Update app.py

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 import torch
-from transformers import AutoProcessor, AutoModel
+from transformers import AutoProcessor, AutoModel # Keep CLIP for potential future use or if FastSAM's text prompt isn't enough
 from PIL import Image, ImageDraw, ImageFont
 import numpy as np
 import random
@@ -12,9 +12,11 @@ import traceback # For detailed error printing
 
 # Device Selection
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+# Force CPU if CUDA fails or isn't desired (sometimes needed on Spaces free tier)
+# DEVICE = "cpu"
 print(f"Using device: {DEVICE}")
 
-# --- CLIP Setup ---
+# --- CLIP Setup (Kept in case needed, but FastSAM's method is primary now) ---
 CLIP_MODEL_ID = "openai/clip-vit-base-patch32"
 clip_processor = None
 clip_model = None
@@ -22,17 +24,26 @@ clip_model = None
 def load_clip_model():
     global clip_processor, clip_model
     if clip_processor is None:
-        print(f"Loading CLIP processor: {CLIP_MODEL_ID}...")
-        clip_processor = AutoProcessor.from_pretrained(CLIP_MODEL_ID)
-        print("CLIP processor loaded.")
+        try:
+            print(f"Loading CLIP processor: {CLIP_MODEL_ID}...")
+            clip_processor = AutoProcessor.from_pretrained(CLIP_MODEL_ID)
+            print("CLIP processor loaded.")
+        except Exception as e:
+            print(f"Error loading CLIP processor: {e}")
+            return False # Indicate failure
     if clip_model is None:
-        print(f"Loading CLIP model: {CLIP_MODEL_ID}...")
-        clip_model = AutoModel.from_pretrained(CLIP_MODEL_ID).to(DEVICE)
-        print(f"CLIP model loaded to {DEVICE}.")
+        try:
+            print(f"Loading CLIP model: {CLIP_MODEL_ID}...")
+            clip_model = AutoModel.from_pretrained(CLIP_MODEL_ID).to(DEVICE)
+            print(f"CLIP model loaded to {DEVICE}.")
+        except Exception as e:
+            print(f"Error loading CLIP model: {e}")
+            return False # Indicate failure
+    return True # Indicate success
+
 
 # --- FastSAM Setup ---
 FASTSAM_CHECKPOINT = "FastSAM-s.pt"
-# Use the official model hub repo URL
 FASTSAM_CHECKPOINT_URL = f"https://huggingface.co/CASIA-IVA-Lab/FastSAM-s/resolve/main/{FASTSAM_CHECKPOINT}"
 
 fastsam_model = None
@@ -53,6 +64,7 @@ def check_and_import_fastsam():
             fastsam_lib_imported = False
         except Exception as e:
             print(f"An unexpected error occurred during fastsam import: {e}")
+            traceback.print_exc()
             fastsam_lib_imported = False
     return fastsam_lib_imported
 
@@ -66,168 +78,210 @@ def download_fastsam_weights():
         except Exception as e:
             print(f"Error downloading FastSAM weights: {e}")
             print("Please ensure the URL is correct and reachable, or manually place the weights file.")
-            # Attempt to remove partially downloaded file if exists
             if os.path.exists(FASTSAM_CHECKPOINT):
-                 try:
-                     os.remove(FASTSAM_CHECKPOINT)
-                 except OSError:
-                     pass # Ignore removal errors
+                 try: os.remove(FASTSAM_CHECKPOINT)
+                 except OSError: pass
             return False
     return os.path.exists(FASTSAM_CHECKPOINT)
 
 def load_fastsam_model():
     global fastsam_model
     if fastsam_model is None:
-        if not check_and_import_fastsam(): # Check import first
+        if not check_and_import_fastsam():
              print("Cannot load FastSAM model because the library couldn't be imported.")
-             return # Exit if import failed
+             return False # Indicate failure
 
-        if download_fastsam_weights(): # Check download/existence second
+        if download_fastsam_weights():
             try:
-                # FastSAM class should be available via globals() now
                 print(f"Loading FastSAM model: {FASTSAM_CHECKPOINT}...")
                 fastsam_model = FastSAM(FASTSAM_CHECKPOINT)
-                print(f"FastSAM model loaded.") # Device handled internally by FastSAM
+                # The FastSAM model itself doesn't need explicit .to(DEVICE)
+                # It seems to handle device selection internally or via the prompt process
+                print(f"FastSAM model loaded.")
+                return True # Indicate success
             except Exception as e:
                 print(f"Error loading FastSAM model: {e}")
                 traceback.print_exc()
         else:
             print("FastSAM weights not found or download failed. Cannot load model.")
+    return fastsam_model is not None # Return True if already loaded or loaded successfully
 
 
 # --- Processing Functions ---
 
+# (Keep run_clip_zero_shot and run_fastsam_segmentation as they were for the other tabs)
 # CLIP Zero-Shot Classification Function
 def run_clip_zero_shot(image: Image.Image, text_labels: str):
+    # Load CLIP if needed
     if clip_model is None or clip_processor is None:
-        load_clip_model() # Attempt to load if not already loaded
-        if clip_model is None:
-             return "Error: CLIP Model not loaded. Check logs.", None
+        if not load_clip_model():
+            return "Error: CLIP Model could not be loaded. Check logs.", None
 
-    if image is None:
-        return "Please upload an image.", None # Return None for the image display
-    if not text_labels:
-        # Return empty results but display the uploaded image
-        return {}, image
+    if image is None: return "Please upload an image.", None
+    if not text_labels: return {}, image # Return empty dict, show image
 
-    labels = [label.strip() for label in text_labels.split(',') if label.strip()] # Ensure non-empty labels
-    if not labels:
-         # Return empty results but display the uploaded image
-         return {}, image
+    labels = [label.strip() for label in text_labels.split(',') if label.strip()]
+    if not labels: return {}, image
 
     print(f"Running CLIP zero-shot classification with labels: {labels}")
-
     try:
-        # Ensure image is RGB
-        if image.mode != "RGB":
-            image = image.convert("RGB")
-
+        if image.mode != "RGB": image = image.convert("RGB")
         inputs = clip_processor(text=labels, images=image, return_tensors="pt", padding=True).to(DEVICE)
-
         with torch.no_grad():
             outputs = clip_model(**inputs)
-            logits_per_image = outputs.logits_per_image
-            probs = logits_per_image.softmax(dim=1)
-
+            probs = outputs.logits_per_image.softmax(dim=1)
         print("CLIP processing complete.")
-
         confidences = {labels[i]: float(probs[0, i].item()) for i in range(len(labels))}
-        # Return results and the original image used for prediction
         return confidences, image
-
     except Exception as e:
         print(f"Error during CLIP processing: {e}")
         traceback.print_exc()
-        # Return error message and the original image
         return f"An error occurred during CLIP: {e}", image
 
-
-# FastSAM Segmentation Function
+# FastSAM Everything Segmentation Function (for the second tab)
 def run_fastsam_segmentation(image_pil: Image.Image, conf_threshold: float = 0.4, iou_threshold: float = 0.9):
-    # Ensure model is loaded or attempt to load
-    if fastsam_model is None:
-        load_fastsam_model()
-        if fastsam_model is None:
-             # Return error message string for the image component (Gradio handles this)
-             return "Error: FastSAM Model not loaded. Check logs."
-    # Ensure library was imported
+    if not load_fastsam_model():
+        return "Error: FastSAM Model not loaded. Check logs."
     if not fastsam_lib_imported:
-        return "Error: FastSAM library not available. Cannot run segmentation."
+        return "Error: FastSAM library not available."
+    if image_pil is None: return "Please upload an image."
+
+    print("Running FastSAM 'segment everything'...")
+    try:
+        if image_pil.mode != "RGB": image_pil = image_pil.convert("RGB")
+        image_np_rgb = np.array(image_pil)
 
+        everything_results = fastsam_model(
+            image_np_rgb, device=DEVICE, retina_masks=True, imgsz=640,
+            conf=conf_threshold, iou=iou_threshold,
+        )
+        prompt_process = FastSAMPrompt(image_np_rgb, everything_results, device=DEVICE)
+        ann = prompt_process.everything_prompt()
+        print(f"FastSAM 'everything' found {len(ann[0]['masks']) if ann and ann[0] and 'masks' in ann[0] else 0} masks.")
+
+        # Plotting
+        output_image = image_pil.copy()
+        if ann and ann[0] is not None and 'masks' in ann[0] and len(ann[0]['masks']) > 0:
+            masks = ann[0]['masks'].cpu().numpy()
+            overlay = Image.new('RGBA', output_image.size, (0, 0, 0, 0))
+            draw = ImageDraw.Draw(overlay)
+            for mask in masks:
+                color = (random.randint(50, 255), random.randint(50, 255), random.randint(50, 255), 128)
+                mask_image = Image.fromarray((mask * 255).astype(np.uint8), mode='L')
+                draw.bitmap((0, 0), mask_image, fill=color)
+            output_image = Image.alpha_composite(output_image.convert('RGBA'), overlay).convert('RGB')
+
+        print("FastSAM 'everything' processing complete.")
+        return output_image
+
+    except Exception as e:
+        print(f"Error during FastSAM 'everything' processing: {e}")
+        traceback.print_exc()
+        return f"An error occurred during FastSAM 'everything': {e}"
+
+
+# --- NEW: Text-Prompted Segmentation Function ---
+def run_text_prompted_segmentation(image_pil: Image.Image, text_prompts: str, conf_threshold: float = 0.4, iou_threshold: float = 0.9):
+    """Segments objects based on text prompts."""
+    if not load_fastsam_model():
+        return "Error: FastSAM Model not loaded. Check logs.", "No prompts provided."
+    if not fastsam_lib_imported:
+        return "Error: FastSAM library not available.", "FastSAM library error."
     if image_pil is None:
-        return "Please upload an image."
+        return "Please upload an image.", "No image provided."
+    if not text_prompts:
+        return image_pil, "Please enter text prompts (e.g., 'person, dog')." # Return original image and message
 
-    print("Running FastSAM segmentation...")
+    prompts = [p.strip() for p in text_prompts.split(',') if p.strip()]
+    if not prompts:
+        return image_pil, "No valid text prompts entered."
+
+    print(f"Running FastSAM text-prompted segmentation for: {prompts}")
 
     try:
-         # Ensure image is RGB
         if image_pil.mode != "RGB":
             image_pil = image_pil.convert("RGB")
-
         image_np_rgb = np.array(image_pil)
 
-        # Run FastSAM inference
+        # 1. Run FastSAM once to get all potential results
+        # NOTE: We might optimize later, but this is the standard way FastSAMPrompt works.
         everything_results = fastsam_model(
-            image_np_rgb,
-            device=DEVICE,
-            retina_masks=True,
-            imgsz=640,
-            conf=conf_threshold,
-            iou=iou_threshold,
+            image_np_rgb, device=DEVICE, retina_masks=True, imgsz=640,
+            conf=conf_threshold, iou=iou_threshold, verbose=False # Less console spam
         )
 
-        # FastSAMPrompt should be available via globals() if import succeeded
+        # 2. Create the prompt processor
         prompt_process = FastSAMPrompt(image_np_rgb, everything_results, device=DEVICE)
-        ann = prompt_process.everything_prompt()
 
-        print(f"FastSAM found {len(ann[0]['masks']) if ann and ann[0] and 'masks' in ann[0] else 0} masks.")
-
-        # --- Plotting Masks on Image ---
+        # 3. Use text_prompt for each prompt and collect masks
+        all_matching_masks = []
+        found_prompts = []
+
+        for text in prompts:
+            print(f"  Processing prompt: '{text}'")
+            # Ann is a list of dictionaries, one per image. We have one image.
+            # Each dict can have 'masks', 'bboxes', 'points'.
+            # text_prompt filters 'everything_results' based on CLIP-like similarity.
+            # It might return multiple masks if multiple instances match the text.
+            ann = prompt_process.text_prompt(text=text)
+
+            if ann and ann[0] is not None and 'masks' in ann[0] and len(ann[0]['masks']) > 0:
+                num_found = len(ann[0]['masks'])
+                print(f"    Found {num_found} mask(s) matching '{text}'.")
+                found_prompts.append(f"{text} ({num_found})")
+                masks = ann[0]['masks'].cpu().numpy() # Get masks as numpy array (N, H, W)
+                all_matching_masks.extend(masks) # Add the numpy arrays to the list
+            else:
+                print(f"    No masks found matching '{text}'.")
+                found_prompts.append(f"{text} (0)")
+
+        # 4. Plot the collected masks
         output_image = image_pil.copy()
-        if ann and ann[0] is not None and 'masks' in ann[0] and len(ann[0]['masks']) > 0:
-            masks = ann[0]['masks'].cpu().numpy() # (N, H, W) boolean
+        status_message = f"Found segments for: {', '.join(found_prompts)}" if found_prompts else "No matching segments found for any prompt."
 
-            overlay = Image.new('RGBA', output_image.size, (0, 0, 0, 0))
-            draw = ImageDraw.Draw(overlay)
+        if not all_matching_masks:
+            print("No matching masks found for any prompt.")
+            return output_image, status_message # Return original image if nothing matched
 
-            for i in range(masks.shape[0]):
-                mask = masks[i]
-                color = (random.randint(50, 255), random.randint(50, 255), random.randint(50, 255), 128) # RGBA
-                mask_image = Image.fromarray((mask * 255).astype(np.uint8), mode='L')
-                draw.bitmap((0,0), mask_image, fill=color)
+        # Convert list of (H, W) masks to a single (N, H, W) array for consistent processing
+        masks_np = np.stack(all_matching_masks, axis=0) # Shape (TotalMasks, H, W)
 
-            output_image = Image.alpha_composite(output_image.convert('RGBA'), overlay).convert('RGB')
+        overlay = Image.new('RGBA', output_image.size, (0, 0, 0, 0))
+        draw = ImageDraw.Draw(overlay)
 
-        print("FastSAM processing and plotting complete.")
-        # *** FIX: Return ONLY the output image for the single Image component ***
-        return output_image
+        for i in range(masks_np.shape[0]):
+            mask = masks_np[i] # Shape (H, W), boolean
+            color = (random.randint(50, 255), random.randint(50, 255), random.randint(50, 255), 150) # RGBA with slightly more alpha
+            mask_image = Image.fromarray((mask * 255).astype(np.uint8), mode='L')
+            draw.bitmap((0, 0), mask_image, fill=color)
+
+        output_image = Image.alpha_composite(output_image.convert('RGBA'), overlay).convert('RGB')
+
+        print("FastSAM text-prompted processing complete.")
+        return output_image, status_message
 
-    except NameError as ne:
-         print(f"NameError during FastSAM processing: {ne}. Was the fastsam library imported correctly?")
-         traceback.print_exc()
-         return f"A NameError occurred: {ne}. Check library import."
     except Exception as e:
-        print(f"Error during FastSAM processing: {e}")
+        print(f"Error during FastSAM text-prompted processing: {e}")
         traceback.print_exc()
-        return f"An error occurred during FastSAM: {e}"
+        return f"An error occurred: {e}", "Error during processing."
 
 
 # --- Gradio Interface ---
 
-# Pre-load models on startup (optional but good for performance)
 print("Attempting to preload models...")
-load_clip_model()
-load_fastsam_model() # This will now also attempt download/check import
+# load_clip_model() # Load CLIP lazily if needed
+load_fastsam_model() # Load FastSAM eagerly
 print("Preloading finished (or attempted).")
 
 
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.Markdown("# CLIP & FastSAM Demo")
-    gr.Markdown("Explore Zero-Shot Classification with CLIP and 'Segment Anything' with FastSAM.")
+    gr.Markdown("Explore Zero-Shot Classification, 'Segment Everything', and Text-Prompted Segmentation.")
 
     with gr.Tabs():
-        # --- CLIP Tab ---
+        # --- CLIP Tab (No changes) ---
         with gr.TabItem("CLIP Zero-Shot Classification"):
+            # ... (keep the existing layout and logic for CLIP) ...
             gr.Markdown("Upload an image and provide comma-separated candidate labels (e.g., 'cat, dog, car'). CLIP will predict the probability of the image matching each label.")
             with gr.Row():
                 with gr.Column(scale=1):
@@ -237,7 +291,6 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                 with gr.Column(scale=1):
                     clip_output_label = gr.Label(label="Classification Probabilities")
                     clip_output_image_display = gr.Image(type="pil", label="Input Image Preview")
-
             clip_button.click(
                 run_clip_zero_shot,
                 inputs=[clip_input_image, clip_text_labels],
@@ -247,56 +300,88 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                 examples=[
                     ["examples/astronaut.jpg", "astronaut, moon, rover, mountain"],
                     ["examples/dog_bike.jpg", "dog, bicycle, person, park, grass"],
-                    ["examples/clip_logo.png", "logo, text, graphics, abstract art"], # Added another example
+                    ["examples/clip_logo.png", "logo, text, graphics, abstract art"],
                 ],
                 inputs=[clip_input_image, clip_text_labels],
-                outputs=[clip_output_label, clip_output_image_display],
-                fn=run_clip_zero_shot,
-                cache_examples=False,
+                outputs=[clip_output_label, clip_output_image_display], fn=run_clip_zero_shot, cache_examples=False,
             )
 
-        # --- FastSAM Tab ---
-        with gr.TabItem("FastSAM Segmentation"):
-            gr.Markdown("Upload an image. FastSAM will attempt to segment all objects/regions in the image.")
+
+        # --- FastSAM Everything Tab (No changes) ---
+        with gr.TabItem("FastSAM Segment Everything"):
+            # ... (keep the existing layout and logic for segment everything) ...
+             gr.Markdown("Upload an image. FastSAM will attempt to segment all objects/regions in the image.")
+             with gr.Row():
+                 with gr.Column(scale=1):
+                     fastsam_input_image_all = gr.Image(type="pil", label="Input Image", elem_id="fastsam_input_all") # Unique elem_id if needed
+                     with gr.Row():
+                         fastsam_conf_all = gr.Slider(minimum=0.1, maximum=1.0, value=0.4, step=0.05, label="Confidence Threshold")
+                         fastsam_iou_all = gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="IoU Threshold")
+                     fastsam_button_all = gr.Button("Run FastSAM Segmentation", variant="primary")
+                 with gr.Column(scale=1):
+                     fastsam_output_image_all = gr.Image(type="pil", label="Segmented Image", elem_id="fastsam_output_all")
+             fastsam_button_all.click(
+                 run_fastsam_segmentation,
+                 inputs=[fastsam_input_image_all, fastsam_conf_all, fastsam_iou_all],
+                 outputs=[fastsam_output_image_all]
+             )
+             gr.Examples(
+                 examples=[
+                     ["examples/dogs.jpg", 0.4, 0.9],
+                     ["examples/fruits.jpg", 0.5, 0.8],
+                     ["examples/lion.jpg", 0.45, 0.9],
+                 ],
+                 inputs=[fastsam_input_image_all, fastsam_conf_all, fastsam_iou_all],
+                 outputs=[fastsam_output_image_all], fn=run_fastsam_segmentation, cache_examples=False,
+             )
+
+        # --- NEW: Text-Prompted Segmentation Tab ---
+        with gr.TabItem("Text-Prompted Segmentation"):
+            gr.Markdown("Upload an image and provide comma-separated text prompts (e.g., 'person, dog, backpack'). FastSAM + CLIP (internally) will segment only the objects matching the text.")
             with gr.Row():
                 with gr.Column(scale=1):
-                    fastsam_input_image = gr.Image(type="pil", label="Input Image")
-                    with gr.Row():
-                        fastsam_conf = gr.Slider(minimum=0.1, maximum=1.0, value=0.4, step=0.05, label="Confidence Threshold")
-                        fastsam_iou = gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="IoU Threshold")
-                    fastsam_button = gr.Button("Run FastSAM Segmentation", variant="primary")
+                    prompt_input_image = gr.Image(type="pil", label="Input Image")
+                    prompt_text_input = gr.Textbox(label="Comma-Separated Text Prompts", placeholder="e.g., glasses, watch, t-shirt")
+                    with gr.Row(): # Reuse confidence/IoU sliders if desired
+                        prompt_conf = gr.Slider(minimum=0.1, maximum=1.0, value=0.4, step=0.05, label="Confidence Threshold")
+                        prompt_iou = gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="IoU Threshold")
+                    prompt_button = gr.Button("Segment by Text", variant="primary")
                 with gr.Column(scale=1):
-                    fastsam_output_image = gr.Image(type="pil", label="Segmented Image")
+                    prompt_output_image = gr.Image(type="pil", label="Text-Prompted Segmentation")
+                    prompt_status_message = gr.Textbox(label="Status", interactive=False) # To show which prompts matched
 
-            fastsam_button.click(
-                run_fastsam_segmentation,
-                inputs=[fastsam_input_image, fastsam_conf, fastsam_iou],
-                # Output is now correctly mapped to the single component
-                outputs=[fastsam_output_image]
+            prompt_button.click(
+                run_text_prompted_segmentation,
+                inputs=[prompt_input_image, prompt_text_input, prompt_conf, prompt_iou],
+                outputs=[prompt_output_image, prompt_status_message] # Map to image and status box
             )
             gr.Examples(
                 examples=[
-                    ["examples/dogs.jpg", 0.4, 0.9],
-                    ["examples/fruits.jpg", 0.5, 0.8],
-                    ["examples/lion.jpg", 0.45, 0.9], # Added another example
+                    ["examples/dog_bike.jpg", "person, bicycle", 0.4, 0.9],
+                    ["examples/astronaut.jpg", "person, helmet", 0.35, 0.9],
+                    ["examples/dogs.jpg", "dog", 0.4, 0.9], # Should find multiple dogs
+                    ["examples/fruits.jpg", "banana, apple", 0.5, 0.8],
+                    ["examples/teacher.jpg", "person, glasses, blackboard", 0.4, 0.9], # Download this image or use another one with glasses/blackboard
                 ],
-                inputs=[fastsam_input_image, fastsam_conf, fastsam_iou],
-                outputs=[fastsam_output_image],
-                fn=run_fastsam_segmentation,
+                inputs=[prompt_input_image, prompt_text_input, prompt_conf, prompt_iou],
+                outputs=[prompt_output_image, prompt_status_message],
+                fn=run_text_prompted_segmentation,
                 cache_examples=False,
             )
 
-    # Add example images (optional, but helpful)
+    # Ensure example images exist or are downloaded
+    # (Keep the existing example download logic, maybe add teacher.jpg if used in examples)
     if not os.path.exists("examples"):
         os.makedirs("examples")
         print("Created 'examples' directory. Attempting to download sample images...")
         example_files = {
-            "astronaut.jpg": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/d astronaut_-_St._Jean_Bay.jpg/640px-Astronaut_-_St._Jean_Bay.jpg", # Find suitable public domain/CC image
-            "dog_bike.jpg": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/gradio/outputs_multimodal.jpg", # Using a relevant example from HF
-            "clip_logo.png": "https://raw.githubusercontent.com/openai/CLIP/main/CLIP.png",
-            "dogs.jpg": "https://raw.githubusercontent.com/ultralytics/assets/main/im/image8.jpg", # From Ultralytics assets
-            "fruits.jpg": "https://raw.githubusercontent.com/ultralytics/assets/main/im/image9.jpg", # From Ultralytics assets
-            "lion.jpg": "https://huggingface.co/spaces/gradio/image-segmentation/resolve/main/images/lion.jpg"
+             "astronaut.jpg": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/d1/Astronaut_-_St._Jean_Bay.jpg/640px-Astronaut_-_St._Jean_Bay.jpg",
+             "dog_bike.jpg": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/gradio/outputs_multimodal.jpg",
+             "clip_logo.png": "https://raw.githubusercontent.com/openai/CLIP/main/CLIP.png",
+             "dogs.jpg": "https://raw.githubusercontent.com/ultralytics/assets/main/im/image8.jpg",
+             "fruits.jpg": "https://raw.githubusercontent.com/ultralytics/assets/main/im/image9.jpg",
+             "lion.jpg": "https://huggingface.co/spaces/gradio/image-segmentation/resolve/main/images/lion.jpg",
+             "teacher.jpg": "https://images.pexels.com/photos/848117/pexels-photo-848117.jpeg?auto=compress&cs=tinysrgb&w=600" # Example with glasses/board
         }
         for filename, url in example_files.items():
              filepath = os.path.join("examples", filename)
@@ -311,7 +396,4 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
 
 # Launch the Gradio app
 if __name__ == "__main__":
-    # share=True is primarily for local testing to get a public link.
-    # Not needed/used when deploying on Hugging Face Spaces.
-    # debug=True is helpful for development. Set to False for production.
-    demo.launch(debug=True)
+    demo.launch(debug=True) # debug=True is helpful locally