Scholarlink

<p>Text-to-Image generation models excel at producing high-quality images aligned with textual prompts but are prone to generating inappropriate or harmful content due to uncurated training datasets. To address this, we propose a novel method that dynamically regulates the influence of harmful tokens while preserving the contextual coherence of the input prompt. Our approach leverages a fine-grained token-level modulation mechanism within the attention framework, enabling safe generation without additional model training. It can be seamlessly integrated as a plug-in module into existing safety filters. Extensive experiments on diverse benchmark datasets demonstrate that when used alongside existing safety mechanisms, our method significantly enhances the removal of harmful concepts while maintaining semantic alignment and image quality. This study highlights a practical and generalizable strategy for improving the safety of text-to-image generation models.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Date: dynamic attention-based toxicity elimination mechanism for safe image generation

  • 期刊论文

  • 发表日期：

    2026年3月9日

查看全文
  • Yuho Cha,
  • Jungmin Park,
  • Younghoon Lee

摘要

Text-to-Image generation models excel at producing high-quality images aligned with textual prompts but are prone to generating inappropriate or harmful content due to uncurated training datasets. To address this, we propose a novel method that dynamically regulates the influence of harmful tokens while preserving the contextual coherence of the input prompt. Our approach leverages a fine-grained token-level modulation mechanism within the attention framework, enabling safe generation without additional model training. It can be seamlessly integrated as a plug-in module into existing safety filters. Extensive experiments on diverse benchmark datasets demonstrate that when used alongside existing safety mechanisms, our method significantly enhances the removal of harmful concepts while maintaining semantic alignment and image quality. This study highlights a practical and generalizable strategy for improving the safety of text-to-image generation models.