Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

• This model belongs to the family of official Lotus models.
• Compared to the previous version (jingheya/lotus-depth-g-v2-0-disparity), this model was trained with random flip augmentation and achieves better results.

Developed by: Jing He✱, Haodong Li✱, Wei Yin, Yixun Liang, Leheng Li, Kaiqiang Zhou, Hongbo Zhang, Bingbing Liu, Ying-Cong Chen✉

Usage

Please refer to this page.