Video Generation Beyond a Single Clip
This addresses the limitation of video generation models that produce only short clips, enabling more realistic and varied long videos for applications like entertainment or simulation.
The paper tackles the problem of generating long videos with diverse content and multiple events, proposing a two-stage approach with additional guidance that improves over state-of-the-art by up to 9.5% in objective metrics and is preferred by users more than 80% of the time.
We tackle the long video generation problem, i.e.~generating videos beyond the output length of video generation models. Due to the computation resource constraints, video generation models can only generate video clips that are relatively short compared with the length of real videos. Existing works apply a sliding window approach to generate long videos at inference time, which is often limited to generating recurrent events or homogeneous content. To generate long videos covering diverse content and multiple events, we propose to use additional guidance to control the video generation process. We further present a two-stage approach to the problem, which allows us to utilize existing video generation models to generate high-quality videos within a small time window while modeling the video holistically based on the input guidance. The proposed approach is complementary to existing efforts on video generation, which focus on generating realistic video within a fixed time window. Extensive experiments on challenging real-world videos validate the benefit of the proposed method, which improves over state-of-the-art by up to 9.5% in objective metrics and is preferred by users more than 80% of time.