Upscale

Automatically upscale and interpolate video files.

Table of Contents

• Usage
• Configuration
• Stats
  • Real-ESRGAN
  • RIFE
  • SVT-AV1
• Requirements
  • Requirements for 1080p, 1080p@48, 4k
  • Requirements for 4k48fps
• Installation
  • Windows
  • Arch Linux

Usage

1. Preparing video file (MKVToolNix)
   • Make sure video file does NOT have an image attachment
   • Video file should have ONE ass subtitle file
   • Name video file similar to the following: Your Title - 01.mkv
2. Place .mkv file inside 0-Source folder
3. Execute python Start.py

Configuration

The Start.py file has two options INSIDE, edit in text editor:

• INTERPOLATE_4K: True or False (wether or not 4k48fps should be outputted)
• MAX_INPUT_WIDTH: '720' (downscales the video to this width, as 1080p upscaling would be insane)

Stats

Note: The VRAM usage is the one reported in nvidia-smi and is system wide. Subtract ~1GB for OS.

Real-ESRGAN

Input	Output	VRAM	RAM	GPU	FPS	OS
1280x720	2120x2880	~4.4GB	~1.8GB	3090 (@360W)	~13.56fps	Windows
1280x720	2120x2880	~4.4GB	~2.4GB	3090 (@350W)	~13.73fps	Linux 🐧

RIFE

Input	Output	VRAM	RAM	GPU	FPS	OS
1080p 23.976fps	1080p 47.952fps	~6.6GB	~4.0GB	3090 (@360W)	~60fps	Windows
1080p 23.976fps	1080p 47.952fps	~7.6GB	~8.4GB	3090 (@350W)	~64fps	Linux 🐧
2160p 23.976fps	2160p 47.952fps	~19.4GB	~8.0GB	3090 (@360W)	~18fps	Windows
2160p 23.976fps	dnf	n/a	~31.0GB (run out of memory)	3090 (@360W)	n/a	Linux 🐧

SVT-AV1

Settings: CRF 26, Preset 6. See encodeCDN.py.

Input	RAM	FPS	CPU	OS
1920x1080	~3.9GB	~76fps	Ryzen 7900x (@130W)	Windows
1920x1080	~4.8GB	~80fps	Ryzen 7900x (@130W)	Linux 🐧
3840x2160	~12.3GB	~35fps	Ryzen 7900x (@130W)	Windows
3840x2160	~13.0GB	~37fps	Ryzen 7900x (@130W)	Linux 🐧

Requirements

• OS: Windows or Linux
• Python: >=3.13
• RAM: Min: 16GB - Recommended: 32GB

Requirements for 1080p, 1080p@48, 4k

• GPU: NVIDIA GPU with 8GB+ of VRAM

Requirements for 4k48fps

• GPU: NVIDIA GPU with 24GB of VRAM

Installation

Windows

1. Download and install Python 3.13 - Check option to add to path
2. Download and install Imagemagick - Check option to install legacy tools (Required for creating player previews thumbs.vtt and sprite.jpg)
3. Download and install MKVToolNix - Add to system path environment manually
4. Download ffmpeg - Either place it inside the MKVToolNix install directory or create a new directory somewhere and add it to system path environment
5. Create a python virtual environment and activate it

   python -m pip install --upgrade pip
   python -m venv .venv
   
   # Activate python venv
   .venv\Scripts\activate
   

6. Install pip packages in venv

   pip install packaging setuptools wheel pymediainfo python-dateutil
   pip install vapoursynth vapoursynth-ffms2
   pip install torch torchvision --index-url https://download.pytorch.org/whl/cu126
   pip install vsrealesrgan vsrife
   

7. Install models used by vsrealesrgan and vsrife

   python -m vsrealesrgan
   python -m vsrife
   

8. Run Start.bat - alternatively: make sure python venv is active with .venv\Scripts\activate, then run python Start.py

Arch Linux

# System Packages
sudo pacman -S python ffmpeg mkvtoolnix-cli mediainfo imagemagick

# Setup virtual environment (in upscale dirctory)
python -m venv .venv
source .venv/bin/activate

# Install pip dependencies
pip install typing-extensions packaging setuptools wheel
pip install pymediainfo python-dateutil
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu126
pip install vapoursynth vapoursynth-ffms2 vsrealesrgan vsrife

# Install models
python -m vsrealesrgan
python -m vsrife