FFHQ-Makeup: Paired Synthetic Makeup Dataset with Facial Consistency Across Multiple Styles

ICLR 2026 Conference Submission14896 Authors

Keywords: Makeup dataset, Synthetic Dataset, Makeup transfer, 3D Morphable Model

Abstract:

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 and text-to-image generation. The former often distorts facial geometry and compromises makeup precision, while the latter 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.
We release FFHQ-Makeup as the first large-scale, multi-style, paired bare–makeup dataset, which we expect will serve as a valuable resource for future research in beauty-related tasks.

Primary Area: datasets and benchmarks

Submission Number: 14896