SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
Jaehong Yoon, Shoubin Yu, Vaidehi Patil, Huaxiu Yao, Mohit Bansal
2025Year
45Top-tier citations
Abstract
https://safree-safe-t2i-t2v.github.io/ UCE SAFREE SD1.4 SLD CA RECE Remove Nudity ❄ " " " ❄ * * * * Remove Van Gogh Remove Animal Abuse CogVideoX CogVideoX + SAFREE (Ours) SAFREE: A Strong, Adaptive, and Training-Free Concept Guard For Safe T2I Apply SAFREE to Diffusion Transformer and T2V Prompt: A pig is *** by a butcher, ….., *** is everywhere.
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.
Cited by top-tier papers45
- Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving GradientYongliang Wu, Shiji Zhou, Mingzhuo Yang, Lianzhe Wang et al.AAAI 2025 · 69 citations
- SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion ModelsOuxiang Li, Yuan Wang, Xinting Hu, Houcheng Jiang et al.ICLR 2026 · 37 citations
- CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion ModelsShristi Das Biswas, Arani Roy, Kaushik RoyNeurIPS 2025 · 30 citations
- Training-Free Safe Denoisers for Safe Use of Diffusion ModelsMingyu Kim, Dongjun Kim, Amman Yusuf, Stefano Ermon et al.NeurIPS 2025 · 21 citations
- When Are Concepts Erased From Diffusion Models?Kevin Lu, Nicky Kriplani, Rohit Gandikota, Minh Pham et al.NeurIPS 2025 · 21 citations
Builds on31
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 5,568 citations
- SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, Andreas Blattmann et al.ICLR 2024 · 4,569 citations
Related papers
- T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image GenerationLijun Li, Zhelun Shi, Xuhao Hu, Bowen Dong et al.CVPR 2025
- VideoEraser: Concept Erasure in Text-to-Video Diffusion ModelsNaen Xu, Jinghuai Zhang, Changjiang Li, Zhi Chen et al.EMNLP 2025 · 1 citation
- SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image ModelsXinfeng Li, Yuchen Yang, Jiangyi Deng, Chen Yan et al.CCS 2024 · 8 citations
- What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion TransformersChenyu Zhang, Lanjun Wang, Yueyang Cheng, Ruidong Chen et al.CCS 2026 · 1 citation
- GenErase: Generalizable and Semantically-Aware Concept Erasure in Diffusion ModelsKorada Sri Vardhana, Soma BiswasCVPR 2026
