ComfyUI Rife TensorRT ⚡

This project provides a TensorRT implementation of RIFE for ultra fast frame interpolation inside ComfyUI

This project is licensed under CC BY-NC-SA, everyone is FREE to access, use, modify and redistribute with the same license.

If you like the project, please give me a star! ⭐

---

⏱️ Performance

Note: The following results were benchmarked on FP16 engines inside ComfyUI, using 2000 frames consisting of 2 alternating similar frames, averaged 2-3 times

Device	Rife Engine	Resolution	Multiplier	FPS
H100	rife49_ensemble_True_scale_1_sim	512 x 512	2	45
H100	rife49_ensemble_True_scale_1_sim	512 x 512	4	57
H100	rife49_ensemble_True_scale_1_sim	1280 x 1280	2	21

🚀 Installation

Navigate to the ComfyUI /custom_nodes directory

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

🛠️ Supported Models

The following RIFE models are supported and will be automatically downloaded and built:

• rife49_ensemble_True_scale_1_sim (default) - Latest and most accurate
• rife48_ensemble_True_scale_1_sim - Good balance of speed and quality
• rife47_ensemble_True_scale_1_sim - Fastest option

Models are automatically downloaded from HuggingFace and TensorRT engines are built on first use.

☀️ Usage

1. Load Model: Insert Right Click -> Add Node -> tensorrt -> Load Rife Tensorrt Model

   • Choose your preferred RIFE model (rife47, rife48, or rife49)
   • Select precision (fp16 recommended for speed, fp32 for maximum accuracy)
   • The model will be automatically downloaded and TensorRT engine built on first use

2. Process Frames: Insert Right Click -> Add Node -> tensorrt -> Rife Tensorrt

   • Connect the loaded model from step 1
   • Input your video frames
   • Configure interpolation settings (multiplier, CUDA graph, etc.)
   • Image resolutions between 256x256 and 3840x3840 are supported

🤖 Environment tested

• WSL Ubuntu 24.04.03 LTS, Cuda 12.9, Tensorrt 10.13.3.9, Python 3.12.11, RTX 5080 GPU
• Windows (Not tested, but should work)

🚨 Updates

December 2025

• Automatic Model Management: No more manual downloads! Models are automatically downloaded from HuggingFace and TensorRT engines are built on demand
• Improved Workflow: New two-node system with Load Rife Tensorrt Model + Rife Tensorrt for better organization
• Updated Dependencies: TensorRT updated to 10.13.3.9 for better performance and compatibility

👏 Credits

• https://github.com/styler00dollar/VSGAN-tensorrt-docker
• https://github.com/Fannovel16/ComfyUI-Frame-Interpolation
• https://github.com/hzwer/ECCV2022-RIFE

License

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