Home
Softono
y

yuvraj108c

Professional software vendor delivering innovative solutions on the Softono platform. Specialized in both open-source and proprietary software development.

Visit Website
Total Products
4

Software by yuvraj108c

ComfyUI-Upscaler-Tensorrt
Open Source

ComfyUI-Upscaler-Tensorrt

<div align="center"> # ComfyUI Upscaler TensorRT ⚡ [![python](https://img.shields.io/badge/python-3.12.3-green)](https://www.python.org/downloads/release/python-3123//) [![cuda](https://img.shields.io/badge/cuda-13.1-green)](https://developer.nvidia.com/cuda-downloads) [![trt](https://img.shields.io/badge/TRT-10.14.1.48-green)](https://developer.nvidia.com/tensorrt) [![by-nc-sa/4.0](https://img.shields.io/badge/license-CC--BY--NC--SA--4.0-lightgrey)](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en) </div> This project provides a [Tensorrt](https://github.com/NVIDIA/TensorRT) implementation for fast image upscaling using models inside ComfyUI (2-4x faster) **Last tested**: 07 June 2026 (ComfyUI v0.23.0 | Torch 2.12.0 | Python 3.12.3 | L40S | CUDA 13.0 | Ubuntu 24.04) <p align="center"> <img src="assets/node_v3.png" style="height: 400px" /> </p> ## ⭐ Support If you like my projects and wish to see updates and new features, please consider supporting me. It helps a lot! [![ComfyUI-Depth-Anything-Tensorrt](https://img.shields.io/badge/ComfyUI--Depth--Anything--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Depth-Anything-Tensorrt) [![ComfyUI-Upscaler-Tensorrt](https://img.shields.io/badge/ComfyUI--Upscaler--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Upscaler-Tensorrt) [![ComfyUI-Dwpose-Tensorrt](https://img.shields.io/badge/ComfyUI--Dwpose--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Dwpose-Tensorrt) [![ComfyUI-Rife-Tensorrt](https://img.shields.io/badge/ComfyUI--Rife--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Rife-Tensorrt) [![ComfyUI-Whisper](https://img.shields.io/badge/ComfyUI--Whisper-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Whisper) [![ComfyUI_InvSR](https://img.shields.io/badge/ComfyUI__InvSR-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI_InvSR) [![ComfyUI-Thera](https://img.shields.io/badge/ComfyUI--Thera-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Thera) [![ComfyUI-Video-Depth-Anything](https://img.shields.io/badge/ComfyUI--Video--Depth--Anything-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Video-Depth-Anything) [![ComfyUI-PiperTTS](https://img.shields.io/badge/ComfyUI--PiperTTS-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-PiperTTS) [![buy-me-coffees](https://i.imgur.com/3MDbAtw.png)](https://www.buymeacoffee.com/yuvraj108cZ) [![paypal-donation](https://i.imgur.com/w5jjubk.png)](https://paypal.me/yuvraj108c) --- ## ⏱️ Performance _Note: The following results were benchmarked on FP16 engines inside ComfyUI, using 100 identical frames_ | Device | Model | Input Resolution (WxH) | Output Resolution (WxH) | FPS | | :----: | :-----------: | :--------------------: | :---------------------: | :-: | | RTX5090 | 4x-UltraSharp | 512 x 512 | 2048 x 2048 | 12.7 | | RTX5090 | 4x-UltraSharp | 1280 x 1280 | 5120 x 5120 | 2.0 | | RTX4090 | 4x-UltraSharp | 512 x 512 | 2048 x 2048 | 6.7 | | RTX4090 | 4x-UltraSharp | 1280 x 1280 | 5120 x 5120 | 1.1 | | RTX3060 | 4x-UltraSharp | 512 x 512 | 2048 x 2048 | 2.2 | | RTX3060 | 4x-UltraSharp | 1280 x 1280 | 5120 x 5120 | 0.35 | ## 🚀 Installation - Install via the manager - Or, navigate to the `/ComfyUI/custom_nodes` directory ```bash git clone https://github.com/yuvraj108c/ComfyUI-Upscaler-Tensorrt.git cd ./ComfyUI-Upscaler-Tensorrt pip install -r requirements.txt ``` Optionally, you can install and use [TensorRT-RTX](https://github.com/NVIDIA/TensorRT-RTX) ```bash pip install tensorrt-rtx ``` ## 🛠️ Supported Models - These upscaler models have been tested to work with Tensorrt. Onnx are available [here](https://huggingface.co/yuvraj108c/ComfyUI-Upscaler-Onnx/tree/main) - The exported tensorrt models support dynamic image resolutions from 256x256 to 1280x1280 px (e.g 960x540, 512x512, 1280x720 etc). - [4x-AnimeSharp](https://openmodeldb.info/models/4x-AnimeSharp) - [4x-UltraSharp](https://openmodeldb.info/models/4x-UltraSharp) - [4x-WTP-UDS-Esrgan](https://openmodeldb.info/models/4x-WTP-UDS-Esrgan) - [4x_NMKD-Siax_200k](https://openmodeldb.info/models/4x-NMKD-Siax-CX) - [4x_RealisticRescaler_100000_G](https://openmodeldb.info/models/4x-RealisticRescaler) - [4x_foolhardy_Remacri](https://openmodeldb.info/models/4x-Remacri) - [RealESRGAN_x4](https://openmodeldb.info/models/4x-realesrgan-x4plus) - [4xNomos2_otf_esrgan](https://openmodeldb.info/models/4x-Nomos2-otf-esrgan) - [4x-ClearRealityV1](https://openmodeldb.info/models/4x-ClearRealityV1) - [4x_UniversalUpscalerV2-Neutral_115000_swaG](https://openmodeldb.info/models/4x-UniversalUpscalerV2-Neutral) - [4x-UltraSharpV2_Lite](https://huggingface.co/Kim2091/UltraSharpV2) - [2x-ESRGAN](https://openmodeldb.info/models/2x-ESRGAN) - [1x-ITF-SkinDiffDetail-Lite-v1](https://openmodeldb.info/models/1x-ITF-SkinDiffDetail-Lite-v1) ## ☀️ Usage - Load [example workflow](assets/tensorrt_upscaling_workflow.json) - Choose the appropriate model from the dropdown - The tensorrt engine will be built automatically - Load an image of resolution between 256-1280px - Set `resize_to` to resize the upscaled images to fixed or custom resolutions ## 🔧 Custom Models - To export other ESRGAN models, you'll have to build the onnx model first, using [export_onnx.py](scripts/export_onnx.py) - Place the onnx model in `/ComfyUI/models/onnx/YOUR_MODEL.onnx` - Then, add your model to this list [load_upscaler_config.json](load_upscaler_config.json) - Finally, run the same workflow and choose your model - If you've tested another working tensorrt model, let me know to add it officially to this node ## 🚨 Updates ### 07 June 2026 - Add support for [TensorRT-RTX](https://github.com/NVIDIA/TensorRT-RTX) ([PR#82](https://github.com/yuvraj108c/ComfyUI-Upscaler-Tensorrt/pull/82) by [@tangalbert919](https://github.com/tangalbert919)) - Add support for 1x/2x/any-x models ### 12 January 2026 - Add more resizing scale factors - Add custom resolution resizing ### 27 August 2025 - Support 4x-UltraSharpV2_Lite, 4x_UniversalUpscalerV2-Neutral_115000_swaG, 4x-ClearRealityV1 - Load models from config [PR#57](https://github.com/yuvraj108c/ComfyUI-Upscaler-Tensorrt/pull/57) by [@NeoAnthropocene](https://github.com/NeoAnthropocene) ### 30 April 2025 - Merge https://github.com/yuvraj108c/ComfyUI-Upscaler-Tensorrt/pull/48 by @BiiirdPrograms to fix soft-lock by raising an error when input image dimensions unsupported ### 4 March 2025 (breaking) - Automatic tensorrt engines are built from the workflow itself, to simplify the process for non-technical people - Separate model loading and tensorrt processing into different nodes - Optimise post processing - Update onnx export script ## ⚠️ Known issues - If you upgrade tensorrt version, you'll have to rebuild the engines - Only models with ESRGAN architecture are currently working - High ram usage when exporting `.pth` to `.onnx` ## 🤖 Environment tested - Ubuntu 24.04, Debian 12 - Windows 11 ## 👏 Credits - [NVIDIA/Stable-Diffusion-WebUI-TensorRT](https://github.com/NVIDIA/Stable-Diffusion-WebUI-TensorRT) - [comfyanonymous/ComfyUI](https://github.com/comfyanonymous/ComfyUI) ## License [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/)

LLM Tools & Chat UIs Image Editing
243 Github Stars
ComfyUI-Whisper
Open Source

ComfyUI-Whisper

# ComfyUI Whisper Transcribe audio and add subtitles to videos using [Whisper](https://github.com/openai/whisper/) in [ComfyUI](https://github.com/comfyanonymous/ComfyUI). Support multiple languages, prompt guidance and multiple whisper models. **Last tested**: 07 June 2026 (ComfyUI v0.23.0 | Torch 2.12.0 | Triton 3.7.0 | Python 3.12.3 | L40S | CUDA 13.0 | Ubuntu 24.04) ![demo-image](https://github.com/yuvraj108c/ComfyUI-Whisper/blob/assets/recording.gif?raw=true) ## ⭐ Support If you like my projects and wish to see updates and new features, please consider supporting me. It helps a lot! [![ComfyUI-Depth-Anything-Tensorrt](https://img.shields.io/badge/ComfyUI--Depth--Anything--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Depth-Anything-Tensorrt) [![ComfyUI-Upscaler-Tensorrt](https://img.shields.io/badge/ComfyUI--Upscaler--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Upscaler-Tensorrt) [![ComfyUI-Dwpose-Tensorrt](https://img.shields.io/badge/ComfyUI--Dwpose--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Dwpose-Tensorrt) [![ComfyUI-Rife-Tensorrt](https://img.shields.io/badge/ComfyUI--Rife--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Rife-Tensorrt) [![ComfyUI-Whisper](https://img.shields.io/badge/ComfyUI--Whisper-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Whisper) [![ComfyUI_InvSR](https://img.shields.io/badge/ComfyUI__InvSR-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI_InvSR) [![ComfyUI-Thera](https://img.shields.io/badge/ComfyUI--Thera-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Thera) [![ComfyUI-Video-Depth-Anything](https://img.shields.io/badge/ComfyUI--Video--Depth--Anything-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Video-Depth-Anything) [![ComfyUI-PiperTTS](https://img.shields.io/badge/ComfyUI--PiperTTS-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-PiperTTS) [![buy-me-coffees](https://i.imgur.com/3MDbAtw.png)](https://www.buymeacoffee.com/yuvraj108cZ) [![paypal-donation](https://i.imgur.com/w5jjubk.png)](https://paypal.me/yuvraj108c) --- ## Installation Install via [ComfyUI Manager](https://github.com/ltdrdata/ComfyUI-Manager) ## Usage Load this [workflow](https://github.com/yuvraj108c/ComfyUI-Whisper/blob/master/example_workflows/whisper_video_subtitles_workflow.json) into ComfyUI Models are auto-downloaded to `/ComfyUI/models/stt/whisper` ## Supported Models 'tiny.en', 'tiny', 'base.en', 'base', 'small.en', 'small', 'medium.en', 'medium', 'large-v1', 'large-v2', 'large-v3', 'large', 'large-v3-turbo', 'turbo' ## Nodes ### Apply Whisper Transcribe audio and get timestamps for each segment and word. ### Add Subtitles To Frames Add subtitles on the video frames. You can specify font family, font color and x/y positions. ### Add Subtitles To Background (Experimental) Add subtitles like wordcloud on blank frames ### Save SRT Export alignments as SRT files in `/ComfyUI/output/srt` directory ## Updates ### 7 June 2026 - Use soundfile to save audio and fix torchcodec issues ### 6 June 2026 - Merge https://github.com/yuvraj108c/ComfyUI-Whisper/pull/39 by [@alastaira](https://github.com/alastaira) for alternative model download folders - Merge https://github.com/yuvraj108c/ComfyUI-Whisper/pull/34 by [@MMaximuss](https://github.com/MMaximuss) for subtitle text outline ### 2 January 2026 - Export alignments as SRT - Add `torchcodec` to requirements ### 27 August 2025 - Merge https://github.com/yuvraj108c/ComfyUI-Whisper/pull/22 by [@francislabountyjr](https://github.com/francislabountyjr) for model patcher, more whisper models support, comfyui model directory support - Merge https://github.com/yuvraj108c/ComfyUI-Whisper/pull/18 by [@qy8502](https://github.com/qy8502) for Prompt Guidance support - Support YRDZST Semibold Font ### 2 May 2025 - Merge https://github.com/yuvraj108c/ComfyUI-Whisper/pull/15 by [@niknah](https://github.com/niknah) for language selection ## Credits - [comfyanonymous/ComfyUI](https://github.com/comfyanonymous/ComfyUI) - [Kosinkadink/ComfyUI-VideoHelperSuite](https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite) - [melMass/comfy_mtb](https://github.com/melMass/comfy_mtb) ## License [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/)

WordPress Themes & Plugins Audio Editing & DAW
242 Github Stars
4k-video-upscaler-colab
Open Source

4k-video-upscaler-colab

# 4k-Video-Upscaler-Colab-Real-ESRGAN Upscale your videos up to 4k on free google colab using [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yuvraj108c/4k-video-upscaler-colab/blob/main/4k_Video_Upscaler_Colab_(Real_ESRGAN).ipynb) [![Try a demo on Replicate](https://replicate.com/lucataco/real-esrgan-video/badge)](https://replicate.com/lucataco/real-esrgan-video) ![Screenshot 2025-05-01 at 10 03 17](https://github.com/user-attachments/assets/7a0cce5d-bb2d-426a-afd6-468c7a77b82b) ## Models - RealESRGAN_x4plus - RealESRGAN_x4plus_anime_6B - realesr-animevideov3 ## ⭐ Support If you like this project and wish to see updates and new features, please consider supporting me. It helps a lot! [![buy-me-coffees](https://i.imgur.com/3MDbAtw.png)](https://www.buymeacoffee.com/yuvraj108cZ) [![paypal-donation](https://i.imgur.com/w5jjubk.png)](https://paypal.me/yuvraj108c)

ML Frameworks Audio Editing & DAW
212 Github Stars
ComfyUI-Depth-Anything-Tensorrt
Open Source

ComfyUI-Depth-Anything-Tensorrt

<div align="center"> # ComfyUI Depth Anything TensorRT [![python](https://img.shields.io/badge/python-3.12.3-green)](https://www.python.org/downloads/release/python-3123//) [![cuda](https://img.shields.io/badge/cuda-13.1-green)](https://developer.nvidia.com/cuda-downloads) [![trt](https://img.shields.io/badge/TRT-10.14.1.48-green)](https://developer.nvidia.com/tensorrt) [![mit](https://img.shields.io/badge/license-MIT-blue)](https://github.com/spacewalk01/depth-anything-tensorrt/blob/main/LICENSE) </div> This repo provides a ComfyUI Custom Node implementation of the [Depth-Anything-Tensorrt](https://github.com/spacewalk01/depth-anything-tensorrt) in Python for ultra fast depth map generation (up to 14x faster than [comfyui_controlnet_aux](https://github.com/Fannovel16/comfyui_controlnet_aux)) **Last tested**: 03 June 2026 (ComfyUI v0.23.0 | Torch 2.12.0 | Python 3.12.3 | H100 | CUDA 13.0 | Ubuntu 24.04) <p align="center"> <img src="assets/demo.gif" /> </p> ## ⭐ Support If you like my projects and wish to see updates and new features, please consider supporting me. It helps a lot! [![ComfyUI-Depth-Anything-Tensorrt](https://img.shields.io/badge/ComfyUI--Depth--Anything--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Depth-Anything-Tensorrt) [![ComfyUI-Upscaler-Tensorrt](https://img.shields.io/badge/ComfyUI--Upscaler--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Upscaler-Tensorrt) [![ComfyUI-Dwpose-Tensorrt](https://img.shields.io/badge/ComfyUI--Dwpose--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Dwpose-Tensorrt) [![ComfyUI-Rife-Tensorrt](https://img.shields.io/badge/ComfyUI--Rife--Tensorrt-blue?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Rife-Tensorrt) [![ComfyUI-Whisper](https://img.shields.io/badge/ComfyUI--Whisper-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Whisper) [![ComfyUI_InvSR](https://img.shields.io/badge/ComfyUI__InvSR-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI_InvSR) [![ComfyUI-FLOAT](https://img.shields.io/badge/ComfyUI--FLOAT-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-FLOAT) [![ComfyUI-Thera](https://img.shields.io/badge/ComfyUI--Thera-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Thera) [![ComfyUI-Video-Depth-Anything](https://img.shields.io/badge/ComfyUI--Video--Depth--Anything-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-Video-Depth-Anything) [![ComfyUI-PiperTTS](https://img.shields.io/badge/ComfyUI--PiperTTS-gray?style=flat-square)](https://github.com/yuvraj108c/ComfyUI-PiperTTS) Special thanks to [livepeer.org](https://www.livepeer.org/) for having supported the project! [![buy-me-coffees](https://i.imgur.com/3MDbAtw.png)](https://www.buymeacoffee.com/yuvraj108cZ) [![paypal-donation](https://i.imgur.com/w5jjubk.png)](https://paypal.me/yuvraj108c) --- ## ⏱️ Performance (Depth Anything V1) _Note: The following results 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 | | H100 | Depth-Anything-L | 518x518 | 1280x720 | 125+ | ## ⏱️ Performance (Depth Anything V2) _Note: The following results were benchmarked on FP16 engines inside ComfyUI_ | Device | Model | Model Input (WxH) | Image Resolution (WxH) | FPS | | :----: | :--------------: | :---------------: | :--------------------: | :-: | | H100 | Depth-Anything-S | 518x518 | 1280x720 | 213 | | H100 | Depth-Anything-B | 518x518 | 1280x720 | 180 | | H100 | Depth-Anything-L | 518x518 | 1280x720 | 109 | ## ⏱️ Performance (Depth Anything V3) _Note: The following results were benchmarked on FP16 engines inside ComfyUI_ | Device | Model | Model Input (WxH) | Image Resolution (WxH) | FPS | | :----: | :--------------: | :---------------: | :--------------------: | :-: | | RTX5090 | DA3Mono-Large | 518x518 | 1280x720 | 85 | | RTX5090 | DA3Metric-Large | 518x518 | 1280x720 | 85 | ## ⏱️ Performance (Distill Any Depth) _Note: The following results were benchmarked on FP16 engines inside ComfyUI_ | Device | Model | Model Input (WxH) | Image Resolution (WxH) | FPS | | :----: | :--------------: | :---------------: | :--------------------: | :-: | | H100 | Distill-Any-Depth-Multi-Teacher-Small | 518x518 | 1280x720 | 76 | | H100 | Distill-Any-Depth-Multi-Teacher-Base | 518x518 | 1280x720 | 68 | | H100 | Distill-Any-Depth-Multi-Teacher-Large | 518x518 | 1280x720 | 59 | | H100 | Distill-Any-Depth-Dav2-Teacher-Large-2w-iter | 518x518 | 1280x720 | 57 | ## 🚀 Installation Navigate to the ComfyUI `/custom_nodes` directory ```bash git clone https://github.com/yuvraj108c/ComfyUI-Depth-Anything-Tensorrt.git cd ./ComfyUI-Depth-Anything-Tensorrt pip install -r requirements.txt ``` ## 🛠️ Building TensorRT Engine There are two ways to build TensorRT engines: ### Method 1: Using the EngineBuilder Node 1. Insert node by `Right 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. ### Method 2: Manual Building 1. Download one of the available onnx models: - [Depth Anything v1](https://huggingface.co/yuvraj108c/Depth-Anything-Onnx/tree/main) - [Depth Anything v2](https://huggingface.co/yuvraj108c/Depth-Anything-2-Onnx/tree/main) - [Depth Anything v3](https://huggingface.co/yuvraj108c/Depth-Anything-3-Onnx/tree/main) - [Distill Any Depth](https://huggingface.co/yuvraj108c/distill-any-depth-onnx/tree/main) 2. Run the export script, e.g ```bash 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 ## ☀️ Usage ### Depth Anything Tensorrt (Basic) - Insert node by `Right Click -> tensorrt -> Depth Anything Tensorrt` - Choose the appropriate engine from the dropdown - Returns a grayscale depth image (IMAGE type) ready for direct use in workflows ### Depth Anything Advanced + Temporal Stabilizer + Depth Map Display For more control over depth visualization, use the advanced pipeline: ```text Depth Anything Tensorrt Advanced │ depths ▼ Depth Temporal Stabilizer Fast GPU (optional, recommended for video) │ depths ▼ Depth Map Display ``` 1. **Depth Anything Tensorrt Advanced** (`Right Click -> tensorrt -> Depth Anything Tensorrt Advanced`) * Returns raw linear depth values instead of a processed image. 2. **Depth Temporal Stabilizer Fast GPU** (`Right Click -> tensorrt -> Depth Temporal Stabilizer Fast GPU`) * Reduces mild frame-to-frame flickering and relative depth-range pulsing using fast CUDA temporal smoothing. * Very high smoothing values can cause trailing on fast-moving objects or strong camera motion. | Parameter | Default | Range | Description | | -------------------- | ------- | ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------- | | `temporal_strength` | 0.45 | 0.0 – 0.95 | Controls how strongly stable pixels inherit depth from the previous stabilized frame. Higher values reduce more flicker but may introduce trails. | | `depth_consistency` | 0.05 | 0.001 – 0.50 | Controls which depth changes are considered stable enough to smooth. Lower values better preserve motion and object edges. | | `align_depth_range` | true | true/false | Corrects frame-to-frame global relative-depth scale and offset pulsing before temporal smoothing. | | `alignment_strength` | 0.70 | 0.0 – 1.0 | Controls how strongly global depth-range alignment is applied. Increasing this usually has less ghosting risk than increasing temporal smoothing. | 3. **Depth Map Display** (`Right Click -> tensorrt -> Depth Map Display`) * Visualizes raw depth values using colormaps with the following adjustments: | Parameter | Default | Range | Description | | ----------------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------ | | `colormap` | — | grayscale, inferno, viridis, plasma, magma, turbo, jet, hot, cool, spring, summer, autumn, winter, bone, rainbow, ocean, hsv, parula, pink | Color scheme for depth visualization | | `invert` | false | true/false | Flip depth so near becomes far and vice versa | | `contrast` | 1.0 | 0.1 – 5.0 | Spread of depth values around the midpoint | | `brightness` | 0.0 | -1.0 – 1.0 | Shifts all depth values up or down | | `gamma` | 1.0 | 0.1 – 5.0 | Non-linear tone curve. Below 1.0 reveals detail in distant regions, above 1.0 in near regions | | `percentile_clip` | 2.0 | 0.0 – 20.0 | Clips outlier depth values at this percentile from both ends before normalizing. Prevents extreme values from compressing the useful range | ## 📝 Changelog - 03/06/2026 - Added fast GPU-based temporal depth stabilizer node to reduce flickering in video depth maps - 02/06/2026 - Added example workflows - 31/01/2026 - Added multiple depth colormaps - Added Depth Map Display adjustments: contrast, brightness, gamma, percentile clipping - Added tooltips, descriptions, and output tooltips to all nodes - 29/01/2026 - Major refactoring (file structure, logging) - Moved model definitions to `config/models.json` - Use huggingface_hub to download onnx models - 10/01/2026 - Add partial support for [Depth Anything V3](https://github.com/ByteDance-Seed/Depth-Anything-3) (DA3Mono-Large, DA3Metric-Large) - 16/09/2025 - Add support for v2 metric models (depth_anything_v2_metric_hypersim_vitl, depth_anything_v2_metric_vkitti_vitl) https://github.com/yuvraj108c/ComfyUI-Depth-Anything-Tensorrt/pull/21 - 08/07/2025 - Add support for [Distill-Any-Depth](https://github.com/Westlake-AGI-Lab/Distill-Any-Depth) - Add benchmark for Distill-Any-Depth models - 20/05/2025 - Merge [PR#15](https://github.com/yuvraj108c/ComfyUI-Depth-Anything-Tensorrt/pull/15) for auto engine building inside comfyui by [ryanontheinside](https://github.com/ryanontheinside) - Merge [PR#14](https://github.com/yuvraj108c/ComfyUI-Depth-Anything-Tensorrt/pull/14) for configurable params in export_trt.py by [rickstaa](https://github.com/rickstaa) - 02/07/2024 - Add Depth Anything V2 onnx models + benchmarks - Merge [PR](https://github.com/yuvraj108c/ComfyUI-Depth-Anything-Tensorrt/pull/9) for engine caching in memory by [BuffMcBigHuge](https://github.com/BuffMcBigHuge) - 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) ## 👏 Credits - [NVIDIA/Stable-Diffusion-WebUI-TensorRT](https://github.com/NVIDIA/Stable-Diffusion-WebUI-TensorRT) - [spacewalk01/depth-anything-tensorrt](https://github.com/spacewalk01/depth-anything-tensorrt) - [martenwikman/depth-anything-tensorrt-docker](https://github.com/martenwikman/depth-anything-tensorrt-docker) - [Westlake-AGI-Lab/Distill-Any-Depth](https://github.com/Westlake-AGI-Lab/Distill-Any-Depth) - [kijai/ComfyUI-DepthAnythingV2](https://github.com/kijai/ComfyUI-DepthAnythingV2)

AI Tools ML Frameworks
131 Github Stars