Self-Discovering Interpretable Diffusion Latent Directions for
Responsible Text-to-Image Generation

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation

28 November 2023

Philip H. S. Torr

Jindong Gu

Papers citing "Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation"

5 / 5 papers shown

Title
ShieldGemma 2: Robust and Tractable Image Content Moderation Wenjun Zeng D. Kurniawan Ryan Mullins Yuchi Liu Tamoghna Saha ... Mani Malek Hamid Palangi Joon Baek Rick Pereira Karthik Narasimhan AI4MH 31 0 0 01 Apr 2025
Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction J. Vice Naveed Akhtar Richard I. Hartley Ajmal Saeed Mian Ajmal Mian DiffM 82 0 0 21 Nov 2024
Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions S. A. Baumann Felix Krause Michael Neumayr Nick Stracke Vincent Tao Hu Bjorn Ommer Björn Ommer DiffM LM&Ro 63 11 0 25 Mar 2024
Cones: Concept Neurons in Diffusion Models for Customized Generation Zhiheng Liu Ruili Feng Kai Zhu Yifei Zhang Kecheng Zheng Yu Liu Deli Zhao Jingren Zhou Yang Cao DiffM 100 116 0 09 Mar 2023
Red-Teaming the Stable Diffusion Safety Filter Javier Rando Daniel Paleka David Lindner Lennard Heim Florian Tramèr DiffM 119 179 0 03 Oct 2022