no code implementations • 30 Apr 2024 • Chanran Kim, Jeongin Lee, Shichang Joung, Bongmo Kim, Yeul-Min Baek
Additionally, our masked cross-attention mechanism enables the precise control of multi-ID and composition in the generated images.
no code implementations • 13 May 2022 • GunHee Lee, Jonghwa Yim, Chanran Kim, Minjae Kim
Despite recent success in conditional image synthesis, prevalent input conditions such as semantics and edges are not clear enough to express `Linear (Ridges)' and `Planar (Scale)' representations.
1 code implementation • 15 Jul 2020 • Byeongjo Kim, Chanran Kim, Jaehoon Lee, Jein Song, Gyoungsoo Park
In general, sufficient data is essential for the better performance and generalization of deep-learning models.