Tianyi Wei

9

Papers

57

Total Citations

Papers (9)

SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models

FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing

FaceRSA: RSA-Aware Facial Identity Cryptography Framework

Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling

HairCLIP: Design Your Hair by Text and Reference Image

HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending

AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA

Improved Image Matting via Real-Time User Clicks and Uncertainty Estimation

Multi-Attentional Deepfake Detection