Update app.py

app.py

@@ -6,11 +6,11 @@ from PIL import Image
 from collections import deque
 import numpy as np
 
-# Load main BLIP model for English captioning
+# Load main BLIP model for image captioning
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
 
-# Load YOLOv5 small model for object detection using ultralytics package
+# Load YOLOv5 model for object detection using ultralytics
 detect_model = YOLO('yolov5s.pt')
 
 # Session memory for last 15 images and captions
@@ -52,16 +52,31 @@ def generate_caption(image):
     return result_text, gallery
 
 with gr.Blocks() as iface:
-    gr.Markdown("# Image Captioning with Object Detection")
+    gr.Markdown(
+        "# 🖼️ Image Captioning with Object Detection"
+    )
+
+    gr.Markdown(
+        """
+        ### 👋 Welcome!  
+        Upload an image and click **Generate Caption** to discover:  
+        - 🎯 The **objects** detected in your image  
+        - 🗒️ A **caption** created automatically by the AI  
+
+        🔁 Your last 15 results are displayed below for quick reference.  
+        💡 Tip: Upload clear, well-lit images for best results!
+        """,
+        elem_id="instructions"
+    )
 
-    image_input = gr.Image(type="pil", label="Upload Image")
+    with gr.Column():
+        image_input = gr.Image(type="pil", label="Upload Image")
+        generate_btn = gr.Button("Generate Caption")
 
     caption_output = gr.Textbox(label="Caption and Detected Objects", lines=3, interactive=False)
 
     gallery = gr.Gallery(label="Last 15 Images and Captions", scale=3)
 
-    generate_btn = gr.Button("Generate Caption")
-
     def on_generate(image):
         if image is None:
             return "Please upload an image.", []