Repository files navigation

This repo provides a ComfyUI Custom Node implementation of theDepth-Anything-Tensorrt in Python for ultra fast depth map generation (up to 14x faster thancomfyui_controlnet_aux)

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

Special thanks tolivepeer.org for supporting the project!

Note: The following results were benchmarked on FP16 engines inside ComfyUI

Note: The following results were benchmarked on FP16 engines inside ComfyUI

Note: The following results were benchmarked on FP16 engines inside ComfyUI

Navigate to the ComfyUI/custom_nodes directory

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

There are two ways to build TensorRT engines:

1. Insert node byRight Click -> tensorrt -> Depth Anything Engine Builder
2. Select the model version (v1 or v2 or DAD) and size (small, base, or large)
3. Optionally customize the engine name, FP16 settings, and onnx path
4. Run the workflow to build the engine

The engine will be automatically downloaded and built in the specified location. Refresh the webpage or strike 'r' on your keyboard, and the new engine will appear in the Depth Anything Tensorrt node.

1. Download one of the available onnx models:
   • Depth Anything v1
   • Depth Anything v2
   • Distill Any Depth
2. Run the export script, e.g

python export_trt.py --onnx-path ./depth_anything_vitl14-fp16.onnx --trt-path ./depth_anything_vitl14-fp16.engine

3. Place the exported engine inside ComfyUI/models/tensorrt/depth-anything directory

• Insert node byRight Click -> tensorrt -> Depth Anything Tensorrt
• Choose the appropriate engine from the dropdown

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

• 16/09/2025

  • Add support for v2 metric models (depth_anything_v2_metric_hypersim_vitl, depth_anything_v2_metric_vkitti_vitl)#21

• 08/07/2025

  • Add support forDistill-Any-Depth
  • Add benchmark for Distill-Any-Depth models

• 20/05/2025

  • MergePR#15 for auto engine building inside comfyui byryanontheinside
  • MergePR#14 for configurable params in export_trt.py byrickstaa

• 02/07/2024

  • Add Depth Anything V2 onnx models + benchmarks
  • MergePR for engine caching in memory byBuffMcBigHuge

• 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 and node category for upcoming 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)

• NVIDIA/Stable-Diffusion-WebUI-TensorRT
• spacewalk01/depth-anything-tensorrt
• martenwikman/depth-anything-tensorrt-docker
• Westlake-AGI-Lab/Distill-Any-Depth
• kijai/ComfyUI-DepthAnythingV2