Skip to content

AI-powered system that converts hand-drawn website sketches into functional HTML/CSS using computer vision.

Notifications You must be signed in to change notification settings

krishnasingh281/sketch2website

Repository files navigation

✏️ Sketch2Website

Python Docker Status License

Sketch2Website is an AI-powered web application that converts hand-drawn website sketches into functional HTML/CSS code.
The goal is simple: reduce the gap between design and development using computer vision and AI.


🚀 Features

  • 🖼️ Upload hand-drawn UI sketches
  • 🔍 Detect layout and UI elements using Vision APIs
  • 🧠 AI-assisted conversion of sketches into HTML/CSS
  • 🐳 Fully Dockerized setup for easy development & deployment
  • 🔐 Environment-based configuration using .env
  • ⚙️ Scalable backend architecture

🛠️ Tech Stack

Backend

  • Python
  • Flask / Django-style architecture
  • Computer Vision APIs (Google Vision or similar)

Frontend

  • HTML, CSS (static templates)

DevOps

  • Docker
  • Docker Compose
  • Nginx (proxy layer)
  • Shell scripts for automation

⚙️ Setup Instructions

1️⃣ Clone the Repository

git clone https://github.com/krishnasingh281/sketch2website.git
cd sketch2website

2️⃣ Set Up Environment Variables

Create a .env file using the sample:

cp .env.sample .env

Update the values inside .env with your API keys and configuration.

3️⃣ Run with Docker Compose

docker-compose up --build

The application will be available at:

http://localhost:8000

##🔑 Environment Variables

Example variables you may need: VISION_API_KEY= SECRET_KEY= DEBUG=True (Refer to .env.sample for the full list.)


##🧪 Development Notes

  • Make sure Docker and Docker Compose are installed.
  • This project is backend-focused; frontend templates are intentionally minimal.
  • The architecture is designed to be extensible for future AI model integrations.

📈 Future Improvements

  • 🤖 Support for multiple AI models (open-source alternatives)

  • 📤 Export code as ZIP / GitHub repo

  • 🧩 Component-level detection (buttons, navbars, cards)

  • ☁️ Cloud deployment (AWS / GCP)


🤝 Contributing

Contributions are welcome!

  • Fork the repo
  • Create a new branch
  • Commit your changes
  • Open a Pull Request

📜 License

This project is licensed under the MIT License.

🙌 Author

Krishna Singh Backend Developer | AI & Web Enthusiast

⭐ If you find this project interesting, give it a star — it helps more than you think!


About

AI-powered system that converts hand-drawn website sketches into functional HTML/CSS using computer vision.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published