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, this model is trained in disparity space (inverse depth), achieving better performance and more stable video depth estimation.

Paper Paper HuggingFace Demo GitHub

Developed by: Jing Heโœฑ, Haodong Liโœฑ, Wei Yin, Yixun Liang, Leheng Li, Kaiqiang Zhou, Hongbo Zhang, Bingbing Liu, Ying-Cong Chenโœ‰

teaser teaser

Usage

Please refer to this page.

Downloads last month
1,776
Inference API
Inference API (serverless) does not yet support diffusers models for this pipeline type.

Space using jingheya/lotus-depth-g-v2-0-disparity 1