FImg) to FImg GANs [176]; s1 Image mask to FImg GANs [177]; CycleGAN [178]; s2 Img to FImg GANs [179–182] FImg to FImg GANs [183–186]; s2 Img to s2 Img GAN [187]; FImg to s1 Img VAE [188]; Subjective decisions styles, such as generating architectural images from sketches or line drawings (s2 Img to FImg) [179–182]. By leveraging generative AI models, architectural images can undergo style blending, where images adversarial networks. Environment and Planning B: Urban Analytics and City Science, 49(3):794–814, 2022. [182] YUQIAN LI1and WEIGUO XU. Research on architectural sketch to scheme image based on context encoder