SketchGen: Transform Your Imagination into Images✨

SketchGen is an innovative tool that allows users to generate realistic images from text descriptions or sketches. Powered by the Stable Diffusion 3.5 model, it combines cutting-edge AI with creative freedom to produce stunning visuals from user inputs.

Features 🚀

• Text-to-Image Generation: Enter a text prompt and let the AI create images based on your imagination. 📝➡️🖼️
• Sketch-to-Image Generation: (Coming soon...) Convert your rough sketches into realistic images. ✏️➡️🖼️
• Customization Options:
  • Style Selection: Choose from Default, Photorealistic, or Anime styles. 🎨
  • Image Resolution: Select from 512x512, 768x768, or 1024x1024 resolution. 🖥️
  • Fine-tune with Inference Steps and Guidance Scale for better control over the generated image. ⚙️

Demo 💻

You can try out the application on Streamlit.

Example Generated Images 📸

Here are some images generated using my SketchGen app:

Installation 🛠️

1. Clone the repository:

   git clone https://github.com/miteshgupta07/SketchGen.git

2. Navigate into the project directory:

   cd sketchgen

3. Install the dependencies:

   pip install -r requirements.txt

4. Run the Streamlit app:

   streamlit run app.py

Usage 💡

• Open the app and select between "Generate with Prompt" or "Generate with Image".
• For text generation: Enter a prompt (e.g., "A cat on Mars") and hit Generate. 📝➡️🖼️
• For image generation: Upload a sketch and generate a detailed image based on your sketch. ✏️➡️🖼️
• Customize your image with options such as style, resolution, and AI parameters. 🎨🔧
• Download the generated image by clicking the Download button. ⬇️

Technologies Used 🛠️

• Python 🐍
• Streamlit: Framework for building the interactive web app. 💻
• Hugging Face: Hosted the Stable Diffusion 3.5 model. 🤗
• PIL: Image manipulation. 🖼️
• diffusers: For handling the image generation using Stable Diffusion. 💨

Future Improvements 🚧

• Sketch-to-Image: Convert sketches into detailed images (Coming soon). ✏️➡️🖼️
• More Image Styles: Additional AI models for unique image styles. 🎨

Acknowledgment 🙏

We would like to express our gratitude to the following:

• Hugging Face: For providing access to the Stable Diffusion 3.5 model. 🤗
• Streamlit: For offering a fantastic framework to build and deploy the web app. 💻
• Python and Libraries: For being the backbone of our project with libraries like PIL and diffusers. 🐍
• The Open-Source Community: For providing inspiration and valuable resources that helped shape this project. 🌍

Thank you to everyone who contributed to this project, whether directly or indirectly! 🙌

Contributing 🤝

Feel free to fork the project and submit pull requests. If you have any feature requests or bugs to report, please open an issue. 🛠️

License 📜

This project is licensed under the MIT License - see the LICENSE file for details. 🏷️