Image text to FImg GANs [160–162]; DMs [4,163–166]; GANs, DMs [5] (s1 Image text + FImg) to FImg DMs [167–170]; GANs [171,172]; GANs, DMs [173]; GANs, CLIP [174,175] (o3 Img + FImg) to FImg GANs [176]; s1 creation of architectural im- ages based on the textual prompts (s1 Image text + FImg to FImg) [160, 167–175]. Additionly, researchers utilize gen- erative AI models to train architectural images and corre- text: A new diffusion model-based method for efficient creative design. Buildings, 13(7):1861, 2023. [167] Frederick Chando Kim, Mikhael Johanes, and Jeffrey Huang. Text2form diffusion. [168] Gernot Riether