EvoMakeup: High-Fidelity and Controllable Makeup Editing with MakeupQuad
This work addresses the challenge of realistic and controllable makeup editing for applications in digital beauty and media, representing an incremental improvement over existing methods.
The paper tackles the problem of low-quality and identity-distorting facial makeup editing by introducing a large-scale dataset and a training framework, resulting in a method that outperforms prior approaches on real-world benchmarks while supporting multiple editing tasks.
Facial makeup editing aims to realistically transfer makeup from a reference to a target face. Existing methods often produce low-quality results with coarse makeup details and struggle to preserve both identity and makeup fidelity, mainly due to the lack of structured paired data -- where source and result share identity, and reference and result share identical makeup. To address this, we introduce MakeupQuad, a large-scale, high-quality dataset with non-makeup faces, references, edited results, and textual makeup descriptions. Building on this, we propose EvoMakeup, a unified training framework that mitigates image degradation during multi-stage distillation, enabling iterative improvement of both data and model quality. Although trained solely on synthetic data, EvoMakeup generalizes well and outperforms prior methods on real-world benchmarks. It supports high-fidelity, controllable, multi-task makeup editing -- including full-face and partial reference-based editing, as well as text-driven makeup editing -- within a single model. Experimental results demonstrate that our method achieves superior makeup fidelity and identity preservation, effectively balancing both aspects. Code and dataset will be released upon acceptance.