Boxi Wu

Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model

PersonalView: Multi-View Consistent Human Image Customization via In-Context Learning

Self-Supervised Direct Preference Optimization for Text-to-Image Diffusion Models

UniHDA: A Unified and Versatile Framework for Generalized Hybrid Domain Adaptation

PersonalVideo: High ID-Fidelity Video Customization With Static Images

LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models

Vividportraits: Face Parsing Guided Portrait Animation