Real-time, high-fidelity face identity swapping with a vision foundation model

Many recent face-swapping methods based on generative adversarial networks (GANs) or autoencoders achieve strong performance under constrained conditions but degrade significantly in high-resolution or extreme pose scenarios. Moreover, most existing models generate outputs at limited resolutions ( 128×128 ), which fall short of modern visual standards. Diffusion-based approaches have shown promise in handling such challenges, but are computationally intensive and unsuitable for real-time applications. In this work, we propose FaceChanger, a real-time face identity swap framework designed to enhance robustness across various poses and outputs at 256×256 (double the linear resolution of typical 128×128 baselines). While maintaining compatibility with conventional GAN- and autoencoder-based pipelines, FaceChanger uniquely incorporates a vision foundation model (VFM) to extract richer semantic features, which can enhance identity preservation, attribute control, and robustness to variations. In this work, we employ the Contrastive Language-Image Pre-training (CLIP) model to obtain the features. These features guide identity preservation and attribute control through newly designed VFM-based visual and textual semantic contrastive losses. Extensive evaluations on benchmarks such as the FaceForensics++ (FF++) dataset, the Multiple Pose, Illumination, and Expression (MPIE) dataset, and the large-pose Flickr face (LPFF) dataset demonstrate that FaceChanger matches or exceeds state-of-the-art performance under standard conditions and significantly outperforms them in high-resolution, pose-intensive scenarios.