4 papers
DreamStyle: A Unified Framework for Video Stylization
Mengtian Li, Jinshu Chen, Songtao Zhao +3
Video stylization, an important downstream task of video generation models, has not yet been thoroughly explored. Its input style conditions typically include text, style image, an…
OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models
Jinshu Chen, Xinghui Li, Xu Bai +8
Recent advances in video insertion based on diffusion models are impressive. However, existing methods rely on complex control signals but struggle with subject consistency, limiti…
HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis
Mengtian Li, Jinshu Chen, Wanquan Feng +4
Personalized portrait synthesis, essential in domains like social entertainment, has recently made significant progress. Person-wise fine-tuning based methods, such as LoRA and Dre…
Customize Your Own Paired Data via Few-shot Way
Jinshu Chen, Bingchuan Li, Miao Hua +2
Existing solutions to image editing tasks suffer from several issues. Though achieving remarkably satisfying generated results, some supervised methods require huge amounts of pair…