SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

Recently video generation has achieved substantial progress with realistic results. Nevertheless, existing AI-generated videos are usually very short clips ("shotlevel") depicting a single scene. To deliver a coherent long video ("story-level"), it is desirable to have creative transition and prediction effects across different clips. This paper presents a short-to-long (S2L) video diffusion model, SEINE, that focuses on generative transition and prediction. The goal is to generate highquality long videos with smooth and creative transitions between scenes and varying lengths of shot-level videos. Specifically, we propose a random-mask video diffusion model to automatically generate transitions based on textual descriptions. By providing the images of different scenes as inputs, combined with textbased control, our model generates transition videos that ensure coherence and visual quality. Furthermore, the model can be readily extended to various tasks such as image-to-video animation and auto-regressive video prediction. To conduct a comprehensive evaluation of this new generative task, we propose three assessing criteria for smooth and creative transition: temporal consistency, semantic similarity, and video-text semantic alignment. Extensive experiments validate the effectiveness of our approach over existing methods for generative transition and prediction, enabling the creation of story-level long videos. Project page: https://vchitect.github.io/SEINE-project/ .