Lotus: Depth Estimation Diffusion Model
ComfyUI Wiki
Lotus by NVIDIA Labs provides depth estimation using a diffusion-based approach, repackaged for ComfyUI.
Lotus is a depth estimation model from NVIDIA Labs that uses a diffusion-based approach for high-quality monocular depth prediction. Repackaged for ComfyUI for use in depth conditioning workflows.
Usage in ComfyUI
Place the model file in ComfyUI/models/ root directory. Requires a ComfyUI custom node that supports Lotus depth estimation.
| Developer | NVIDIA Labs |
| Release Date | 2025 |
| Architecture | Diffusion-based Depth Estimation |
| License | NVIDIA-Open-Model-License |
| Type | Depth Estimation |
| Variant | Depth D v1.1 |
Links
- Hugging Face (Comfy-Org): Comfy-Org/lotus
- Upstream (NVIDIA): NVlabs/lotus
Guides and workflows related to this model series.
No articles found.
Comments
Sign in with GitHub to join the discussion.