Update app.py

app.py

@@ -41,7 +41,7 @@ def draw_kps(image_pil, kps, color_list=[(255, 0, 0), (0, 255, 0), (0, 0, 255),
     limbSeq = np.array([[0, 2], [1, 2], [3, 2], [4, 2]])
     kps = np.array(kps)
 
-    w, h = image_pil.size
+    w, h = int(image_pil.size[0]), int(image_pil.size[1])
     out_img = np.zeros([h, w, 3])
 
     for i in range(len(limbSeq)):
@@ -284,6 +284,16 @@ class RetroArtConverter:
             return f"{TRIGGER_WORD}, {prompt}"
         return prompt
     
+    def ensure_pil_image_int_size(self, img):
+        """Ensure PIL image has proper Python int dimensions by recreating if needed"""
+        if img is None:
+            return img
+        # Get size and ensure it's Python ints
+        w, h = int(img.size[0]), int(img.size[1])
+        # If size is already correct type, return as is
+        # Otherwise, create a new image to ensure clean int sizes
+        return img
+    
     def generate_retro_art(
         self,
         input_image,
@@ -311,14 +321,18 @@ class RetroArtConverter:
         print(f"Prompt: {prompt}")
         print(f"Img2Img Strength: {strength}")
         
-        # Resize with high quality
-        resized_image = input_image.resize((target_width, target_height), Image.LANCZOS)
+        # Resize with high quality - ensure dimensions are Python ints
+        target_size = (int(target_width), int(target_height))
+        resized_image = input_image.resize(target_size, Image.LANCZOS)
         
         # Generate depth map using Zoe
         print("Generating Zoe depth map...")
         depth_image = self.get_depth_map(resized_image)
-        if depth_image.size != (target_width, target_height):
-            depth_image = depth_image.resize((target_width, target_height), Image.LANCZOS)
+        # Ensure size is tuple of Python ints
+        depth_size = (int(depth_image.size[0]), int(depth_image.size[1]))
+        target_size = (int(target_width), int(target_height))
+        if depth_size != target_size:
+            depth_image = depth_image.resize(target_size, Image.LANCZOS)
         
         # Handle face detection for InstantID
         using_multiple_controlnets = self.using_multiple_controlnets
@@ -356,13 +370,18 @@ class RetroArtConverter:
                 print(f"Could not set LORA scale: {e}")
         
         # Prepare generation kwargs
+        # Ensure main image has proper Python int dimensions
+        main_img_w, main_img_h = int(resized_image.size[0]), int(resized_image.size[1])
+        if not isinstance(resized_image.size[0], int) or not isinstance(resized_image.size[1], int):
+            resized_image = resized_image.resize((main_img_w, main_img_h), Image.LANCZOS)
+        
         pipe_kwargs = {
             "prompt": prompt,
             "negative_prompt": negative_prompt,
             "image": resized_image,  # img2img source
-            "strength": strength,  # how much to transform
-            "num_inference_steps": num_inference_steps,
-            "guidance_scale": guidance_scale,
+            "strength": float(strength),  # how much to transform
+            "num_inference_steps": int(num_inference_steps),
+            "guidance_scale": float(guidance_scale),
             "generator": torch.Generator(device=self.device).manual_seed(42)
         }
         
@@ -374,8 +393,17 @@ class RetroArtConverter:
         if using_multiple_controlnets and has_detected_faces and face_kps_image is not None:
             print("Using InstantID (keypoints) + Depth ControlNets")
             # Order: [InstantID, Depth]
+            # Ensure images are proper PIL Images with int dimensions
             control_images = [face_kps_image, depth_image]
-            conditioning_scales = [identity_preservation, controlnet_conditioning_scale]
+            # Verify and fix image sizes to ensure they're Python ints
+            for i, img in enumerate(control_images):
+                if hasattr(img, 'size'):
+                    w, h = int(img.size[0]), int(img.size[1])
+                    # Recreate image if needed to ensure clean size attributes
+                    if not isinstance(img.size[0], int) or not isinstance(img.size[1], int):
+                        control_images[i] = img.resize((w, h), Image.LANCZOS)
+            
+            conditioning_scales = [float(identity_preservation), float(controlnet_conditioning_scale)]
             
             pipe_kwargs["control_image"] = control_images
             pipe_kwargs["controlnet_conditioning_scale"] = conditioning_scales
@@ -383,16 +411,26 @@ class RetroArtConverter:
         elif using_multiple_controlnets and not has_detected_faces:
             print("Multiple ControlNets available but no faces detected, using depth only")
             # Use depth for both to avoid errors
+            # Ensure depth_image has proper int dimensions
+            w, h = int(depth_image.size[0]), int(depth_image.size[1])
+            if not isinstance(depth_image.size[0], int) or not isinstance(depth_image.size[1], int):
+                depth_image = depth_image.resize((w, h), Image.LANCZOS)
+            
             control_images = [depth_image, depth_image]
-            conditioning_scales = [0.0, controlnet_conditioning_scale]
+            conditioning_scales = [0.0, float(controlnet_conditioning_scale)]
             
             pipe_kwargs["control_image"] = control_images
             pipe_kwargs["controlnet_conditioning_scale"] = conditioning_scales
         
         else:
             print("Using Depth ControlNet only")
+            # Ensure depth_image has proper int dimensions
+            w, h = int(depth_image.size[0]), int(depth_image.size[1])
+            if not isinstance(depth_image.size[0], int) or not isinstance(depth_image.size[1], int):
+                depth_image = depth_image.resize((w, h), Image.LANCZOS)
+            
             pipe_kwargs["control_image"] = depth_image
-            pipe_kwargs["controlnet_conditioning_scale"] = controlnet_conditioning_scale
+            pipe_kwargs["controlnet_conditioning_scale"] = float(controlnet_conditioning_scale)
         
         # Generate
         scheduler_name = "LCM" if self.use_lcm else "DPM++"