首页|期刊导航|Computational Visual Media|Text to image generation with bidirectional Multiway Transformers

Text to image generation with bidirectional Multiway Transformers

Hangbo Bao Li Dong Songhao Piao Furu Wei

Computational Visual Media2025，Vol.11Issue(2)：P.405-422,18.

Computational Visual Media2025，Vol.11Issue(2)：P.405-422,18.DOI:10.26599/CVM.2025.9450377

Text to image generation with bidirectional Multiway Transformers

Hangbo Bao ¹Li Dong ²Songhao Piao ¹Furu Wei²

作者信息

1. Department of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China
2. Microsoft Research Asia,Beijing 100080,China
折叠

摘要

关键词

text to image generation/VQ-VAE/Transformer/generative models

分类

信息技术与安全科学

引用本文复制引用

Hangbo Bao,Li Dong,Songhao Piao,Furu Wei..Text to image generation with bidirectional Multiway Transformers[J].Computational Visual Media,2025,11(2):P.405-422,18.

Computational Visual Media

ISSN：2096-0433

访问量0

下载量0

段落导航