Skip to content

Implementation of Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization. Give your image the art style you want.

Notifications You must be signed in to change notification settings

mcjmk/transfer-style

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

39 Commits
 
 
 
 
 
 

Repository files navigation

Transfer Style

Web application that transforms images by applying artistic styles using deep learning. Based on the paper Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization.

Prerequisites

  • Node.js (v14 or higher)
  • Python 3.11
  • Conda (Miniconda or Anaconda)

Installation

Backend Setup

cd backend
conda env create -f environment.yml
conda activate transfer-style
uvicorn server:app --reload

Frontend Setup

cd frontend
npm install
npm start

Usage

  1. Open http://localhost:3000
  2. Upload content image
  3. Upload style image
  4. Click "Generate"

Tech Stack

  • Backend: FastAPI + PyTorch
  • Frontend: React + Bootstrap
  • Model: AdaIN architecture trained on WikiArt and MSCOCO datasets

Acknowledgments

Based on the work of Huang et al. (ICCV 2017) and uses pre-trained VGG models.

About

Implementation of Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization. Give your image the art style you want.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •