Generative Computing Lab

The Generative Computing Lab (GCL) at Inha University advances Generative AI (Gen AI) technologies to ensure that a wide range of people can benefit from them. We focuse on (but is not limited to) diffusion models and their applications, Gen AI + X (Gen AI for various domains) and ethical and responsible use of Gen AI.

인하대학교 생성 컴퓨팅 연구실은 다양한 사람들이 혜택을 누릴 수 있는 생성형 AI 기술 개발을 목표로 연구를 수행하고 있습니다. 주요 연구 분야는 확산 모델(Diffusion Models)의 응용, 생성형 AI의 다양한 도메인 적용(Gen AI + X), 그리고 생성형 AI의 윤리적이고 책임 있는 활용 방안 등이 있습니다.

Research Highlights

Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models (CVPR 2025)
An ultra-fast method to protect images against mimicry attempts from personalized diffusion models.

DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models (AAAI 2024)
An innovative approach to image generation that leverages textual inversion within text-to-image diffusion models.

DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion Models (arXiv preprint)
A novel framework for blending multiple modalities in text-to-image diffusion models.

AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks (ICCV 2023)
Aesthetic pattern-aware style transfer networks for high-quality image synthesis.

Interactive Cartoonization with Controllable Perceptual Factors (CVPR 2023)
An interactive way of cartoonization that allows for the manipulation of perceptual factors.

WebtoonMe: A Data-Centric Approach for Full-Body Portrait Stylization (SIGGRAPH Asia TC 2022)
A practical approach to full-body portrait stylization.

Rethinking Data Augmentation for Image Super-Resolution: A Comprehensive Analysis and a New Strategy (CVPR 2020)
A first attempt at modern data augmentation for image super-resolution.

Fast, Accurate, and Lightweight Super-Resolution With Cascading Residual Network (ECCV 2018)
A lightweight and efficient approach to image super-resolution.

News

July 2025

One paper A Plug-and-Play Approach for Robust Image Editing in Text-to-Image Diffusion Models has been accepted to ICCV Workshops (What is Next in Multimodal Foundation Models?).

June 2025

One paper Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models has been accepted to CVPR.

Feb 2025

One paper Magnitude Attention-based Dynamic Pruning has been accepted to Expert Systems with Applications, and one paper CutMAA: Motion-Aware Data Augmentation for Light Field Super-Resolution has been accepted to IEEE Access.

Sep 2024

The Generative Computing Lab has been opened at Inha University.

Feb 2024

One paper DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models has been accepted to AAAI