---

🚀 Project Overview

The AI-Powered E-commerce Product Listing Generator is a groundbreaking project that automates the generation of product titles and bullet-point descriptions using AI. It takes a product image as input and returns a well-written, SEO-optimized product listing ready for any e-commerce platform.

---

🧠 Key Features

• ✨ End-to-End AI Workflow: Transforms product images into SEO-optimized titles and listings with zero manual input.
• 🖼️ Visual Intelligence with LLAVA: Performs deep visual analysis using LLAVA’s multimodal AI to extract detailed product insights from images.
• ✍️ Human-Like Text Generation: Utilizes the Mistral model to create fluent, engaging, and context-aware product descriptions and titles.
• 💻 Intuitive Streamlit Interface: Upload, preview, and generate product listings through a sleek, responsive frontend that’s beginner-friendly.
• 🔐 Token-Based API Authentication: Ensures secure communication between the models and frontend using Hugging Face and ngrok tokens.
• ☁️ 100% Free & Cloud-Based: Powered entirely by free-tier services like Google Colab, Hugging Face Spaces, and ngrok — no local setup required.
• ⚡ Plug-and-Play Ready: Lightweight and modular design makes it easy to integrate with your e-commerce backend or inventory systems.

---

🖼️ Demo

---

🛠️ Technologies Used

---

📁 Project Structure

AI-Powered-Ecommerce-Product-Listing-Generator/
├── LLAVA-Model.ipynb                 # Image understanding using LLAVA
├── Mistral-Model.ipynb               # Product listing generation using Mistral
├── Frontend-UI.py                    # Streamlit frontend
├── assets/
│   └── demo.gif                      # Demonstration GIF
└── README.md                         # Documentation

---

🔧 Prerequisites

• Hugging Face Token: Create one here
• ngrok Token: Create one here

---

⚙️ Installation & Setup

1. Clone the Repository

git clone https://github.com/GothiProCoder/AI-Powered-Ecommerce-Product-Listing-Generator.git
cd AI-Powered-Ecommerce-Product-Listing-Generator

2. Run Mistral Notebook

• Open Mistral-Model.ipynb in Google Colab
• Enter Hugging Face and ngrok tokens in their respective placeholder values within the codes itself
• Run all cells sequentially
• Copy the final Mistral API URL

3. Run LLAVA Notebook

• Open LLAVA-Model.ipynb
• Enter Hugging Face and ngrok tokens in their respective placeholder values within the codes itself
• Paste Mistral API URL in the last cell by replacing the MISTRAL-MODEL-NGROK-API-URL placeholder text
• Run all cells sequentially
• Copy the LLAVA API URL

4. Launch Streamlit Frontend

• Replace 'ENTER-LLAVA-NGROK-API-URL' with the actual LLAVA API URL

• streamlit run Frontend-UI.py

---

📈 Example Output

• Input: Image of a T-shirt
• Generated Title: Classic Cotton Round Neck T-Shirt - Unisex Fit
• Description: Crafted from 100% breathable cotton, this round-neck t-shirt offers unmatched comfort and a stylish fit for all-day wear.

---

🤝 Contributing

We welcome contributions! Please fork the repository, make your changes, and submit a pull request. For major changes, please open an issue first to discuss what you'd like to change.

---

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

---

📬 Contact

Developed by GothiProCoder
Reach me on Email | LinkedIn