Paired bare-makeup facial images are essential for a wide range of beauty-related tasks, such as virtual try-on, facial privacy protection, and facial aesthetics analysis. However, collecting high-quality paired makeup datasets remains a significant challenge. Real-world data acquisition is constrained by the difficulty of collecting large-scale paired images, while existing synthetic approaches often suffer from limited realism or inconsistencies between bare and makeup images.
Current synthetic methods typically fall into two categories: warping-based transformations, which often distort facial geometry and compromise the precision of makeup; and text-to-image generation, which tends to alter facial identity and expression, undermining consistency.
In this work, we present FFHQ-Makeup, a high-quality synthetic makeup dataset that pairs each identity with multiple makeup styles while preserving facial consistency in both identity and expression. Built upon the diverse FFHQ dataset, our pipeline transfers real-world makeup styles from existing datasets onto 18K identities by introducing an improved makeup transfer method that disentangles identity and makeup. Each identity is paired with 5 different makeup styles, resulting in a total of 90K high-quality bare–makeup image pairs.
To the best of our knowledge, this is the first work that focuses specifically on constructing makeup dataset.
We hope that FFHQ-Makeup fills the gap of lacking high-quality bare–makeup paired datasets and serves as a valuable resource for future research in beauty-related tasks.
Real-world data collection is hindered by logistical constraints, limited resources, and privacy concerns.
synthetic approaches often suffer from limited realism or inconsistencies between bare and makeup images.
Our FFHQ-Makeup dataset inherits the diversity of FFHQ. As shown, it includes multiple bare-makeup pairs examples across different ethnicities, ages, genders, expressions, and cases with occlusions or shadows.
Comparison of makeup transfer methods for dataset generation. Our method best preserves the target identity and expression while producing visually plausible makeup. In contrast, other methods often introduce artifacts or alter key facial attributes such as identity and expression.
@inproceedings{yang_2025_ffhq_makeup,
title={FFHQ-Makeup: Paired Synthetic Makeup Dataset with Facial Consistency Across Multiple Styles},
author={Xingchao Yang and Shiori Ueda and Yuantian Huang and Tomoya Akiyama and Takafumi Taketomi},
booktitle={arXiv},
year={2025},
}