This paper creates a novel method of deep neural style transfer by generating style images from freeform user text input. The language model and style transfer model form a seamless pipeline that can create output images with similar losses and improved quality when compared to baseline style transfer methods. The language model returns a closely matching image given a style text and description input, which is then passed to the style transfer model with an input content image to create a final output. A proof-of-concept tool is also developed to integrate the models and demonstrate the effectiveness of deep image style transfer from freeform text.
@article{arxiv.2212.06868,
title = {Deep Image Style Transfer from Freeform Text},
author = {Tejas Santanam and Mengyang Liu and Jiangyue Yu and Zhaodong Yang},
journal= {arXiv preprint arXiv:2212.06868},
year = {2022}
}