Image to Sketch: input
Image to Sketch: output
Style Art: original
Style Art: output
Machine learning is a hot topic. I want to learn more about AI. So I decided to use build an AI-driven app to show off my skill.
What it does
This application has three cool features.
- 1: Image2Sketch: Transform a painting to sketch.
- 2: Colorization: The AI can create its own color style to paint on a sketch.
- 3: StyleArt: Combining the content of one image with the style of another image.
How I built it
Back-End: Node.js, MongoDB, Nodemon, Express, Mongoose, Multer, ShellJS
Machine Learning Models: STYLE2PAINTS 2.1, sketchKeras, neural-style
Challenges I ran into
I have a hard time writing a custom API. The custom API aims to serve as a communication portal between the mobile application and the server. Handling POST/GET request traffic is complicated. Fortunately, stackoverflow is here for me.
Accomplishments that I'm proud of
The project is done. I am very proud of myself.
What I learned
I learned how to build a NodeJS server, use TeleSign API and using Machine Learning models to enhance my mobile application.
What's next for ANIME is LYFE!!!
I will make it open source. You are more than welcome to take a look and fork it.