FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images

Figure 1: Results of facial parts swapping using the proposed FuseAnyPart at 512 512 resolution. The swapped face (central image) is generated by fusing the original face (top-left image) with three facial part reference images (bottom-left, top-right, bottom-right). Notably, FuseAnyPart can seamlessly blend facial parts from multiple reference images with significant differences in appearance, producing high-fidelity and natural-looking swapped faces.