Yanze Wu

From August 2023 to December 2025, I worked as an Applied Researcher at ByteDance Intelligent Creation, where I led research efforts in image/video customization and editing. Prior to that, I spent three years at Tencent ARC Lab, focusing on AIGC controllable generation and image/video super-resolution. I obtained my master's degree from Fudan University in 2020.

I have a broad interest in GenAI. While my previous work primarily focused on application-oriented tasks such as controllable and customized generation, my current research focus has shifted towards Video Foundation Models.

If you are interested in collaborating with me, please feel free to reach out. I am always looking for self-motivated research interns.

News

• [05/2025] We release DreamO, a unified framework for image customization.
• [09/2024] PuLID accepted by NeurIPS 2024. Check our recent updates, including PuLID-FLUX.
• [05/2024] We release PuLID, a pure and lightning ID customization method.
• [04/2024] The extension of MM-RealSR was accepted by TPAMI.
• [02/2024] One paper was accepted by CVPR 2024 as Highlight (11.9%).
• [12/2023] One paper was accepted by AAAI 2024.
• [09/2022] One paper was accepted by NeurIPS 2022.
• [07/2022] One paper was accepted by ECCV 2022.
• [07/2021] One paper was accepted by ICCV 2021.

Publications

(* equal contribution, ^# corresponding author)

DreamO: A Unified Framework for Image Customization
by ByteDance Intelligent Creation (Core Contributor & Corresponding Author)
SIGGRAPH Asia, 2025
Paper (arXiv) / Codes (GitHub) / 🤗 Demo

PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Zinan Guo*, Yanze Wu*^#, Zhuowei Chen, Lang Chen, Peng Zhang, Qian He
NeurIPS, 2024
Paper (arXiv) / Codes (GitHub) / PuLID 🤗 demo / PuLID-FLUX 🤗 demo

DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations
Tianhao Qi, Shancheng Fang, Yanze Wu, Hongtao Xie, Jiawei Liu, Lang Chen, Qian He, Yongdong Zhang
CVPR, 2024, Selected as Highlight (11.9%)
Paper (arXiv) / Project Page / Codes (GitHub)

T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models
Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, Ying Shan, Xiaohu Qie
Annual AAAI Conference on Artificial Intelligence (AAAI), 2024
Paper (arXiv) / Codes (GitHub)

AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos
Yanze Wu*, Xintao Wang*, Gen Li, Ying Shan
Advances in Neural Information Processing Systems (NeurIPS), 2022
Paper (arXiv) / Codes (GitHub)

MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolution
Chong Mou, Yanze Wu, Xintao Wang, Chao Dong, Jian Zhang, Ying Shan
European Conference on Computer Vision (ECCV), 2022
Paper (arXiv) / Codes (GitHub)

Towards Vivid and Diverse Image Colorization with Generative Color Prior
Yanze Wu, Xintao Wang, Yu Li, Honglun Zhang, Xun Zhao, Ying Shan
IEEE International Conference on Computer Vision (ICCV), 2021
Paper (arXiv) / Codes (GitHub)

Awards

Silver Medal of The 2015 ACM/ICPC Asia EC-Final Contest, 2015
Silver Medal of The 2015 ACM/ICPC Asia Changchun Regional Contest, 2015
Silver Medal of The 2016 ACM/ICPC Asia Qingdao Regional Contest, 2016

Experiences

ByteDance

Jan. 2025 - Dec. 2025

Senior Tech Expert

ByteDance

Aug. 2023 - Dec. 2024

Tech Expert

Tencent

May. 2020 - Jul. 2023

Researcher