Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Lingyun, Xie, Yu, Fang, Zhongli, Liu, Yu, Chen, Ping
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SafeCtrl: Region-Based Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress
by: Zhang, Lingyun, et al.
Published: (2025)

NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image Generation
by: Xie, Yu, et al.
Published: (2025)

TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
by: Zeng, Weichao, et al.
Published: (2024)

Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization
by: Zhang, Lingyun, et al.
Published: (2024)

ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation
by: Yang, Liudi, et al.
Published: (2026)

Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints
by: Fang, Chuan, et al.
Published: (2023)

IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis
by: Zhang, Lingyun, et al.
Published: (2026)

DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation
by: Zhang, Hongfei, et al.
Published: (2025)

CtrlNeRF: The Generative Neural Radiation Fields for the Controllable Synthesis of High-fidelity 3D-Aware Images
by: Liu, Jian, et al.
Published: (2024)

UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control
by: Xia, Tian, et al.
Published: (2024)

Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations
by: Mao, Shunqi, et al.
Published: (2025)

RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers
by: Cao, Ke, et al.
Published: (2025)

Mitigating Memorization in Text-to-Image Diffusion via Region-Aware Prompt Augmentation and Multimodal Copy Detection
by: Chen, Yunzhuo, et al.
Published: (2026)

CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion
by: Xi, Dianbing, et al.
Published: (2025)

LumiCtrl : Learning Illuminant Prompts for Lighting Control in Personalized Text-to-Image Models
by: Butt, Muhammad Atif, et al.
Published: (2025)

AttriCtrl: Fine-Grained Control of Aesthetic Attribute Intensity in Diffusion Models
by: Chen, Die, et al.
Published: (2025)

CameraCtrl: Enabling Camera Control for Text-to-Video Generation
by: He, Hao, et al.
Published: (2024)

EmoCtrl: Controllable Emotional Image Content Generation
by: Yang, Jingyuan, et al.
Published: (2025)

Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
by: Lin, Kuan Heng, et al.
Published: (2024)

CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning
by: Cao, Qingqing, et al.
Published: (2024)

CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance
by: Wang, Hanyang, et al.
Published: (2026)

RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
by: Xue, Zeyue, et al.
Published: (2023)

LightCtrl: Training-free Controllable Video Relighting
by: Peng, Yizuo, et al.
Published: (2026)

Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization
by: Li, Feifei, et al.
Published: (2025)

SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
by: Qi, Peigui, et al.
Published: (2025)

BSDM: Background Suppression Diffusion Model for Hyperspectral Anomaly Detection
by: Ma, Jitao, et al.
Published: (2023)

Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers
by: Chen, Ruidong, et al.
Published: (2026)

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
by: Wang, Chen, et al.
Published: (2025)

DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image Animation
by: Zhao, Haoyu, et al.
Published: (2025)

TIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion Transformers
by: Liu, Yihua, et al.
Published: (2026)

SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation
by: Ma, Yingzi, et al.
Published: (2026)

Personalized Safety Alignment for Text-to-Image Diffusion Models
by: Lei, Yu, et al.
Published: (2025)

Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes
by: Gosselin, Anthony, et al.
Published: (2025)

Beyond Detection: A Structure-Aware Framework for Scene Text Tracking
by: Yu, Chenmin, et al.
Published: (2026)

Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation
by: Gou, Yunhao, et al.
Published: (2024)

Ctrl-VI: Controllable Video Synthesis via Variational Inference
by: Duan, Haoyi, et al.
Published: (2025)

Using Powerful Prior Knowledge of Diffusion Model in Deep Unfolding Networks for Image Compressive Sensing
by: Liao, Chen, et al.
Published: (2025)

CtrlFuse: Mask-Prompt Guided Controllable Infrared and Visible Image Fusion
by: Sun, Yiming, et al.
Published: (2026)

PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models
by: Xie, Yiwei, et al.
Published: (2026)

Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement
by: Chen, Zhennan, et al.
Published: (2024)