CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers

29 May 2022  ·  Wenyi Hong, Ming Ding, Wendi Zheng, Xinghan Liu, Jie Tang ·

Large-scale pretrained transformers have created milestones in text (GPT-3) and text-to-image (DALL-E and CogView) generation. Its application to video generation is still facing many challenges: The potential huge computation cost makes the training from scratch unaffordable; The scarcity and weak relevance of text-video datasets hinder the model understanding complex movement semantics. In this work, we present 9B-parameter transformer CogVideo, trained by inheriting a pretrained text-to-image model, CogView2. We also propose multi-frame-rate hierarchical training strategy to better align text and video clips. As (probably) the first open-source large-scale pretrained text-to-video model, CogVideo outperforms all publicly available models at a large margin in machine and human evaluations.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Video Generation UCF-101 CogVideo (128x128, class-conditional) Inception Score 51.11 # 12
FVD16 305 # 10