Much of the state-of-the-art in image synthesis inspired by real artwork are\neither entirely generative by filtered random noise or inspired by the transfer\nof style. This work explores the application of image inpainting to continue\nfamous artworks and produce generative art with a Conditional GAN. During the\ntraining stage of the process, the borders of images are cropped, leaving only\nthe centre. An inpainting GAN is then tasked with learning to reconstruct the\noriginal image from the centre crop by way of minimising both adversarial and\nabsolute difference losses, which are analysed by both their Fr\\'echet\nInception Distances and manual observations which are presented. Once the\nnetwork is trained, images are then resized rather than cropped and presented\nas input to the generator. Following the learning process, the generator then\ncreates new images by continuing from the edges of the original piece. Three\nexperiments are performed with datasets of 4766 landscape paintings\n(impressionism and romanticism), 1167 Ukiyo-e works from the Japanese Edo\nperiod, and 4968 abstract artworks. Results show that geometry and texture\n(including canvas and paint) as well as scenery such as sky, clouds, water,\nland (including hills and mountains), grass, and flowers are implemented by the\ngenerator when extending real artworks. In the Ukiyo-e experiments, it was\nobserved that features such as written text were generated even in cases where\nthe original image did not have any, due to the presence of an unpainted border\nwithin the input image.\n