Thanks to GAN models (Generative Adversarial Network) we can alter the shapes of objects to understand the evolution of shapes. Between different classes of objects there is a middle way, a middle object to be discovered, which could suggest new directions to the designer. AI is the new muse of creative people.
The designer has to experience this multidimensional visual universe. The latent space, in which the images generated by the GAN move, seems born for designers and to inspire their creativity.
We can control the images generated by AI through the "design gesture": drawing, the primordial form of design expression, becomes the magic wand with which to direct the overflowing production of AI. We believe there can be a perfect dialogue between those who master the "progetto" and AI that is potentially able to generate every possible form.
The designer begins to design a new table, chair, or sofa. AI Mobili observes the drawing and gives advice on what the object could be like. AI Mobili reproduces it as a hyper realistic rendering, and shows different versions and variations. The more accurate and detailed your drawing becomes, the more hyper-realistic tips and previews follow your style and aesthetic. The system can be trained on your collection of drawings, renderings, photos and grasp your design style and start suggesting more and more consistent shapes and colors.