Can I read STIV: Scalable Text and Image Conditioned Video Generation on EtoBox?

STIV: Scalable Text and Image Conditioned Video Generation by Lin, Zongyu; Liu, Wei; Chen, Chen; Lu, Jiasen; Hu, Wenze; Fu, Tsu-Jui; Allardice, Jesse; Lai, Zhengfeng; Song, Liangchen; Zhang, Bowen; Chen, Cha; Fei, Yiran; Jiang, Yifan; Li, Lezhi; Sun, Yizhou; Chang, Kai-Wei; Yang, Yinfei is a scholarly article available to read on EtoBox.

What is STIV: Scalable Text and Image Conditioned Video Generation about?

The field of video generation has made remarkable advancements, yet there remains a pressing need for a clear, systematic recipe that can guide the development of robust and scalable models. In this work, we present a comprehensive study that systematically explores the interplay of model architectures, training recipes, and data curation strategies, culminating in a simple and scalable text-image-conditioned video generation method, named STIV. Our framework integrates image condition into a Diffusion Transformer (DiT) through frame replacement, while incorporating text conditioning via a joint image-text conditional classifier-free guidance. This design enables STIV to perform both text-to-video (T2V) and text-image-to-video (TI2V) tasks simultaneously. Additionally, STIV can be easily extended to various applications, such as video prediction, frame interpolation, multi-view generation, and long video generation, etc. With comprehensive ablation studies on T2I, T2V, and TI2V, STIV demonstrate strong performance, despite its simple design. An 8.7B model with 512 resolution achieves 83.1 on VBench T2V, surpassing both leading open and closed-source models like CogVideoX-5B, Pika,

Author

Lin, Zongyu; Liu, Wei; Chen, Chen; Lu, Jiasen; Hu, Wenze; Fu, Tsu-Jui; Allardice, Jesse; Lai, Zhengfeng; Song, Liangchen; Zhang, Bowen; Chen, Cha; Fei, Yiran; Jiang, Yifan; Li, Lezhi; Sun, Yizhou; Chang, Kai-Wei; Yang, Yinfei

Published

2024

Language

EN