Update app.py

app.py

@@ -32,7 +32,7 @@ def generate_normal_map(image, strength=1.0, blur_size=5, use_bilateral=False, c
     normal_map[..., 1] = cv2.normalize(normal_map[..., 1], None, -strength, strength, cv2.NORM_MINMAX)
     normal_map[..., 2] = 1.0
     
-    # Add color influence (e.g., red affects X, green affects Y)
+    # Add color influence
     color_factor = color_influence * strength
     normal_map[..., 0] += (img[..., 0] / 255.0 - 0.5) * color_factor
     normal_map[..., 1] += (img[..., 1] / 255.0 - 0.5) * color_factor
@@ -44,18 +44,20 @@ def generate_normal_map(image, strength=1.0, blur_size=5, use_bilateral=False, c
     normal_map = np.clip(normal_map, 0, 255).astype(np.uint8)
     return Image.fromarray(normal_map)
 
-# Advanced Displacement Map with adaptive thresholding and edge enhancement
+# Advanced Displacement Map with fixed type handling
 def generate_displacement_map(image, contrast=1.0, add_noise=False, noise_scale=0.1, edge_boost=1.0):
     img = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2GRAY)
-    # Adaptive histogram equalization for better contrast
+    # Adaptive histogram equalization
     clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
     img = clahe.apply(img)
     # Adjust contrast
     img = cv2.convertScaleAbs(img, alpha=contrast, beta=0)
     # Edge enhancement with Laplacian
     laplacian = cv2.Laplacian(img, cv2.CV_64F)
-    img = cv2.addWeighted(img, 1.0, laplacian, edge_boost, 0)
-    img = np.clip(img, 0, 255).astype(np.uint8)
+    # Convert Laplacian to uint8 after scaling and clipping
+    laplacian = cv2.convertScaleAbs(laplacian, alpha=edge_boost, beta=0)
+    # Ensure both arrays are uint8 before blending
+    img = cv2.addWeighted(img, 1.0, laplacian, 0.5 * edge_boost, 0)  # Reduced weight for stability
     # Optional Perlin noise
     if add_noise:
         height, width = img.shape
@@ -66,10 +68,10 @@ def generate_displacement_map(image, contrast=1.0, add_noise=False, noise_scale=
         img = cv2.add(img, noise_map.astype(np.uint8))
     return Image.fromarray(img)
 
-# Advanced Roughness Map with frequency separation and texture analysis
+# Advanced Roughness Map with frequency separation
 def generate_roughness_map(image, invert=True, sharpness=1.0, detail_boost=0.5, frequency_weight=0.5):
     img = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2GRAY)
-    # Frequency separation: Low-frequency (smooth) and high-frequency (detail)
+    # Frequency separation
     low_freq = cv2.bilateralFilter(img, 9, 75, 75)
     high_freq = cv2.subtract(img, low_freq)
     # Combine with weight
@@ -83,7 +85,7 @@ def generate_roughness_map(image, invert=True, sharpness=1.0, detail_boost=0.5,
     img = cv2.addWeighted(img, 1.0 + detail_boost, blurred, -detail_boost, 0)
     return Image.fromarray(img)
 
-# Process function with advanced parameters
+# Process function
 def process_image(input_image, normal_strength=1.0, normal_blur=5, normal_bilateral=False, normal_color=0.3,
                   disp_contrast=1.0, disp_noise=False, disp_noise_scale=0.1, disp_edge=1.0,
                   rough_invert=True, rough_sharpness=1.0, rough_detail=0.5, rough_freq=0.5):
@@ -95,7 +97,7 @@ def process_image(input_image, normal_strength=1.0, normal_blur=5, normal_bilate
                                            detail_boost=rough_detail, frequency_weight=rough_freq)
     return normal_map, displacement_map, roughness_map
 
-# Gradio Interface with advanced controls
+# Gradio Interface
 interface = gr.Interface(
     fn=process_image,
     inputs=[