1. DreamFactory: Pioneering Multi-Scene Long Video Generation with a Multi-Agent Framework
- Author
-
Xie, Zhifei, Tang, Daniel, Tan, Dingwei, Klein, Jacques, Bissyand, Tegawend F., and Ezzini, Saad
- Subjects
Computer Science - Artificial Intelligence ,Computer Science - Computation and Language ,Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Software Engineering ,TsingHua University - Abstract
Current video generation models excel at creating short, realistic clips, but struggle with longer, multi-scene videos. We introduce \texttt{DreamFactory}, an LLM-based framework that tackles this challenge. \texttt{DreamFactory} leverages multi-agent collaboration principles and a Key Frames Iteration Design Method to ensure consistency and style across long videos. It utilizes Chain of Thought (COT) to address uncertainties inherent in large language models. \texttt{DreamFactory} generates long, stylistically coherent, and complex videos. Evaluating these long-form videos presents a challenge. We propose novel metrics such as Cross-Scene Face Distance Score and Cross-Scene Style Consistency Score. To further research in this area, we contribute the Multi-Scene Videos Dataset containing over 150 human-rated videos., Comment: 13 pages, 8 figures
- Published
- 2024