Image de couverture de livre

SafeCtrl: Region-Based Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Lingyun, Xie, Yu, Fu, Yanwei, Chen, Ping
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SafeCtrl: Region-Aware Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress
par: Zhang, Lingyun, et autres
Publié: (2026)

NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image Generation
par: Xie, Yu, et autres
Publié: (2025)

Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization
par: Zhang, Lingyun, et autres
Publié: (2024)

TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
par: Zeng, Weichao, et autres
Publié: (2024)

UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control
par: Xia, Tian, et autres
Publié: (2024)

Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations
par: Mao, Shunqi, et autres
Publié: (2025)

Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints
par: Fang, Chuan, et autres
Publié: (2023)

LumiCtrl : Learning Illuminant Prompts for Lighting Control in Personalized Text-to-Image Models
par: Butt, Muhammad Atif, et autres
Publié: (2025)

RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers
par: Cao, Ke, et autres
Publié: (2025)

AttriCtrl: Fine-Grained Control of Aesthetic Attribute Intensity in Diffusion Models
par: Chen, Die, et autres
Publié: (2025)

CameraCtrl: Enabling Camera Control for Text-to-Video Generation
par: He, Hao, et autres
Publié: (2024)

CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion
par: Xi, Dianbing, et autres
Publié: (2025)

CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance
par: Wang, Hanyang, et autres
Publié: (2026)

EmoCtrl: Controllable Emotional Image Content Generation
par: Yang, Jingyuan, et autres
Publié: (2025)

ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation
par: Yang, Liudi, et autres
Publié: (2026)

DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation
par: Zhang, Hongfei, et autres
Publié: (2025)

Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
par: Lin, Kuan Heng, et autres
Publié: (2024)

CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning
par: Cao, Qingqing, et autres
Publié: (2024)

LightCtrl: Training-free Controllable Video Relighting
par: Peng, Yizuo, et autres
Publié: (2026)

Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization
par: Li, Feifei, et autres
Publié: (2025)

DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image Animation
par: Zhao, Haoyu, et autres
Publié: (2025)

LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model
par: Cao, Chenjie, et autres
Publié: (2023)

Mitigating Memorization in Text-to-Image Diffusion via Region-Aware Prompt Augmentation and Multimodal Copy Detection
par: Chen, Yunzhuo, et autres
Publié: (2026)

Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers
par: Chen, Ruidong, et autres
Publié: (2026)

CtrlFuse: Mask-Prompt Guided Controllable Infrared and Visible Image Fusion
par: Sun, Yiming, et autres
Publié: (2026)

Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes
par: Gosselin, Anthony, et autres
Publié: (2025)

Ctrl-VI: Controllable Video Synthesis via Variational Inference
par: Duan, Haoyi, et autres
Publié: (2025)

Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling
par: Zhang, Guiyu, et autres
Publié: (2024)

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
par: Wang, Chen, et autres
Publié: (2025)

Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models
par: Koh, Eunseo, et autres
Publié: (2025)

IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis
par: Zhang, Lingyun, et autres
Publié: (2026)

SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation
par: Ma, Yingzi, et autres
Publié: (2026)

RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
par: Xue, Zeyue, et autres
Publié: (2023)

MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model
par: Cao, Chenjie, et autres
Publié: (2024)

SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
par: Qi, Peigui, et autres
Publié: (2025)

DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation
par: Lin, Hongbin, et autres
Publié: (2025)

Image-Text-Image Knowledge Transfer for Lifelong Person Re-Identification with Hybrid Clothing States
par: Wang, Qizao, et autres
Publié: (2024)

Personalized Safety Alignment for Text-to-Image Diffusion Models
par: Lei, Yu, et autres
Publié: (2025)

Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference
par: Yu, Zihao, et autres
Publié: (2023)

CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models
par: He, Hao, et autres
Publié: (2025)