Giter Club home page Giter Club logo

paint-with-ml's Introduction

paint-with-ml

This app uses a version of the GauGAN deep learning model to transform an input segmentation masks into a landscape painting.

GauGAN, released in 2019, is the most powerful image-to-image translation algorithm currently known. This version of the model has been trained on the popular ADE20K dataset, then fine-tuned on a dataset of 250 paintings from Bob Ross's beloved PBS series, "The Joy of Painting".

Choose from nine different semantic brushes to craft your painting. Then click on the "Run" button to generate a result! Here are some example outputs:

Try it out yourself by visiting paintwith.spell.ml. To learn more about how this model was built and served, check out the accompanying article on the Spell blog.

Project hierarchy

├── LICENSE
├── README.md             <- You're reading it!
├── lib/                  <- Vendored model code (Python).
│   ├── SPADE-master/     <- Vendored copy of NVlabs/SPADE.* **
│   └── model_server/     <- Model server code (uses Spell model serving).
├── models                <- Model assets
│   ├── model_0.py        <- The build script for the first model trained.
│   ├── ...
│   ├── model_N.py        <- The build script for the last model trained.
│   └── README.md         <- Reference to the models builds.
├── notebooks             <- Jupyter notebooks discussing the model build process.
├── requirements.txt      <- Project environment requirements, installable with pip.
├── app/                  <- User-facing demo React web app.
│   ├── README.md         <- Reference on how to build and serve the web app.
│   ├── index.html
│   ├── components/       <- React components.
│   ├── models/           <- Model configs (see model_server/).
│   ├── static/
│   ├── requirements.txt  <- Web app Python requirements, installable with pip.
|   └── package.json      <- Web app JS requirements, installable with npm.
├── Dockerfile            <- Dockerfile bundling the web application.
└── .gitignore

*  Also contains a copy of vacancy/Synchronized-BatchNorm-PyTorch, a NVlabs/SPADE requirement
** Code has minor modifications made for compatibility with the Jupyter environment

paint-with-ml's People

Contributors

residentmario avatar dependabot[bot] avatar

Watchers

James Cloos avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.