Portrait stylization is a challenging task involving the transformation of an input portrait image into a specific style while preserving its inherent characteristics. The recent introduction of Stable Diffusion (SD) has significantly improved the quality of outcomes in this field. However, a practical stylization framework that can effectively filter harmful input content and preserve the distinct characteristics of an input, such as skin-tone, while maintaining the quality of stylization remains lacking. These challenges have hindered the wide deployment of such a framework. To address these issues, this study proposes a portrait stylization framework that incorporates a nudity content identification module (NCIM) and a skin-tone-aware portrait stylization module (STAPSM). In experiments, NCIM showed good performance in enhancing explicit content filtering, and STAPSM accurately represented a diverse range of skin tones. Our proposed framework has been successfully deployed in practice, and it has effectively satisfied critical requirements of real-world applications.

翻译：肖像风格化是一项具有挑战性的任务，涉及在保留输入肖像图像固有特征的同时，将其转换为特定风格。近期引入的稳定扩散（Stable Diffusion, SD）显著提升了该领域输出成果的质量。然而，目前仍缺乏一种实用的风格化框架，既能有效过滤有害输入内容，又能保留输入图像（如肤色）的显著特征，同时保持风格化质量。这些挑战阻碍了此类框架的广泛部署。为解决上述问题，本研究提出了一种集成裸体内容识别模块（NCIM）和肤色感知肖像风格化模块（STAPSM）的肖像风格化框架。实验中，NCIM在增强显式内容过滤方面表现良好，而STAPSM能够准确呈现多样化的肤色范围。我们所提出的框架已成功投入实际应用，有效满足了真实场景的关键需求。