Skip to content

Vanshika135-svvv/GEN-AI-task2

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

⚡ TASK-02: NEURAL VISIONS // AI IMAGE GEN

Prodigy InfoTech Internship // Generative AI Track

🚀 LIVE DEPLOYMENT

Check out the live version of this project here: 👉 View Live App on Vercel

🛸 Project Overview

Task-02 utilizes Stable Diffusion XL to transform text into imagery via a U-Net architecture, bridging a reactive Neo-Brutalist frontend with remote GPU clusters through a Flask-based Client-Server model for instantaneous Base64 DOM injection.


🛠️ Technical Stack

  • Backend: Python / Flask
  • AI Engine: Hugging Face Inference API (SDXL 1.0)
  • Frontend: HTML5, CSS3 (Bento-Grid), JavaScript (ES6+)
  • Deployment: Vercel (Serverless Functions)

✨ Key Features

  • Reactive UI: Gen Z "Neo-Brutalist" aesthetic with bold borders and high-contrast colors.
  • Live Latency Tracker: Real-time JavaScript timer to monitor AI generation speed.
  • Vibe Selectors: One-click style tags for instant prompt engineering.
  • Zero-Storage: Images are handled as Base64 strings for fast, temporary DOM injection.

📂 Project Structure

PRODIGY_TASK2/
├── app.py              # Flask server & AI Logic
├── .env                # Secret API Tokens (Hidden)
├── requirements.txt    # Library dependencies
├── static/
│   └── style.css       # Neo-Brutalist styling
└── templates/
    └── index.html      # Reactive frontend & JS Timer


About

Gemini said Task-02 utilizes Stable Diffusion XL to transform text into imagery via a U-Net architecture, bridging a reactive Neo-Brutalist frontend with remote GPU clusters through a Flask-based Client-Server model for instantaneous Base64 DOM injection.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors