CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tu, Jiahang, Feng, Qian, Dong, Jiahua, Zhao, Hanbin, Zhang, Chao, Sebe, Nicu, Qian, Hui
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2501.15562