ComfyUI Depth Anything TensorRT

This repo provides a ComfyUI Custom Node implementation of the Depth-Anything-Tensorrt in Python for ultra fast depth map generation (up to 5x faster)

⏱️ Performance

Note: Results below were benchmarked on FP16 engines inside ComfyUI

Device	Model	Model Input (WxH)	Image Resolution (WxH)	FPS
RTX4090	Depth-Anything-S	518x518	1280x720	35
RTX4090	Depth-Anything-B	518x518	1280x720	33
RTX4090	Depth-Anything-L	518x518	1280x720	24

🚀 Installation

Navigate to the ComfyUI /custom_nodes directory

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

🛠️ Building Tensorrt Engine

Download one of the available onnx models (e.g depth_anything_vitl14.onnx)
Edit model paths inside export_trt.py accordingly and run it
Place the exported engine inside ComfyUI /models/tensorrt/depth-anything directory

☀️ Usage

Insert node via tensorrt -> Depth Anything Tensorrt
Choose the appropriate engine from the dropdown

🤖 Environment tested

Ubuntu 22.04 LTS, Cuda 12.3, Tensorrt 10.0.1, Python 3.10, RTX 4090 GPU
Windows (Not tested)

📝 Changelog

26/04/2024
- Update to tensorrt 10.0.1
- Massive code refactor, remove trtexec, remove pycuda, show engine building progress
- Update and standardise engine directory for future tensorrt custom nodes suite
7/04/2024
- Fix image resize bug during depth map post processing
30/03/2024
- Fix CUDNN_STATUS_MAPPING_ERROR
27/03/2024
- Major refactor and optimisation (remove subprocess)

README.md