VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 7310 - 7320
• Main Authors: Chen, Haoxin, Zhang, Yong, Cun, Xiaodong, Xia, Menghan, Wang, Xintao, Weng, Chao, Shan, Ying
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.06.2024
• Subjects: Analytical models; Computer vision; Couplings; Degradation; Diffusion models; Noise; Training

Text-to-video generation aims to produce a video based on a given prompt. Recently, several commercial video models have been able to generate plausible videos with mini-mal noise, excellent details, and high aesthetic scores. However, these models rely on large-scale, well-filtered, high-quality vi...