activity
20242026
collaborators

6 papers

cs.CV2026

CDST: Color Disentangled Style Transfer for Universal Style Reference Customization

Shiwen Zhang, Zhuowei Chen, Lang Chen +1

We introduce Color Disentangled Style Transfer (CDST), a novel and efficient two-stream style transfer training paradigm which completely isolates color from style and forces the s…

cs.CV2026

OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer

Pengze Zhang, Yanze Wu, Mengtian Li +8

Videos convey richer information than images or text, capturing both spatial and temporal dynamics. However, most existing video customization methods rely on reference images or t…

cs.CV2025

DreamO: A Unified Framework for Image Customization

Chong Mou, Yanze Wu, Wenxu Wu +15

Recently, extensive research on image customization (e.g., identity, subject, style, background, etc.) demonstrates strong customization capabilities in large-scale generative mode…

cs.CV2025

InstructX: Towards Unified Visual Editing with MLLM Guidance

Chong Mou, Qichao Sun, Yanze Wu +5

With recent advances in Multimodal Large Language Models (MLLMs) showing strong visual understanding and reasoning, interest is growing in using them to improve the editing perform…

cs.CV2025

MUSAR: Exploring Multi-Subject Customization from Single-Subject Dataset via Attention Routing

Zinan Guo, Pengze Zhang, Yanze Wu +3

Current multi-subject customization approaches encounter two critical challenges: the difficulty in acquiring diverse multi-subject training data, and attribute entanglement across…

cs.CV2024

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Zinan Guo, Yanze Wu, Zhuowei Chen +3

We propose Pure and Lightning ID customization (PuLID), a novel tuning-free ID customization method for text-to-image generation. By incorporating a Lightning T2I branch with a sta…