Text-to-Classic: A Diffusion Method for Classical Art Generation Based on Text

Text-to-Image generation has recently become a hot research topic and diffusion models have achieved remarkable performance in this task. However, most previous researches aim at real scene generation. Few researches focus on classical art paintings. Besides, diffusion models are commonly heavy-weighted with a large number of parameters, which has a high computational cost. In this paper, we aim to solve the classical art paintings synthesis subtask. We propose a lightweight diffusion model Text-to-Classic(T2C) to synthesize classical art paintings according to text descriptions. Experiment results show that our method can achieve good performance with fewer parameters.