MACE: mass concept erasure in diffusion models
The rapid expansion of large-scale text-to-image diffusion models has raised growing concerns regarding their potential misuse in creating harmful or misleading content. In this paper, we introduce MACE, a finetuning framework for the task of MAss Concept Erasure. This task aims to prevent models fr...
Saved in:
Main Authors: | Lu, Shilin, Wang, Zilan, Li, Leyang, Liu, Yanzhu, Kong, Adams Wai Kin |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/180560 https://openaccess.thecvf.com/CVPR2024?day=all |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
TF-ICON: diffusion-based training-free cross-domain image composition
by: Lu, Shilin, et al.
Published: (2023) -
Coherent visual story generation using diffusion models
by: Jiang, Jiaxi
Published: (2024) -
Exemplar based image colourization using diffusion models
by: Rahul, George
Published: (2024) -
From noise to information: discriminative tasks based on randomized neural networks and generative tasks based on diffusion models
by: Hu, Minghui
Published: (2024) -
A comparative review of latent spaces in latent diffusion model with other generative models
by: Sun Jiaxin
Published: (2024)