As modern text-to-image (T2I) models draw closer to synthesizing highly realistic content, the threat of unsafe content generation grows, and it becomes paramount to exercise control. Existing approaches steer these models by applying Euclidean adjustments to text embeddings, redirecting the generation away from unsafe concepts. In this work, we introduce hyperbolic control (HyCon): a novel control mechanism based on parallel transport that leverages semantically aligned hyperbolic representation space to yield more expressive and stable manipulation of concepts. HyCon reuses off-the-shelf generative models and a state-of-the-art hyperbolic text encoder, linked via a lightweight adapter. HyCon achieves state-of-the-art results across four safety benchmarks and four T2I backbones, showing that hyperbolic steering is a practical and flexible approach for more reliable T2I generation.

翻译：随着现代文本到图像（T2I）模型愈发接近合成高度逼真的内容，不安全内容生成的威胁也随之增长，实施控制变得至关重要。现有方法通过对文本嵌入应用欧几里得调整来引导这些模型，使生成内容远离不安全概念。在本工作中，我们提出了双曲控制（HyCon）：一种基于平行移动的新型控制机制，它利用语义对齐的双曲表示空间，实现对概念更具表现力和更稳定的操控。HyCon 复用了现成的生成模型和一个最先进的双曲文本编码器，二者通过一个轻量级适配器连接。HyCon 在四个安全基准测试和四个 T2I 骨干模型上均取得了最先进的结果，表明双曲引导是一种实用且灵活的方法，可实现更可靠的 T2I 生成。