FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live Images

TL;DR

FLUXSynID is a novel framework that generates high-resolution, identity-controlled synthetic face datasets with diverse attributes, improving realism and diversity for biometric research while addressing privacy and demographic issues.

Contribution

Introduces FLUXSynID, enabling fine-grained control over synthetic face attributes and producing paired images under structured conditions, with a large, diverse dataset of synthetic identities.

Findings

Generated dataset aligns well with real-world identity distributions

Achieves greater inter-class diversity than prior methods

Supports biometric research with publicly available data

Abstract

Synthetic face datasets are increasingly used to overcome the limitations of real-world biometric data, including privacy concerns, demographic imbalance, and high collection costs. However, many existing methods lack fine-grained control over identity attributes and fail to produce paired, identity-consistent images under structured capture conditions. We introduce FLUXSynID, a framework for generating high-resolution synthetic face datasets along with a dataset of 14,889 synthetic identities. We generate synthetic faces with user-defined identity attribute distributions, offering both document-style and trusted live capture images. The dataset generated using the FLUXSynID framework shows improved alignment with real-world identity distributions and greater inter-class diversity compared to prior work. Our work is publicly released to support biometric research, including face recognition and morphing attack detection.