Update app.py

app.py

@@ -179,6 +179,9 @@ def upscale_image_4k(input_path, output_path):
             h, w = image.shape[:2]
             log_message(f"📏 Original resolution: {w}x{h}")
             
+            # Define target dimensions first
+            target_h, target_w = h * 4, w * 4
+            
             # Check GPU memory availability
             if torch.cuda.is_available():
                 device = torch.device('cuda')
@@ -199,9 +202,6 @@ def upscale_image_4k(input_path, output_path):
                     
                     log_message("🧠 Applying neural upscaling...")
                     
-                    # Progressive upscaling for better quality
-                    target_h, target_w = h * 4, w * 4
-                    
                     with torch.no_grad():
                         # Step 1: 2x upscaling with bicubic
                         intermediate = torch.nn.functional.interpolate(
@@ -299,7 +299,6 @@ def upscale_image_4k(input_path, output_path):
                 else:
                     # CPU fallback
                     log_message("⚠️ Using CPU - optimized processing")
-                    target_h, target_w = h * 4, w * 4
                     
                     # Progressive upscaling on CPU
                     intermediate = cv2.resize(image, (w * 2, h * 2), interpolation=cv2.INTER_CUBIC)
@@ -314,6 +313,23 @@ def upscale_image_4k(input_path, output_path):
                     
                     cv2.imwrite(output_path, final_result)
                     log_message(f"✅ CPU upscaling completed: {target_w}x{target_h}")
+            else:
+                # CPU only fallback (no CUDA available)
+                log_message("💻 Using CPU processing (CUDA not available)")
+                
+                # Progressive upscaling on CPU
+                intermediate = cv2.resize(image, (w * 2, h * 2), interpolation=cv2.INTER_CUBIC)
+                upscaled = cv2.resize(intermediate, (target_w, target_h), interpolation=cv2.INTER_CUBIC)
+                
+                # Apply sharpening on CPU
+                kernel = np.array([[-1,-1,-1], [-1,9,-1], [-1,-1,-1]])
+                sharpened = cv2.filter2D(upscaled, -1, kernel)
+                
+                # Blend for smoothing
+                final_result = cv2.addWeighted(upscaled, 0.7, sharpened, 0.3, 0)
+                
+                cv2.imwrite(output_path, final_result)
+                log_message(f"✅ CPU upscaling completed: {target_w}x{target_h}")
             
             # Add to processed files list
             app_state["processed_files"].append({