---
title: Lotus-2
canonical_url: "https://www.modelscope.cn/models/1038lab/Lotus-2"
md_url: "https://www.modelscope.cn/models/1038lab/Lotus-2.md"
repository: 1038lab/Lotus-2
last_updated: 2026-10-01
license: apache-2.0
parameters: 1.9B
tensor_type:
- F32
- F16
- I32
library_name:
- safetensors
- pytorch
frameworks:
- pytorch
downloads: 247
stars: 0
tags:
- depth-estimation
- normal-estimation
- geometry-estimation
- flux
- comfyui
---
# Lotus-2
> Lotus-2 - 1038lab 在 ModelScope 开源的模型。Lotus & Lotus-2: Visual Foundation Models for Dense Geometry Estimation
1038lab/Lotus-2 是 ModelScope 魔搭社区上的 1.9B 参数机器学习模型，采用 apache-2.0 许可。
- **Repository**: 1038lab/Lotus-2
- **License**: apache-2.0
- **Parameters**: 1.9B
- **Tags**: depth-estimation, normal-estimation, geometry-estimation, flux, comfyui
- **Downloads**: 247
- **Stars**: 0
- **Last updated**: 2026-10-01
Source: https://www.modelscope.cn/models/1038lab/Lotus-2
---
# Lotus & Lotus-2: Visual Foundation Models for Dense Geometry Estimation
This repository provides consolidated, plug-and-play model weights for both **Lotus-2 (FLUX.1-dev SOTA)** and **Lotus-1 (SD 2.1 Fast)** for monocular **depth** and **surface normal** estimation, pre-configured for native integration with [ComfyUI-Lotus-2](https://github.com/1038lab/ComfyUI-Lotus-2).
[](https://lotus-2.github.io/)
[](https://huggingface.co/papers/2512.01030)
[](https://github.com/EnVision-Research/Lotus-2)
[](https://github.com/1038lab/ComfyUI-Lotus-2)
[-yellow)](https://huggingface.co/spaces/haodongli/Lotus-2_Depth)
[-yellow)](https://huggingface.co/spaces/haodongli/Lotus-2_Normal)
---
## 📦 Repository Contents
All safetensors weights in this repository are verified, standalone, and organized for direct automatic downloading or manual placement.
### 1. Lotus-2 Weights (FLUX.1-dev Monocular Geometry)
Developed by EnVision-Research (2026), built on FLUX.1-dev DiT using multi-stage LoRA and Local Continuity Modules (LCM):
| File Name | Size | Task | Description |
| :--- | :--- | :--- | :--- |
| `lotus-2_core_predictor_depth.safetensors` | ~1.43 GB | Depth | LoRA adapter for core global depth prediction |
| `lotus-2_detail_sharpener_depth.safetensors` | ~1.43 GB | Depth | LoRA adapter for high-frequency depth refinement |
| `lotus-2_lcm_depth.safetensors` | ~39 kB | Depth | Local Continuity Module for depth smoothness |
| `lotus-2_core_predictor_normal.safetensors` | ~2.87 GB | Normal | LoRA adapter for core surface normal prediction |
| `lotus-2_detail_sharpener_normal.safetensors` | ~2.87 GB | Normal | LoRA adapter for high-frequency normal refinement |
| `lotus-2_lcm_normal.safetensors` | ~39 kB | Normal | Local Continuity Module for normal consistency |
| `ae.safetensors` | ~335 MB | VAE | FLUX.1-dev native autoencoder |
### 2. Lotus-1 Weights (SD 2.1 Fast UNet Engine)
Developed by EnVision-Research, lightweight standalone diffusion UNet models (~1.7 GB):
| File Name | Size | Task | Description |
| :--- | :--- | :--- | :--- |
| `lotus-depth-g-v2-1-disparity-fp16.safetensors` | ~1.74 GB | Depth | Standalone Generative Depth (disparity, FP16) |
| `lotus-normal-g-v1-1-fp16.safetensors` | ~1.74 GB | Normal | Standalone Generative Surface Normal (FP16) |
| `vae-ft-mse-840000-ema-pruned.safetensors` | ~335 MB | VAE | Stable Diffusion 2.1 fine-tuned MSE Autoencoder |
---
## 🚀 Usage in ComfyUI
These models are natively supported by the [ComfyUI-Lotus-2](https://github.com/1038lab/ComfyUI-Lotus-2) custom node suite under category `🧪AILab/Geometry`:
```bash
cd ComfyUI/custom_nodes
git clone https://github.com/1038lab/ComfyUI-Lotus-2.git
```
### Node 1: `Lotus 2 (FLUX)` (SOTA Quality)
- **Minimal Inputs**: Requires only `image` and `model` (FLUX.1-dev UNet / Checkpoint).
- **Zero VRAM Waste**: VAE and text conditioning are handled internally—no need to connect DualCLIPLoader or load 10GB T5 models!
- **Auto-Download**: If LoRA or VAE files are not found locally, the node automatically downloads them from this repository (`1038lab/Lotus-2`).
### Node 2: `Lotus` (SD 2.1 Fast Engine)
- **Standalone**: All-in-one node without requiring an external base model loader.
- **Fast**: Generates high-quality geometry maps in seconds.
---
## 👏 Credits & Acknowledgments
We express our sincere gratitude and full credit to the original research teams and creators:
### Lotus-2 (FLUX-based)
- **Authors**: [Jing He](https://scholar.google.com/citations?hl=en&user=RsLS11MAAAAJ)1, [Haodong Li](https://haodong-li.com/)1,2*, [Mingzhi Sheng](https://github.com/MingzhiSheng)1*, [Ying-Cong Chen](https://www.yingcong.me/)1,3✉
- **Affiliations**: 1HKUST (GZ), 2HKUST, 3HKUST Dept. of CSE
- **Original Code & Weights**: [EnVision-Research/Lotus-2](https://github.com/EnVision-Research/Lotus-2) / [jingheya/Lotus-2](https://huggingface.co/jingheya/Lotus-2)
### Lotus-1 (SD-based)
- **Authors**: Jing He, Haodong Li, Weicai Ye, Wang Zhao, Suping Chen, Torsten Sattler, Guofeng Zhang, Shenghua Gao, Ying-Cong Chen
- **Original Code & Weights**: [EnVision-Research/Lotus](https://github.com/EnVision-Research/Lotus) / [jingheya/lotus-*](https://huggingface.co/jingheya)
### Base Models
- **FLUX.1-dev & FLUX VAE**: [Black Forest Labs](https://blackforestlabs.ai/)
- **Stable Diffusion 2.1 & VAE**: [Stability AI](https://stability.ai/)
---
## 📑 Citation
If you find Lotus or Lotus-2 helpful in your research or projects, please cite the official papers:
```bibtex
@article{he2025lotus2,
title = {Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model},
author = {He, Jing and Li, Haodong and Sheng, Mingzhi and Chen, Ying-Cong},
journal = {arXiv preprint arXiv:2512.01030},
year = {2025}
}
@article{he2024lotus,
title = {Lotus: Diffusion-based Visual Foundation Model for Dense Geometry Estimation},
author = {He, Jing and Li, Haodong and Ye, Weicai and Zhao, Wang and Chen, Suping and Sattler, Torsten and Zhang, Guofeng and Gao, Shenghua and Chen, Ying-Cong},
journal = {arXiv preprint arXiv:2409.08272},
year = {2024}
}
```