Himanshu2003/PixelWhiz

🌟 PixelWhiz: See the Unseen 🌟

🧠 Summary

PixelWhiz is an interactive Streamlit web app that allows users to upload an image and optionally ask a question about it. Using Google’s Gemini model, the app analyzes the image and provides AI-generated responses — from identifying objects and describing scenes to answering context-specific questions.

⚙️ How It Works

1. 1.The user uploads an image (.jpg, .jpeg, or .png) and optionally types a question.
2. 2.The image and text input are sent to Google’s Gemini 2.5 Flash model using the google-generativeai API.
3. 3.The model processes the input and returns a descriptive or analytical text response.
4. 4.The response is displayed on the Streamlit interface.

🧩 Tech Stack

• —Frontend: Streamlit
• —AI Model: Google Gemini 2.5 Flash
• —Image Processing: Pillow (PIL)
• —Language: Python 3