Image Generation with Interactive Evolutionary System using Bayesian Optimization
Y. Dianey Rueda-Arango, David Rojas-Velázquez, Aleksandra V. Gorelova, Johan Garssen, Alberto Paolo Tonda, Alejandro Lopez‐Rincon · 2024
Interactive Evolutionary Systems (IES) can generate several designs based on a handful of input parameters. Never-theless, the choice of the parameters is an open problem and it is limited to a few evaluations as they require human input. As a solution, Bayesian Optimization (BO) can be used to tune IES parameters. BO is a statistical method that efficiently models and optimizes expensive black-box derivative-free functions in few evaluations. In the context of creative IES, such as image generators, it can be used in conjunction with user preferences to optimize a complex-structured input space, such as variations of artistic images with uniqueness and creativity that follow the original concept and the artistic intention. Therefore, for this objective, we propose an implementation of BOIES with a metric based on user preferences that interactively evaluates a batch of images to evolve a set of parameters in Stable Diffusion to create variations with a given human-made artwork. Our results proved better than baseline, and against generated images using Neural Style Transfer (NST). The resulting images were consistent in terms of uniqueness, quality, and following a given concept.