1 code implementation • 14 Mar 2024 • Wonjun Kang, Kevin Galim, Hyung Il Koo
A commonly adopted strategy for editing real images involves inverting the diffusion process to obtain a noisy representation of the original image, which is then denoised to achieve the desired edits.
no code implementations • 30 Jun 2023 • Wonjun Kang, Kevin Galim, Hyung Il Koo
In this paper, we propose a method to improve diffusion models to focus on producing the correct object count given the input prompt.
1 code implementation • CVPR 2020 • Maxim Maximov, Kevin Galim, Laura Leal-Taixé
We are able to train our model completely on synthetic data and directly apply it to a wide range of real-world images.
Ranked #1 on Depth Estimation on NYU-Depth V2 (RMSE metric)