NCNN Executable

Overview

Real-ESRGAN provides portable executable files powered by NCNN and Vulkan. These executables work on Intel/AMD/Nvidia GPUs without requiring Python, PyTorch, or CUDA installation.

The NCNN executable is ideal for users who want a simple, portable solution without setting up a Python environment.

Download Executables

Windows

Download for Windows

Linux

Download for Ubuntu/Linux

MacOS

Download for MacOS

Direct Download Links

# Windows
https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-windows.zip

# Linux
https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-ubuntu.zip

# MacOS
https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesrgan-ncnn-vulkan-20220424-macos.zip

Quick Start

Download and Extract

Download the appropriate executable for your platform and extract the archive.

Run Basic Command

Windows
Linux/MacOS

realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png

./realesrgan-ncnn-vulkan -i input.jpg -o output.png

Check Output

The enhanced image is saved as output.png with 4x upscaling by default.

Command-Line Reference

Basic Syntax

Usage: realesrgan-ncnn-vulkan -i infile -o outfile [options]...

Arguments

-h

flag

Show help message

-i input-path

string

required

Input image path (jpg/png/webp) or directoryExamples:

Single file: -i input.jpg
Directory: -i input_folder

-o output-path

string

required

Output image path (jpg/png/webp) or directoryExamples:

Single file: -o output.png
Directory: -o output_folder

-s scale

integer

default:"4"

Upscale ratio: 2, 3, or 4Example: -s 2 for 2x upscaling

-t tile-size

integer

default:"0"

Tile size (>=32 or 0=auto)

0: Auto tile size
>=32: Manual tile size
Format for multi-GPU: 0,0,0

Use tiling for large images or limited VRAM.

-m model-path

string

default:"models"

Folder path to pre-trained models

-n model-name

string

default:"realesr-animevideov3"

Model name to use. Options:

realesr-animevideov3 (default)
realesrgan-x4plus
realesrgan-x4plus-anime
realesrnet-x4plus

-g gpu-id

string

default:"auto"

GPU device to use

auto: Automatic selection
Single GPU: -g 0, -g 1, etc.
Multi-GPU: -g 0,1,2

-j load:proc:save

string

default:"1:2:2"

Thread count for load/proc/save

Default: 1:2:2
Multi-GPU: 1:2,2,2:2

-x

flag

Enable TTA (Test-Time Augmentation) modeImproves quality but increases processing time.

-f format

string

default:"ext/png"

Output image format: jpg, png, or webp

Default: same as input or PNG

-v

flag

Verbose output (show detailed information)

Available Models

realesr-animevideov3
realesrgan-x4plus
realesrgan-x4plus-anime
realesrnet-x4plus

Default model - Optimized for anime videos and images

# Windows
realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n realesr-animevideov3

# Linux/MacOS
./realesrgan-ncnn-vulkan -i input.jpg -o output.png -n realesr-animevideov3

Size: XS (~8MB)
Best for: Anime images and video frames
Speed: Fast

General purpose model

# Windows
realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n realesrgan-x4plus

# Linux/MacOS
./realesrgan-ncnn-vulkan -i input.jpg -o output.png -n realesrgan-x4plus

Size: ~64MB
Best for: Real-world photos, general images
Speed: Medium

Anime-optimized model

# Windows
realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n realesrgan-x4plus-anime

# Linux/MacOS
./realesrgan-ncnn-vulkan -i input.jpg -o output.png -n realesrgan-x4plus-anime

Size: ~17MB
Best for: Anime illustrations
Speed: Medium-Fast

ESRGAN without GAN (smoother results)

# Windows
realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n realesrnet-x4plus

# Linux/MacOS
./realesrgan-ncnn-vulkan -i input.jpg -o output.png -n realesrnet-x4plus

Size: ~64MB
Best for: When you want smooth results without GAN artifacts
Speed: Medium

Usage Examples

General Images

realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n realesrgan-x4plus

Anime Images

./realesrgan-ncnn-vulkan -i anime.jpg -o output.png -n realesr-animevideov3

Video Frames Processing

Extract Frames

mkdir tmp_frames
ffmpeg -i input.mp4 -qscale:v 1 -qmin 1 -qmax 1 -vsync 0 tmp_frames/frame%08d.png

Process Frames

mkdir out_frames
./realesrgan-ncnn-vulkan -i tmp_frames -o out_frames -n realesr-animevideov3 -s 2 -f jpg

Merge Back to Video

# Get FPS from original
ffmpeg -i input.mp4

# Merge with audio
ffmpeg -r 23.98 -i out_frames/frame%08d.jpg -i input.mp4 \
  -map 0:v:0 -map 1:a:0 -c:a copy -c:v libx264 \
  -r 23.98 -pix_fmt yuv420p output.mp4

Advanced Options

./realesrgan-ncnn-vulkan -i large_image.jpg -o output.png -t 512

Performance Tips

Tile Size SelectionChoose tile size based on your GPU VRAM:

8GB+ VRAM: -t 0 (auto) or no tiling
4-8GB VRAM: -t 512 or -t 400
Less than 4GB VRAM: -t 256 or -t 200

Smaller tiles use less memory but may show slight artifacts at tile boundaries.

Multi-GPU UsageFor systems with multiple GPUs:

./realesrgan-ncnn-vulkan -i input.jpg -o output.png -g 0,1,2 -t 0,0,0

This distributes processing across GPUs 0, 1, and 2.

TTA ModeEnable TTA for potentially better quality (slower):

./realesrgan-ncnn-vulkan -i input.jpg -o output.png -x

TTA applies transformations, processes, then averages results. Best for critical images.

NCNN vs Python Implementation

Advantages
Limitations
Comparison

NCNN Advantages:✓ No Python/PyTorch installation required ✓ Portable executable - works out of the box ✓ Works with Intel/AMD GPUs via Vulkan ✓ Smaller download size ✓ No CUDA requirement ✓ Easier for non-technical users

NCNN Limitations:✗ May produce slightly different results than PyTorch ✗ Potential block inconsistency with tiling ✗ No --outscale for arbitrary scaling ✗ No face enhancement integration ✗ No denoise strength control ✗ Fewer models availableFor maximum quality and features, use the Python implementation.

Feature	NCNN	Python
Setup	Easy	Requires Python
GPU Support	Intel/AMD/Nvidia	Nvidia (CUDA)
Face Enhancement	No	Yes
Arbitrary Scale	No	Yes
Denoise Control	No	Yes
Quality	Very Good	Excellent
Speed	Fast	Fast

Troubleshooting

Vulkan not found error

Install Vulkan drivers for your GPU:Windows:

Nvidia: Install latest GeForce drivers
AMD: Install latest Radeon drivers
Intel: Install latest graphics drivers

Linux:

# Ubuntu/Debian
sudo apt install vulkan-utils

# Check Vulkan
vulkaninfo

MacOS:

macOS 10.15+ includes Vulkan support via MoltenVK

Out of memory error

Reduce tile size:

./realesrgan-ncnn-vulkan -i input.jpg -o output.png -t 256

Or use an even smaller tile size:

./realesrgan-ncnn-vulkan -i input.jpg -o output.png -t 128

Block artifacts in output

This is due to tiling. To minimize:

Use larger tile size (if memory allows):

./realesrgan-ncnn-vulkan -i input.jpg -o output.png -t 512

Use auto tile size:

./realesrgan-ncnn-vulkan -i input.jpg -o output.png -t 0

If possible, disable tiling by using the Python implementation

Model not found error

Ensure models are in the correct directory:

Check the models folder exists in the same directory as the executable
Verify model files are present

Specify custom model path:

./realesrgan-ncnn-vulkan -i input.jpg -o output.png -m /path/to/models

Slow processing on CPU

If using CPU instead of GPU:

Install proper GPU drivers
Verify Vulkan is working: vulkaninfo (Linux)

Specify GPU explicitly:

./realesrgan-ncnn-vulkan -i input.jpg -o output.png -g 0

Additional Resources

Real-ESRGAN-ncnn-vulkan

Official NCNN implementation repository

Python Inference

Full Python implementation with all features

Anime Videos

Process anime videos using NCNN

When to Use NCNN vs Python

Use NCNN When
Use Python When

✓ You don’t have Python installed ✓ You want a simple, portable solution ✓ You have Intel or AMD GPU (no CUDA) ✓ You need quick setup ✓ You’re processing standard images ✓ You don’t need face enhancement

Get Started

Core Concepts

Usage Guides

Training

Models

Resources

Overview

Download Executables

Windows

Linux

MacOS

Direct Download Links

Quick Start

Command-Line Reference

Basic Syntax

Arguments

Available Models

Usage Examples

General Images

Anime Images

Video Frames Processing

Advanced Options

Performance Tips

NCNN vs Python Implementation

Troubleshooting

Additional Resources

Real-ESRGAN-ncnn-vulkan

Python Inference

Anime Videos

When to Use NCNN vs Python

Build docs developers (and LLMs) love

Get Started

Core Concepts

Usage Guides

Training

Models

Resources

​Overview

​Download Executables

Windows

Linux

MacOS

​Direct Download Links

​Quick Start

​Command-Line Reference

​Basic Syntax

​Arguments

​Available Models

​Usage Examples

​General Images

​Anime Images

​Video Frames Processing

​Advanced Options

​Performance Tips

​NCNN vs Python Implementation

​Troubleshooting

​Additional Resources

Real-ESRGAN-ncnn-vulkan

Python Inference

Anime Videos

​When to Use NCNN vs Python

Build docs developers (and LLMs) love

Overview

Download Executables

Direct Download Links

Quick Start

Command-Line Reference

Basic Syntax

Arguments

Available Models

Usage Examples

General Images

Anime Images

Video Frames Processing

Advanced Options

Performance Tips

NCNN vs Python Implementation

Troubleshooting

Additional Resources

When to Use NCNN vs Python