Update README to use GitHub demo.gif URL

- Changed demo.gif reference to external GitHub URL
- Points to https://github.com/HGboda/vision-web-app/raw/master/demo.gif
- Avoids Hugging Face binary file restrictions
- Demo will display properly in README

README.md

@@ -8,6 +8,12 @@ pinned: false
 license: gpl-3.0
 ---
 
+## 🎬 Demo
+
+![Vision LLM Agent Demo](https://github.com/HGboda/vision-web-app/raw/master/demo.gif)
+
+*Live demo showing product comparison analysis with image upload, real-time processing, and detailed results across multiple analysis tabs.*
+
 # Vision LLM Agent - Object Detection with AI Assistant
 
 A multi-model object detection and image classification demo with LLM-based AI assistant for answering questions about detected objects. This project uses YOLOv8, DETR, and ViT models for vision tasks, and TinyLlama for natural language processing. The application includes a secure login system to protect access to the AI features.