no code implementations • 30 May 2024 • Sanghyeon Na, Yonggyu Kim, Hyunjoon Lee
The generation of high-quality human images through text-to-image (T2I) methods is a significant yet challenging task.
no code implementations • 3 Aug 2023 • Sanghyeon Na
We argue that a model which is proficient in generating a megapixel image can achieve this goal.
no code implementations • 11 Feb 2019 • Sanghyeon Na, Seungjoo Yoo, Jaegul Choo
First, we use a content representation from the source domain conditioned on a style representation from the target domain.