G-Refine: A General Quality Refiner for Text-to-Image Generation

1 code implementation • 29 Apr 2024 • Chunyi Li, HaoNing Wu, Hongkun Hao, ZiCheng Zhang, Tengchaun Kou, Chaofeng Chen, Lei Bai, Xiaohong Liu, Weisi Lin, Guangtao Zhai

Based on the mechanisms of the Human Visual System (HVS) and syntax trees, the first two indicators can respectively identify the perception and alignment deficiencies, and the last module can apply targeted quality enhancement accordingly.

Text-to-Image Generation