In this research, we have carried out various experiments to perform mutual transformation between a domain of Ikebana (Japanese traditional flower arrangement) photos and other domains of images (landscapes, animals, portraits) to create new artworks via CycleGAN, a variation of GANs (Generative Adversarial Networks) - new AI technology that can perform deep learning with less training data. With the capability of achieving transformation between two image sets using CycleGAN, we obtained several interesting results in which Ikebana plays the role of a digital painting tool due to the flexibility and minimality of the Japanese culture form. Our experiments show that Ikebana can be developed as a painting tool in digital art with the help of CycleGAN and opens a new way to create digital artworks of high-abstracted level by applying AI techniques to elements from traditional culture.