Update app.py

app.py

@@ -27,7 +27,7 @@ st.set_page_config(
 
 # Main title and description
 st.title("Deepfake Image Analyser")
-st.markdown("Analyze images for deepfake manipulation with multi-stage analysis")
+st.markdown("Analyse images for deepfake manipulation")
 
 # Check for GPU availability
 def check_gpu():
@@ -42,19 +42,31 @@ def check_gpu():
 # Sidebar components
 st.sidebar.title("About")
 st.sidebar.markdown("""
-This analyzer performs multi-stage detection:
-1. **Initial Detection**: CLIP-based classifier
-2. **GradCAM Visualization**: Highlights suspicious regions
-3. **Image Captioning**: BLIP model describes the image content
-4. **LLM Analysis**: Fine-tuned Llama 3.2 Vision provides detailed explanations
-
-The system looks for:
-- Facial inconsistencies
-- Unnatural movements
-- Lighting issues
-- Texture anomalies
-- Edge artifacts
-- Blending problems
+### About Deepfake Analyzer
+This tool performs multi-stage deepfake detection using advanced AI models:
+
+**CLIP Model**: Initial Real/Fake classification with confidence score
+**GradCAM**: Visualization of suspicious regions via heat map
+**BLIP**: Structured description of image content
+**Llama 3.2 Vision**: Detailed explanation of potential manipulation
+
+### How to Use
+
+**Load Models**:
+- Begin with CLIP (required for basic detection)
+- Add BLIP for enhanced descriptions
+- Add Vision LLM for in-depth analysis
+
+**Analyze Images**:
+- Upload an image using the file selector
+- Examine the GradCAM heat map highlighting suspicious areas
+
+**Get Insights**:
+- Use preset questions or ask your own
+- Review either technical or simple explanations
+
+---
+*Note: GPU recommended for faster processing*
 """)
 
 # Fixed values for temperature and max tokens