Update app.py

app.py

@@ -1,5 +1,4 @@
 import torch
-from transformers import BlipProcessor, BlipForConditionalGeneration
 from PIL import Image
 from RealESRGAN import RealESRGAN
 import gradio as gr
@@ -28,10 +27,6 @@ model2 = load_model(2)
 model4 = load_model(4)
 model8 = load_model(8)
 
-# Initialize BLIP processor and model for image captioning
-processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
-model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to(device)
-
 # Enhance the image using the specified scale
 def enhance_image(image, scale):
     try:
@@ -54,13 +49,6 @@ def enhance_image(image, scale):
         print(f"Error enhancing image: {e}")
         return image
 
-# Generate captions for the images using BLIP
-def generate_caption(image):
-    inputs = processor(images=image, return_tensors="pt").to(device)
-    output_ids = model.generate(**inputs)
-    caption = processor.decode(output_ids[0], skip_special_tokens=True)
-    return caption
-
 # Adjust the DPI of the image
 def muda_dpi(input_image, dpi):
     dpi_tuple = (dpi, dpi)
@@ -79,11 +67,10 @@ def resize_image(input_image, width, height):
     temp_file.close()
     return Image.open(temp_file.name)
 
-# Process the images: enhance, adjust DPI, resize, caption, and save
+# Process the images: enhance, adjust DPI, resize, and save
 def process_images(image_files, enhance, scale, adjust_dpi, dpi, resize, width, height):
     processed_images = []
     file_paths = []
-    captions = []
     
     for i, image_file in enumerate(image_files):
         input_image = np.array(Image.open(image_file).convert('RGB'))
@@ -98,10 +85,6 @@ def process_images(image_files, enhance, scale, adjust_dpi, dpi, resize, width,
         if resize:
             original_image = resize_image(np.array(original_image), width, height)
             
-        # Generate a caption for the image
-        caption = generate_caption(original_image)
-        captions.append(caption)
-        
         # Create a custom filename
         custom_filename = f"Image_Captioning_with_BLIP_{i+1}.jpg"
         
@@ -116,13 +99,13 @@ def process_images(image_files, enhance, scale, adjust_dpi, dpi, resize, width,
         processed_images.append(original_image)
         file_paths.append(final_path)
     
-    return processed_images, file_paths, captions
+    return processed_images, file_paths
 
 # Gradio interface setup
 iface = gr.Interface(
     fn=process_images,
     inputs=[
-        gr.Files(label="Upload Image Files"),
+        gr.Files(label="Upload Image Files"),  # Use gr.Files for multiple file uploads
         gr.Checkbox(label="Enhance Images (ESRGAN)"),
         gr.Radio(['2x', '4x', '8x'], type="value", value='2x', label='Resolution model'),
         gr.Checkbox(label="Adjust DPI"),
@@ -132,15 +115,13 @@ iface = gr.Interface(
         gr.Number(label="Height", value=512)
     ],
     outputs=[
-        gr.Gallery(label="Final Images"),
-        gr.Files(label="Download Final Images"),
-        gr.Textbox(label="Image Captions")
+        gr.Gallery(label="Final Images"),  # Use gr.Gallery to display multiple images
+        gr.Files(label="Download Final Images")
     ],
-    title="Multi-Image Enhancer with Captioning",
-    description="Upload multiple images (.jpg, .png), enhance using AI, adjust DPI, resize, generate captions, and download the final results."
+    title="Multi-Image Enhancer",
+    description="Upload multiple images (.jpg, .png), enhance using AI, adjust DPI, resize, and download the final results."
 )
 
 # Launch the Gradio interface
 iface.launch(debug=True)
 
-