EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
Paper
•
2412.09618
•
Published
•
21
•
3
Zhuofan Zong
zongzhuofan
AI & ML interests
None yet
Recent Activity
authored
a paper
6 days ago
VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video
Face Swapping
upvoted
a
paper
9 days ago
VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video
Face Swapping
upvoted
a
paper
9 days ago
Causal Diffusion Transformers for Generative Modeling
Organizations
zongzhuofan's activity
commented
a
paper
13 days ago
commented
a
paper
6 months ago