Kavli Affiliate: Xiang Zhang | First 5 Authors: Zongyu Wu, Hongcheng Gao, Yueze Wang, Xiang Zhang, Suhang Wang | Summary: Text-to-Image (T2I) models have shown great performance in generating images based on textual prompts. However, these models are vulnerable to unsafe input to generate unsafe content like sexual, harassment and illegal-activity images. Existing studies based […]
Continue.. Universal Prompt Optimizer for Safe Text-to-Image Generation