Abstract: Face reenactment and face swap have gained a lot of attention due to their broad range of applications in computer vision. Although both tasks share similar objectives (e.g. manipulating expression and pose), existing methods do not explore the benefits of combining these two tasks.In this paper, we introduce a unified end-to-end pipeline for face swapping and reenactment. We propose a novel approach to isolated disentangled representation learning of specific visual attributes in an unsupervised manner. A combination of the proposed training losses allows us to synthesize results in a one-shot manner. The proposed method does not require subject-specific training.We compare our method against state-of-the-art methods for multiple public datasets of different complexities. The proposed method outperforms other SOTA methods in terms of realistic-looking face images.