ICLR2025

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation

Jaehong Yoon, Shoubin Yu, Vaidehi Patil, Huaxiu Yao, Mohit Bansal

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.