Update README.md

README.md

@@ -1,42 +1,27 @@
 ---
-title: AI Image Describer
-emoji: 📷
+title: LLaVA Image Describer
+emoji: 🦙
 colorFrom: blue
 colorTo: purple
 sdk: streamlit
-sdk_version: "1.32.0"
+sdk_version: "1.28.0"
 app_file: app.py
 pinned: false
 ---
 
-# 🌍 Multilingual Image Describer
-
-A web-based application that generates image descriptions in multiple languages using Vision-Language Models (VLMs).
+# 🦙 LLaVA Image Describer
+Upload or capture images → Get real AI descriptions in 9 languages.
 
 ## Features
-- 📷 Multiple image sources (Upload, Camera, Samples)
-- 🌍 Support for 12+ languages
-- ⚡ Real-time image analysis
-- 🎯 Detailed object and scene descriptions
-- 🔄 Customizable output settings
+- 🦙 **Real LLaVA AI analysis** of each image
+- 📸 **Upload or camera capture**
+- 🌍 **9 languages** with country flags
+- 🔍 **Unique descriptions** for every image
+- 📥 **Download** analysis as text
 
 ## How to Use
-1. **Select Language**: Choose your preferred output language
-2. **Choose Image Source**: Upload, take a photo, or use samples
-3. **Generate**: Click "Generate Description" button
-4. **View Results**: See the description in your selected language
-
-## Models Used
-- **BLIP**: For detailed image captioning
-- **BLIP-2**: For advanced scene understanding (optional)
-
-## Deployment on Hugging Face
-This app is configured to run on Hugging Face Spaces with:
-- Python 3.9+
-- PyTorch
-- Transformers library
-
-## Local Development
-```bash
-pip install -r requirements.txt
-streamlit run app.py
+1. Upload or capture an image
+2. Select language (9 options)
+3. Choose description style
+4. Click "ANALYZE WITH LLaVA"
+5. Get unique AI-generated description