Picture for Wonjun Kang

Wonjun Kang

Parameter-Efficient Fine-Tuning of State Space Models

Add code
Oct 11, 2024
Viaarxiv icon

Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing

Add code
Mar 14, 2024
Viaarxiv icon

Can MLLMs Perform Text-to-Image In-Context Learning?

Add code
Feb 02, 2024
Viaarxiv icon

Counting Guidance for High Fidelity Text-to-Image Synthesis

Add code
Jun 30, 2023
Viaarxiv icon

One-Shot Face Reenactment on Megapixels

Add code
May 26, 2022
Figure 1 for One-Shot Face Reenactment on Megapixels
Figure 2 for One-Shot Face Reenactment on Megapixels
Figure 3 for One-Shot Face Reenactment on Megapixels
Figure 4 for One-Shot Face Reenactment on Megapixels
Viaarxiv icon