Picture for Hyoung-Kyu Song

Hyoung-Kyu Song

EdgeFusion: On-Device Text-to-Image Generation

Add code
Apr 18, 2024
Viaarxiv icon

LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights

Add code
Apr 18, 2024
Figure 1 for LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights
Figure 2 for LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights
Figure 3 for LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights
Figure 4 for LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insights
Viaarxiv icon

LatentSwap: An Efficient Latent Code Mapping Framework for Face Swapping

Add code
Mar 02, 2024
Viaarxiv icon

Shortened LLaMA: A Simple Depth Pruning for Large Language Models

Add code
Feb 05, 2024
Viaarxiv icon

On Architectural Compression of Text-to-Image Diffusion Models

Add code
May 25, 2023
Viaarxiv icon

Talking Face Generation with Multilingual TTS

Add code
May 13, 2022
Figure 1 for Talking Face Generation with Multilingual TTS
Figure 2 for Talking Face Generation with Multilingual TTS
Figure 3 for Talking Face Generation with Multilingual TTS
Figure 4 for Talking Face Generation with Multilingual TTS
Viaarxiv icon

Deep User Identification Model with Multiple Biometrics

Add code
Sep 03, 2019
Figure 1 for Deep User Identification Model with Multiple Biometrics
Figure 2 for Deep User Identification Model with Multiple Biometrics
Figure 3 for Deep User Identification Model with Multiple Biometrics
Figure 4 for Deep User Identification Model with Multiple Biometrics
Viaarxiv icon