Jen-Yuan (Joy) Huang

Hello! I am a graduate student at the School of Intelligence Science and Technology at Peking University, advised by Professor Tong Lin. My research interest lies in computer vision and generative models. I enjoy developing fancy AI-generated content (AIGC) models, and I am currently a member of InstantX Team.

I received my Bachelor's degree in Industrial Engineering from Nanjing University, with a specialization in optimization and operation research. During my undergraduate studies, I had the opportunity to work closely with Professor Xiaopeng Luo.

profile photo

Publications

project image
project image

InstantIR: Blind Image Restoration with Instant Generative Reference


Jen-Yuan Huang, Haofan Wang, Qixun Wang, Xu Bai, Hao Ai, Peng Xing, Jen-Tse Huang
arXiv, 2024
arXiv / demo / website / code

InstantIR is a novel blind image restoration model based on Stable Diffusion. At each denoising step, we generate a restoration reference from current diffusion latent, which is used to align the low-quality image encoding and condition the generation process.

project image

CSGO: Content-Style Composition in Text-to-Image Generation


Peng Xing, Haofan Wang, Yanpeng Sun, Qixun Wang, Xu Bai, Hao Ai, Jen-Yuan Huang, Zechao Li
arXiv, 2024
arxiv / demo / website / code

In this work, we devlop an image stylization model named CSGO, which transfers the style presented by an input reference image to a source image. To enable end-to-end training, we introduce an automatic construction pipeline and IMAGStyle, first large-scale style transfer dataset with 210K {content;style;target}-triplet.

project image

InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation


Haofan Wang, Peng Xing, Jen-Yuan Huang, Hao Ai, Qixun Wang, Xu Bai
arXiv, 2024
arxiv / demo / website / code

In this paper, we explore natural style transfer while maintaining content integrity. Through analyzing different components of the Stable Diffusion UNet, we identify layers that specialize in processing style and content. Furthermore, we introduce a style discriminator to enhance the stylization of the output.

Contact

E-mail: jenyuan@stu.pku.edu.cn
Address: Peking University, Beijing, China


Design and source code from: Jon Barron's website