Saved in:
Bibliographic Details
Main Authors: Chen, Shoufa, Xu, Mengmeng, Ren, Jiawei, Cong, Yuren, He, Sen, Xie, Yanping, Sinha, Animesh, Luo, Ping, Xiang, Tao, Perez-Rua, Juan-Manuel
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.04557
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913372468936704
author Chen, Shoufa
Xu, Mengmeng
Ren, Jiawei
Cong, Yuren
He, Sen
Xie, Yanping
Sinha, Animesh
Luo, Ping
Xiang, Tao
Perez-Rua, Juan-Manuel
author_facet Chen, Shoufa
Xu, Mengmeng
Ren, Jiawei
Cong, Yuren
He, Sen
Xie, Yanping
Sinha, Animesh
Luo, Ping
Xiang, Tao
Perez-Rua, Juan-Manuel
contents In this study, we explore Transformer-based diffusion models for image and video generation. Despite the dominance of Transformer architectures in various fields due to their flexibility and scalability, the visual generative domain primarily utilizes CNN-based U-Net architectures, particularly in diffusion-based models. We introduce GenTron, a family of Generative models employing Transformer-based diffusion, to address this gap. Our initial step was to adapt Diffusion Transformers (DiTs) from class to text conditioning, a process involving thorough empirical exploration of the conditioning mechanism. We then scale GenTron from approximately 900M to over 3B parameters, observing significant improvements in visual quality. Furthermore, we extend GenTron to text-to-video generation, incorporating novel motion-free guidance to enhance video quality. In human evaluations against SDXL, GenTron achieves a 51.1% win rate in visual quality (with a 19.8% draw rate), and a 42.3% win rate in text alignment (with a 42.9% draw rate). GenTron also excels in the T2I-CompBench, underscoring its strengths in compositional generation. We believe this work will provide meaningful insights and serve as a valuable reference for future research.
format Preprint
id arxiv_https___arxiv_org_abs_2312_04557
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GenTron: Diffusion Transformers for Image and Video Generation
Chen, Shoufa
Xu, Mengmeng
Ren, Jiawei
Cong, Yuren
He, Sen
Xie, Yanping
Sinha, Animesh
Luo, Ping
Xiang, Tao
Perez-Rua, Juan-Manuel
Computer Vision and Pattern Recognition
In this study, we explore Transformer-based diffusion models for image and video generation. Despite the dominance of Transformer architectures in various fields due to their flexibility and scalability, the visual generative domain primarily utilizes CNN-based U-Net architectures, particularly in diffusion-based models. We introduce GenTron, a family of Generative models employing Transformer-based diffusion, to address this gap. Our initial step was to adapt Diffusion Transformers (DiTs) from class to text conditioning, a process involving thorough empirical exploration of the conditioning mechanism. We then scale GenTron from approximately 900M to over 3B parameters, observing significant improvements in visual quality. Furthermore, we extend GenTron to text-to-video generation, incorporating novel motion-free guidance to enhance video quality. In human evaluations against SDXL, GenTron achieves a 51.1% win rate in visual quality (with a 19.8% draw rate), and a 42.3% win rate in text alignment (with a 42.9% draw rate). GenTron also excels in the T2I-CompBench, underscoring its strengths in compositional generation. We believe this work will provide meaningful insights and serve as a valuable reference for future research.
title GenTron: Diffusion Transformers for Image and Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.04557