Update Visual-CoT demo - 2025-10-12 23:05:52

Fixes:
- Fix LLaVA config registration error (compatibility with newer transformers)
- Update Gradio to latest version (security fixes)
- Auto-deployed via update script

llava/mm_utils.py

@@ -27,6 +27,7 @@ def expand2square(pil_img, background_color):
 
 def process_images(images, image_processor, model_cfg):
     from PIL import Image
+    import numpy as np
     
     image_aspect_ratio = getattr(model_cfg, "image_aspect_ratio", None)
     new_images = []
@@ -38,15 +39,21 @@ def process_images(images, image_processor, model_cfg):
     else:
         processor = image_processor
     
-    # Ensure all images are PIL Images
+    # Ensure all images are PIL Images in RGB format
     processed_images = []
     for img in images:
+        # Convert numpy array to PIL Image
+        if isinstance(img, np.ndarray):
+            img = Image.fromarray(img.astype(np.uint8))
+        
+        # Ensure it's a PIL Image
         if not isinstance(img, Image.Image):
-            # Convert to PIL Image if needed
-            if hasattr(img, 'convert'):
-                img = img.convert('RGB')
-            else:
-                raise ValueError(f"Invalid image type: {type(img)}")
+            raise ValueError(f"Invalid image type: {type(img)}. Expected PIL Image or numpy array.")
+        
+        # Convert to RGB if needed
+        if img.mode != 'RGB':
+            img = img.convert('RGB')
+        
         processed_images.append(img)
     
     if image_aspect_ratio == 'pad':