Update app.py

app.py

@@ -26,7 +26,7 @@ st.set_page_config(
 )
 
 # Main title and description
-st.title("Deepfake Image Analyzer")
+st.title("Advanced Deepfake Image Analyzer")
 st.markdown("Analyze images for deepfake manipulation with multi-stage analysis")
 
 # Check for GPU availability
@@ -39,10 +39,54 @@ def check_gpu():
         st.sidebar.warning("⚠️ No GPU detected. Analysis will be slower.")
         return False
 
-# Set constant values for generation parameters
-TEMPERATURE = 0.7
-MAX_TOKENS = 500
-CUSTOM_INSTRUCTION = "Focus on analyzing the highlighted regions from the GradCAM visualization. Examine facial inconsistencies, lighting irregularities, and other artifacts visible in the heat map."
+# Sidebar components
+st.sidebar.title("Options")
+
+# Temperature slider
+temperature = st.sidebar.slider(
+    "Temperature", 
+    min_value=0.1, 
+    max_value=1.0, 
+    value=0.7, 
+    step=0.1,
+    help="Higher values make output more random, lower values more deterministic"
+)
+
+# Max response length slider
+max_tokens = st.sidebar.slider(
+    "Maximum Response Length", 
+    min_value=100, 
+    max_value=1000, 
+    value=500, 
+    step=50,
+    help="The maximum number of tokens in the response"
+)
+
+# Custom instruction text area in sidebar
+custom_instruction = st.sidebar.text_area(
+    "Custom Instructions (Advanced)",
+    value="Focus on analyzing the highlighted regions from the GradCAM visualization. Examine facial inconsistencies, lighting irregularities, and other artifacts visible in the heat map.",
+    help="Add specific instructions for the LLM analysis"
+)
+
+# About section in sidebar
+st.sidebar.markdown("---")
+st.sidebar.subheader("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
+""")
 
 # ----- GradCAM Implementation -----
 
@@ -514,7 +558,7 @@ def load_llm_model():
             return None, None
 
 # Analyze image function
-def analyze_image_with_llm(image, gradcam_overlay, face_box, pred_label, confidence, question, model, tokenizer, custom_instruction=""):
+def analyze_image_with_llm(image, gradcam_overlay, face_box, pred_label, confidence, question, model, tokenizer, temperature=0.7, max_tokens=500, custom_instruction=""):
     # Create a prompt that includes GradCAM information
     if custom_instruction.strip():
         full_prompt = f"{question}\n\nThe image has been processed with GradCAM and classified as {pred_label} with confidence {confidence:.2f}. Focus on the highlighted regions in red/yellow which show the areas the detection model found suspicious.\n\n{custom_instruction}"
@@ -549,9 +593,9 @@ def analyze_image_with_llm(image, gradcam_overlay, face_box, pred_label, confide
         with torch.no_grad():
             output_ids = model.generate(
                 **inputs,
-                max_new_tokens=MAX_TOKENS,
+                max_new_tokens=max_tokens,
                 use_cache=True,
-                temperature=TEMPERATURE,
+                temperature=temperature,
                 top_p=0.9
             )
 
@@ -566,67 +610,6 @@ def analyze_image_with_llm(image, gradcam_overlay, face_box, pred_label, confide
             
         return result
 
-# Sidebar chat interface
-def chat_interface():
-    st.sidebar.title("Deepfake Analysis Chat")
-    
-    # Display chat history
-    if 'chat_history' not in st.session_state:
-        st.session_state.chat_history = []
-    
-    # Display chat messages
-    for i, (question, answer) in enumerate(st.session_state.chat_history):
-        st.sidebar.markdown(f"**You:** {question}")
-        st.sidebar.markdown(f"**AI:** {answer}")
-        st.sidebar.markdown("---")
-    
-    # Only show the chat interface if image has been analyzed
-    if hasattr(st.session_state, 'current_image'):
-        # New question input
-        new_question = st.sidebar.text_area("Ask about the image:", height=100)
-        
-        # Send button
-        if st.sidebar.button("Send Question", type="primary"):
-            if new_question:
-                try:
-                    # Add caption info if it's the first question
-                    caption_text = ""
-                    if not st.session_state.chat_history:
-                        if hasattr(st.session_state, 'image_caption'):
-                            caption_text += f"\n\nImage Description:\n{st.session_state.image_caption}"
-                        if hasattr(st.session_state, 'gradcam_caption'):
-                            caption_text += f"\n\nGradCAM Analysis:\n{st.session_state.gradcam_caption}"
-                        
-                        full_question = new_question + caption_text
-                    else:
-                        full_question = new_question
-                    
-                    result = analyze_image_with_llm(
-                        st.session_state.current_image,
-                        st.session_state.current_overlay,
-                        st.session_state.current_face_box,
-                        st.session_state.current_pred_label,
-                        st.session_state.current_confidence,
-                        full_question,
-                        st.session_state.llm_model,
-                        st.session_state.tokenizer,
-                        custom_instruction=CUSTOM_INSTRUCTION
-                    )
-                    
-                    # Add to chat history
-                    st.session_state.chat_history.append((new_question, result))
-                    st.experimental_rerun()
-                    
-                except Exception as e:
-                    st.sidebar.error(f"Error during LLM analysis: {str(e)}")
-    else:
-        st.sidebar.info("Upload and analyze an image to start chatting")
-    
-    # Clear chat button
-    if st.session_state.chat_history and st.sidebar.button("Clear Chat History"):
-        st.session_state.chat_history = []
-        st.experimental_rerun()
-
 # Main app
 def main():
     # Initialize session state variables
@@ -644,8 +627,9 @@ def main():
         st.session_state.blip_processor = None
         st.session_state.blip_model = None
     
-    # Set up chat interface in sidebar
-    chat_interface()
+    # Initialize chat history
+    if 'chat_history' not in st.session_state:
+        st.session_state.chat_history = []
     
     # Create expanders for each stage
     with st.expander("Stage 1: Model Loading", expanded=True):
@@ -795,4 +779,144 @@ def main():
             except Exception as e:
                 st.error(f"Error processing image: {str(e)}")
                 import traceback
-                st.error(traceback.format_exc())  # This will show the full error traceback
+                st.error(traceback.format_exc())  # This will show the full error traceback
+    
+    # Image Analysis Summary section - AFTER Stage 2
+    if hasattr(st.session_state, 'current_image') and (hasattr(st.session_state, 'image_caption') or hasattr(st.session_state, 'gradcam_caption')):
+        with st.expander("Image Analysis Summary", expanded=True):
+            st.subheader("Generated Descriptions and Analysis")
+            
+            # Display image, captions, and results in organized layout with proper formatting
+            col1, col2 = st.columns([1, 2])
+            
+            with col1:
+                # Display original image and overlay side by side with controlled size
+                st.image(st.session_state.current_image, caption="Original Image", width=300)
+                if hasattr(st.session_state, 'current_overlay'):
+                    st.image(st.session_state.current_overlay, caption="GradCAM Overlay", width=300)
+            
+            with col2:
+                # Detection result
+                if hasattr(st.session_state, 'current_pred_label'):
+                    st.markdown("### Detection Result")
+                    st.markdown(f"**Classification:** {st.session_state.current_pred_label} (Confidence: {st.session_state.current_confidence:.2%})")
+                    st.markdown("---")
+                
+                # Image description
+                if hasattr(st.session_state, 'image_caption'):
+                    st.markdown("### Image Description")
+                    st.markdown(st.session_state.image_caption)
+                    st.markdown("---")
+                
+                # GradCAM analysis
+                if hasattr(st.session_state, 'gradcam_caption'):
+                    st.markdown("### GradCAM Analysis")
+                    st.markdown(st.session_state.gradcam_caption)
+    
+    # LLM Analysis section - AFTER Image Analysis Summary
+    with st.expander("Stage 3: Detailed Analysis with Vision LLM", expanded=False):
+        if hasattr(st.session_state, 'current_image') and st.session_state.llm_model_loaded:
+            st.subheader("Detailed Deepfake Analysis")
+            
+            # Display chat history
+            for i, (question, answer) in enumerate(st.session_state.chat_history):
+                st.markdown(f"**Question {i+1}:** {question}")
+                st.markdown(f"**Answer:** {answer}")
+                st.markdown("---")
+            
+            # Include both captions in the prompt if available
+            caption_text = ""
+            if hasattr(st.session_state, 'image_caption'):
+                caption_text += f"\n\nImage Description:\n{st.session_state.image_caption}"
+                
+            if hasattr(st.session_state, 'gradcam_caption'):
+                caption_text += f"\n\nGradCAM Analysis:\n{st.session_state.gradcam_caption}"
+            
+            # Default question with option to customize
+            default_question = f"This image has been classified as {st.session_state.current_pred_label}. Analyze the key features that led to this classification, focusing on the highlighted areas in the GradCAM visualization. Provide both a technical explanation for experts and a simple explanation for non-technical users."
+            
+            # User input for new question
+            new_question = st.text_area("Ask a question about the image:", value=default_question if not st.session_state.chat_history else "", height=100)
+            
+            # Analyze button and Clear Chat button in the same row
+            col1, col2 = st.columns([3, 1])
+            with col1:
+                analyze_button = st.button("🔍 Send Question", type="primary")
+            with col2:
+                clear_button = st.button("🗑️ Clear Chat History")
+            
+            if clear_button:
+                st.session_state.chat_history = []
+                st.experimental_rerun()
+                
+            if analyze_button and new_question:
+                try:
+                    # Add caption info if it's the first question
+                    if not st.session_state.chat_history:
+                        full_question = new_question + caption_text
+                    else:
+                        full_question = new_question
+                    
+                    result = analyze_image_with_llm(
+                        st.session_state.current_image,
+                        st.session_state.current_overlay,
+                        st.session_state.current_face_box,
+                        st.session_state.current_pred_label,
+                        st.session_state.current_confidence,
+                        full_question,
+                        st.session_state.llm_model,
+                        st.session_state.tokenizer,
+                        temperature=temperature,
+                        max_tokens=max_tokens,
+                        custom_instruction=custom_instruction
+                    )
+                    
+                    # Add to chat history
+                    st.session_state.chat_history.append((new_question, result))
+                    
+                    # Display the latest result too
+                    st.success("✅ Analysis complete!")
+                    
+                    # Check if the result contains both technical and non-technical explanations
+                    if "Technical" in result and "Non-Technical" in result:
+                        try:
+                            # Split the result into technical and non-technical sections
+                            parts = result.split("Non-Technical")
+                            technical = parts[0]
+                            non_technical = "Non-Technical" + parts[1]
+                            
+                            # Display in two columns
+                            tech_col, simple_col = st.columns(2)
+                            with tech_col:
+                                st.subheader("Technical Analysis")
+                                st.markdown(technical)
+                            
+                            with simple_col:
+                                st.subheader("Simple Explanation")
+                                st.markdown(non_technical)
+                        except Exception as e:
+                            # Fallback if splitting fails
+                            st.subheader("Analysis Result")
+                            st.markdown(result)
+                    else:
+                        # Just display the whole result
+                        st.subheader("Analysis Result")
+                        st.markdown(result)
+                    
+                    # Rerun to update the chat history display
+                    st.experimental_rerun()
+                    
+                except Exception as e:
+                    st.error(f"Error during LLM analysis: {str(e)}")
+                    
+        elif not hasattr(st.session_state, 'current_image'):
+            st.warning("⚠️ Please upload an image and complete the initial detection first.")
+        else:
+            st.warning("⚠️ Please load the Vision LLM to perform detailed analysis.")
+    
+    # Footer
+    st.markdown("---")
+    st.caption("Advanced Deepfake Image Analyzer with Structured BLIP Captioning")
+
+if __name__ == "__main__":
+    main()