System for generating image, and non-transitory computer readable medium

The present disclosure pertains to a system for efficiently learning a specific site. In order to achieve this purpose, provided is a system configured to generate a converted image from the input of an input image, the system including a learning model, the parameters of which are adjusted so as to suppress errors with a second image converted by the input of the input image, the learning model implements a different learning between at least a first region within the image and a second region different from the first region. 本公开涉及以高效地进行特定部位的学习为目的的系统。为了实现该目的，提出一种系统，其构成为根据输入图像的输入来生成转换图像，其中，该系统包含以抑制与通过所述输入图像的输入而转换的第二图像之间的误差的方式调整了参数的学习模型，该学习模型至少在图像内的第一区域和与该第一区域不同的第二区域之间实施不同的学习。