This project provides a 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)

⭐ Support

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

⏱️ Performance

Note: The following results were benchmarked on FP16 engines inside ComfyUI, using 100 identical frames

🚀 Installation

• Install via the manager
• Or, navigate to the /ComfyUI/custom_nodes directory

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

pip install tensorrt-rtx 

🛠️ Supported Models

• These upscaler models have been tested to work with Tensorrt. Onnx are available here

• The exported tensorrt models support dynamic image resolutions from 256x256 to 1280x1280 px (e.g 960x540, 512x512, 1280x720 etc).

  • 4x-AnimeSharp
  • 4x-UltraSharp
  • 4x-WTP-UDS-Esrgan
  • 4x_NMKD-Siax_200k
  • 4x_RealisticRescaler_100000_G
  • 4x_foolhardy_Remacri
  • RealESRGAN_x4
  • 4xNomos2_otf_esrgan
  • 4x-ClearRealityV1
  • 4x_UniversalUpscalerV2-Neutral_115000_swaG
  • 4x-UltraSharpV2_Lite
  • 2x-ESRGAN
  • 1x-ITF-SkinDiffDetail-Lite-v1

☀️ Usage

• Load example workflow
• 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
• Place the onnx model in /ComfyUI/models/onnx/YOUR_MODEL.onnx
• Then, add your model to this list 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 (PR#82 by @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 by @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
• comfyanonymous/ComfyUI

License

Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)