ComfyUI Video Depth Anything

This project is an unofficial ComfyUI implementation of Video Depth Anything, for depth estimation on long videos without compromising quality, consistency, or generalization ability.

Last tested: 8 January 2026 (ComfyUI v0.8.2@a60b7b8 | Torch 2.9.1 | Python 3.12.3 | RTX5090 | CUDA 13.0 | Ubuntu 24.04)

⭐ Support

If you like my projects and wish to see updates and new features, please consider supporting me. It helps a lot!

Installation

Navigate to the ComfyUI /custom_nodes directory

git clone https://github.com/yuvraj108c/ComfyUI-Video-Depth-Anything.git
cd ./ComfyUI-Video-Depth-Anything
pip install -r requirements.txt

Usage

• Load example workflow
• Models will download automatically to /ComfyUI/models/videodepthanything.
• You can also download them manually from the official repository to that same directory.
• Supported models: 'video_depth_anything_vits.pth', 'video_depth_anything_vitb.pth', 'video_depth_anything_vitl.pth', 'metric_video_depth_anything_vits.pth', 'metric_video_depth_anything_vitb.pth', 'metric_video_depth_anything_vitl.pth'

Params

• input_size: Input size for model inference (default=518)
• max_res: Maximum resolution for model inference (default=1280)
• precision: Precision for inference (default=fp16)

Changelog

8 January 2026

• Support vitb and metric models
• Save EXR

9 February 2025

• Support autocast inference, minor cleanups

Citation

@article{video_depth_anything,
  title={Video Depth Anything: Consistent Depth Estimation for Super-Long Videos},
  author={Chen, Sili and Guo, Hengkai and Zhu, Shengnan and Zhang, Feihu and Huang, Zilong and Feng, Jiashi and Kang, Bingyi}
  journal={arXiv:2501.12375},
  year={2025}
}

LICENSE

• Video-Depth-Anything-Small model is under the Apache-2.0 license.
• Video-Depth-Anything-Base model is under the CC-BY-NC-4.0 license.
• Video-Depth-Anything-Large model is under the CC-BY-NC-4.0 license.