We present a training-free, plug-and-play method, namely VFace, for high-quality face swapping in videos. It can be seamlessly integrated with image-based face swapping approaches built on diffusion models. First, we introduce a Frequency Spectrum Attention Interpolation technique to facilitate generation and intact key identity characteristics. Second, we achieve Target Structure Guidance via plug-and-play attention injection to better align the structural features from the target frame to the generation. Third, we present a Flow-Guided Attention Temporal Smoothening mechanism that enforces spatiotemporal coherence without modifying the underlying diffusion model to reduce temporal inconsistencies typically encountered in frame-wise generation. Our method requires no additional training or video-specific fine-tuning. Extensive experiments show that our method significantly enhances temporal consistency and visual fidelity, offering a practical and modular solution for video-based face swapping. Our code is available at https://github.com/Sanoojan/VFace.
@article{arxiv.2602.07835,
title = {VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping},
author = {Sanoojan Baliah and Yohan Abeysinghe and Rusiru Thushara and Khan Muhammad and Abhinav Dhall and Karthik Nandakumar and Muhammad Haris Khan},
journal= {arXiv preprint arXiv:2602.07835},
year = {2026}
}