GFPGAN-ncnn-vulkan - GitLite

KO | EN

gitlite — search

#python #golang #android #machine-learning #rust #linux #macos #nodejs #cli #vue #awesome-list #security #mcp #openai

GFPGAN-ncnn-vulkan

(★ 53)

[WIP] NCNN with Vulkan implementation of GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration

File Explorer

Download Latest Version (.zip)

- - build_dev_fedora_lunar_vulkan.yml
  - build_dev_fedora_rpm_vulkan.yml
  - build_dev_ubuntu.yml
  - build_dev_windows.yml
  - release.yml
- dependabot.yml
- .gitignore
- .name
- GFPGAN-ncnn-vulkan.iml
- misc.xml
- modules.xml
- vcs.xml
- - libwebp
  - ncnn
- - face.h
  - gfpgan.h
  - realesrgan.h
- .clang-format
- CMakeLists.txt
- face.cpp
- gfpgan-ncnn-vulkan-demo.cpp
- gfpgan.cpp
- realesrgan.cpp
.gitignore
.gitmodules
.pre-commit-config.yaml
CODE_OF_CONDUCT.md
commitlint.config.js
LICENSE
README.md

# Installation Guide

1. Get the code

git clone https://github.com/onuralpszr/GFPGAN-ncnn-vulkan

Downloads the entire project code from GitHub to your computer.

cd GFPGAN-ncnn-vulkan

Moves into the project folder you just downloaded.

2. CMake

Medium Recommended

Prerequisites

Git Needed to download the project code from GitHub.
CMake The tool used to generate build configuration.
C/C++ 컴파일러 Windows needs Visual Studio (Community edition, free), macOS needs Xcode Command Line Tools, Linux needs the gcc/g++ package.

cmake ..

Analyzes the source code and generates build configuration files (must be run inside the build folder).

cmake --build . --parallel $(($(nproc) - 1))

Type this command into your terminal and run it.

✅ Check that an executable was created inside the build folder, then run it directly (e.g. ./build/app_name).

Pulled directly from this repo's README.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# GFPGAN-ncnn-vulkan 🚀

[![Windows Dev Build](https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/actions/workflows/build_dev_windows.yml/badge.svg)](https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/actions/workflows/build_dev_windows.yml)
[![Ubuntu Dev Build](https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/actions/workflows/build_dev_ubuntu.yml/badge.svg)](https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/actions/workflows/build_dev_ubuntu.yml)
[![Fedora Dev Build (RPM Vulkan)](https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/actions/workflows/build_dev_fedora_rpm_vulkan.yml/badge.svg)](https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/actions/workflows/build_dev_fedora_rpm_vulkan.yml)
[![Fedora Dev Build (Lunar Vulkan SDK)](https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/actions/workflows/build_dev_fedora_lunar_vulkan.yml/badge.svg)](https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/actions/workflows/build_dev_fedora_lunar_vulkan.yml)
[![pre-commit.ci status](https://results.pre-commit.ci/badge/github/onuralpszr/GFPGAN-ncnn-vulkan/main.svg)](https://results.pre-commit.ci/latest/github/onuralpszr/GFPGAN-ncnn-vulkan/main)
![GitHub](https://img.shields.io/github/license/onuralpszr/GFPGAN-ncnn-vulkan?color=red)
[![Open issue](https://img.shields.io/github/issues/onuralpszr/GFPGAN-ncnn-vulkan)](https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/issues)
[![Closed issue](https://img.shields.io/github/issues-closed/onuralpszr/GFPGAN-ncnn-vulkan)](https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/issues)
![GitHub pull requests](https://img.shields.io/github/issues-pr-raw/onuralpszr/GFPGAN-ncnn-vulkan)
![cpp](https://img.shields.io/badge/C++20-Project-blue.svg?style=flat&logo=c%2B%2B)
[![Github All Releases](https://img.shields.io/github/downloads/onuralpszr/GFPGAN-ncnn-vulkan/total.svg)](https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/releases)

Ncnn with Vulkan implementation of **GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration**

This repository contains the code and pre-trained models for a real-world face restoration algorithm based on the [GFPGAN](https://github.com/TencentARC/GFPGAN) method and optimized for mobile devices using the [NCNN](https://github.com/Tencent/ncnn) framework with a Vulkan backend.

The goal of this project is to develop practical algorithms that can restore the appearance of damaged or low-quality face images, such as those obtained from security cameras, old photographs, or social media profiles. The proposed approach combines the power of deep learning with the speed and efficiency of hardware acceleration, making it suitable for real-time applications on smartphones, drones, or robots.

## Clone Project and Get Submodules

Make sure submodules are initialized and updated

```console
git clone https://github.com/onuralpszr/GFPGAN-ncnn-vulkan.git
git submodule update --init --recursive
```

## Clone project with Submodules

```sh
git clone --recursive https://github.com/onuralpszr/GFPGAN-ncnn-vulkan.git
```

## Project Prerequisites ⚙️

- CMake version 3.20 or later
- C++17 or above with filesystem support
- Clang-Tidy for code analysis (optional)
- Threads library
- Vulkan SDK
- glslangValidator executable
- OpenCV library
- OpenMP library
- ncnn library
- libwebp library

## Building 🛠️

Configure and build

```sh
mkdir -p build && cd build
cmake ..
cmake --build . --parallel $(($(nproc) - 1))
```

## :construction: Model support :construction:

1. GFPGANCleanv1-NoCE-C2

### TODO: :bookmark_tabs:

- [x] Support ncnn-vulkan
- [ ] Convert pth->onnx->ncnn
- [ ] Model with colorization

### References

1. <https://github.com/xinntao/Real-ESRGAN>
2. <https://github.com/TencentARC/GFPGAN>
3. <https://github.com/xinntao/Real-ESRGAN-ncnn-vulkan>
4. <https://github.com/Tencent/ncnn>
5. <https://github.com/Tencent/ncnn/tree/master/tools/pnnx>
6. <https://github.com/pnnx/pnnx>
7. <https://github.com/deepcam-cn/yolov5-face>
8. <https://github.com/derronqi/yolov7-face>
9. <https://github.com/derronqi/yolov8-face>
10. <https://github.com/FeiGeChuanShu/GFPGAN-ncnn>
11. <https://github.com/ultralytics/ultralytics>

## Download Model files (GFPGAN-ncnn model files)

### Models-v0.0.1

<https://github.com/onuralpszr/GFPGAN-ncnn-vulkan/releases/download/v0.0.1-models/GFPGAN-ncnn-models.zip>