Grid Diffusion Models for Text-to-Video Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Taegyeong, Kwon, Soyeong, Kim, Taehwan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912170956029952
author Lee, Taegyeong
Kwon, Soyeong
Kim, Taehwan
author_facet Lee, Taegyeong
Kwon, Soyeong
Kim, Taehwan
contents Recent advances in the diffusion models have significantly improved text-to-image generation. However, generating videos from text is a more challenging task than generating images from text, due to the much larger dataset and higher computational cost required. Most existing video generation methods use either a 3D U-Net architecture that considers the temporal dimension or autoregressive generation. These methods require large datasets and are limited in terms of computational costs compared to text-to-image generation. To tackle these challenges, we propose a simple but effective novel grid diffusion for text-to-video generation without temporal dimension in architecture and a large text-video paired dataset. We can generate a high-quality video using a fixed amount of GPU memory regardless of the number of frames by representing the video as a grid image. Additionally, since our method reduces the dimensions of the video to the dimensions of the image, various image-based methods can be applied to videos, such as text-guided video manipulation from image manipulation. Our proposed method outperforms the existing methods in both quantitative and qualitative evaluations, demonstrating the suitability of our model for real-world video generation.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00234
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Grid Diffusion Models for Text-to-Video Generation
Lee, Taegyeong
Kwon, Soyeong
Kim, Taehwan
Computer Vision and Pattern Recognition
Recent advances in the diffusion models have significantly improved text-to-image generation. However, generating videos from text is a more challenging task than generating images from text, due to the much larger dataset and higher computational cost required. Most existing video generation methods use either a 3D U-Net architecture that considers the temporal dimension or autoregressive generation. These methods require large datasets and are limited in terms of computational costs compared to text-to-image generation. To tackle these challenges, we propose a simple but effective novel grid diffusion for text-to-video generation without temporal dimension in architecture and a large text-video paired dataset. We can generate a high-quality video using a fixed amount of GPU memory regardless of the number of frames by representing the video as a grid image. Additionally, since our method reduces the dimensions of the video to the dimensions of the image, various image-based methods can be applied to videos, such as text-guided video manipulation from image manipulation. Our proposed method outperforms the existing methods in both quantitative and qualitative evaluations, demonstrating the suitability of our model for real-world video generation.
title Grid Diffusion Models for Text-to-Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.00234