OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

TL;DR

This paper introduces OpenVid-1M, a high-quality, large-scale dataset for text-to-video generation, along with a novel Multi-modal Video Diffusion Transformer that effectively utilizes textual and visual information.

Contribution

The paper presents a new high-quality dataset for T2V generation and a multi-modal transformer model that better exploits semantic textual information.

Findings

OpenVid-1M outperforms previous datasets in T2V tasks.

MVDiT effectively captures semantic and structural information.

High-definition videos generated using OpenVidHD-0.4M demonstrate improved quality.

Abstract

Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset. The previous popular video datasets, e.g. WebVid-10M and Panda-70M, are either with low quality or too large for most research institutions. Therefore, it is challenging but crucial to collect a precise high-quality text-video pairs for T2V generation. 2) Ignoring to fully utilize textual information. Recent T2V methods have focused on vision transformers, using a simple cross attention module for video generation, which falls short of thoroughly extracting semantic information from text prompt. To address these issues, we introduce OpenVid-1M, a precise high-quality dataset with expressive captions. This open-scenario dataset contains over 1 million text-video pairs, facilitating research on T2V generation. Furthermore, we curate 433K 1080p videos from OpenVid-1M to create OpenVidHD-0.4M, advancing high-definition video generation. Additionally, we propose a novel Multi-modal Video Diffusion Transformer (MVDiT) capable of mining both structure information from visual tokens and semantic information from text tokens. Extensive experiments and ablation studies verify the superiority of OpenVid-1M over previous datasets and the effectiveness of our MVDiT.