写喜剧生成

COMIC: Agentic Sketch Comedy Generation

摘要

Support