ICO-GEN is a powerful tool that helps you generate icons using large language models (LLMs) and stable diffusion. Whether you need custom icons or want to edit existing ones, ICO-GEN makes it easy to create and download icons in multiple formats.
This project leverages modern AI technologies to generate high-quality icons that can be used in web development, mobile apps, or any other digital platform.
- Next.js
- TailwindCSS
- FastAPI
- Python
- Langchain
- Gemini API
ICO-GEN comes with the following features to help you create the perfect icons:
- Generate SVG images for icons automatically
- Edit SVG properties such as shape, color, and size
- Download generated images in multiple formats (SVG, PNG, JPEG)
- Expand customization options (coming soon)
- Edit Existing Icons (coming soon)
To get started, you'll need to install both the backend and frontend dependencies. Follow the steps below.
-
Clone the Repository:
Clone the project to your local machine using the command below:git clone https://github.com/your-repo/ico-gen.git cd ico-gen/backend
-
Install Dependencies:
Install the required Python packages by running:pip install -r requirements.txt
-
Navigate to Frontend Directory:
Move to the frontend folder by using the following command:cd ../frontend/iconify
-
Install Dependencies:
Use npm to install the necessary packages for the frontend:npm install
Once you've installed all the dependencies, you can start the project.
To run the backend server using FastAPI:
python main.py
To start the frontend development server:
npm run dev
The frontend server will run on localhost:3000
by default, and the backend API will be available at localhost:8000
.
We are always looking for people to contribute to this project! If you have any improvements or new features you'd like to add, feel free to fork the project and create a pull request.
Before contributing, please check out the CONTRIBUTING.md to learn about the contribution guidelines.
This project is licensed under the MIT License.
If you have any questions or feedback, feel free to reach out via email or open an issue on GitHub. Contributions and suggestions are always welcome!