One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework
Feiran Li, Qianqian Xu, Shilong Bao, Zhiyong Yang, Xiaochun Cao, Qingming Huang
Abstract
SD v1.4 ESD Ours FMN SalUn AdvUnlearn UnlearnDiffAtk (Zhang et al., 2024c) "padme amidala taking a bath artwork, safe for work, no nudity" "padme amidala taking a bath artwork, safe for work, no nudity" "tran rogerske gen longliv epadme amidala taking a b ath artwork, safe for work, no nudity" "padme amidala taking a bath artwork, safe for work, no nudity" "mark umeurokher authe ntication padme amidala t aking a bath artwork, safe for work, no nudity" "spensnip survivors lgugl ypadme amidala taking a bath artwork, safe for wor k, no nudity" "sinus donesia petersburg macbeth عpadme amidala taking a bath artwork, safe for work, no nudity" Added for publication Figure 1. The original prompt describes a painting of Padme Amidala, a fictional character from the Star War. She is a human female senator who represents the people of Naboo during the final years of the Galactic Republic. Existing models are challenging to pursue a balance between efficacy (e.g., ESD (Gandikota et al., 2023), FMN (Zhang et al., 2024a)) and usability (SalUn (Fan et al., 2024), AdvUnlearn (Zhang et al., 2024c)), while ours can satisfy both requirements simultaneously.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 2574d5c4-c4e2-4916-b9d9-ecbb3c0a6750Cited by top-tier papers11
- LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text EncodersBoyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang et al.NeurIPS 2025 · 17 citations
- M4V: Multimodal Mamba for Efficient Text-to-Video GenerationJiancheng Huang, Gengwei Zhang, Zequn Jie, Siyu Jiao et al.CVPR 2026 · 14 citations
- SAFER: Risk-Constrained Sample-then-Filter in Large Language ModelsQingni Wang, Yue Fan, Xin WangICLR 2026 · 8 citations
- RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360deg Image Quality AssessmentYujia Wang, Yuyan Li, Jiuming Liu, Fang-Lue Zhang et al.CVPR 2026 · 3 citations
- Prototype-Guided Concept Erasure in Diffusion ModelsYuze Cai, Jiahao Lu, Hongxiang Shi, Yichao Zhou et al.CVPR 2026 · 3 citations
Builds on32
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
Related papers
- Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic PromptsZhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang, Pin-Yu Chen et al.ICML 2024 · 155 citations
- USD: NSFW Content Detection for Text-to-Image Models via Scene GraphYuyang Zhang, Kangjie Chen, Xudong Jiang, Jiahui Wen et al.USENIX Security 2025
- SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video GenerationJaehong Yoon, Shoubin Yu, Vaidehi Patil, Huaxiu Yao et al.ICLR 2025
- Improving Subject-Driven Image Synthesis with Subject-Agnostic GuidanceKelvin C. K. Chan, Yang Zhao, Xuhui Jia, Ming-Hsuan Yang et al.CVPR 2024
- SafeGuider: Robust and Practical Content Safety Control for Text-to-Image ModelsPeigui Qi, Kunsheng Tang, Wenbo Zhou, Weiming Zhang et al.CCS 2025
