s1 Fac) to FFac GANs [145–151] DM, CycleGAN [152] (aw + pw + awin + pwin + s1 Fac) to RFac pix2pix [153] FFac to FFac CycleGAN [154]; StyleGAN2 [155] (FFac + s2 Fac) to FFac GANs [156] (aw + pw + awin + can be generated using semantic segmentation images (aw + (pw) + awin + (pwin) + s1 Fac to RFac) [153]. Additionally, generative AI proves instrumental in training architectural facade images for both Guangquan Zhou. 3d face parsing via surface parameterization and 2d semantic segmentation network, 2022. [153] Da Wan, Runqi Zhao, Sheng Zhang, Hui Liu, Lian Guo, Pengbo Li, and Lei Ding. A deep learning-based