Update README.md

README.md

@@ -1,12 +1,28 @@
+# 🧠 Variational Autoencoder (VAE) Interactive Playground
+
+An interactive Flask web app that lets you **train, visualize, and generate MNIST digits** using a Variational Autoencoder (VAE).  
+Built with **PyTorch**, **Flask**, and **Matplotlib**.
+
 ---
-title: Vae
-emoji: 🌖
-colorFrom: yellow
-colorTo: pink
-sdk: gradio
-sdk_version: 5.49.1
-app_file: app.py
-pinned: false
+
+## 🚀 Features
+- Train a VAE model directly in your browser
+- Real-time loss visualization
+- Latent space plotting (2D)
+- Reconstruction and generation of handwritten digits
+- Adjustable architecture and hyperparameters
+
+---
+
+## 🧩 Tech Stack
+- **Flask** for the web interface
+- **PyTorch** for model training
+- **Matplotlib** for plots
+- **Threading** for non-blocking training
+
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## ⚙️ Run locally
+```bash
+pip install -r requirements.txt
+python app.py