Boost Your Human Image Generation Model via Direct Preference Optimization

Human image generation is a key focus in image synthesis due to its broad applications. However, generating high-quality human images remains challenging because even slight inaccuracies in anatomy, pose, or fine details can compromise visual realism. To address these challenges, we explore Direct Preference Optimization (DPO), a method that trains models to generate images similar to preferred (winning) images while diverging from non-preferred (losing) ones. Conventional DPO approaches typically employ generated images as winning images, which may limit the model's ability to achieve high levels of realism. To overcome this limitation, we propose an enhanced DPO approach that incorporates high-quality real images as winning images, encouraging the model to produce outputs that resemble those real images rather than generated ones. Specifically, our approach, \textbf{HG-DPO} (\textbf{H}uman image \textbf{G}eneration through \textbf{DPO}), employs a novel curriculum learning framework that allows the model to gradually improve toward generating realistic human images, making the training more feasible than attempting the improvement all at once. Furthermore, we demonstrate that HG-DPO effectively adapts to personalized text-to-image tasks, generating high-quality, identity-specific images, which highlights the practical value of our approach.