Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xie, Qingsong, Zhang, Zhao, Huang, Zhe, Zhang, Yanhao, Lu, Haonan, Yang, Zhenyu
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2503.08377