HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis

no code implementations • 21 Mar 2025 • Mengtian Li, Jinshu Chen, Wanquan Feng, Bingchuan Li, Fei Dai, Songtao Zhao, Qian He

Personalized portrait synthesis, essential in domains like social entertainment, has recently made significant progress.

Customize Your Own Paired Data via Few-shot Way

no code implementations • 21 May 2024 • Jinshu Chen, Bingchuan Li, Miao Hua, Panpan Xu, Qian He

Existing solutions to image editing tasks suffer from several issues.

Few-Shot Learning

MOGAN: Morphologic-structure-aware Generative Learning from a Single Image

1 code implementation • 4 Mar 2021 • Jinshu Chen, Qihui Xu, Qi Kang, Mengchu Zhou

For training for ROI, we propose to utilize the data coming from the original image being augmented and bring in a novel module to transform such augmented data into knowledge containing both structures and appearances, thus enhancing the model's comprehension of the sample.

Generative Adversarial Network ROI-based image generation