Update app.py

app.py

@@ -8,9 +8,12 @@ import wget
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
 # Load the models
+# Image captioning model to generate captions from uploaded images
 caption_image = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large", device=device)
+# Stable Diffusion model for generating new images based on captions
 sd_pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5").to(device)
 
+# Load the translation model (English to Arabic)
 translator = pipeline(
     task="translation",
     model="facebook/nllb-200-distilled-600M",
@@ -18,37 +21,48 @@ translator = pipeline(
     device=device
 )
 
+# Download the image
+url1 = "https://github.com/Shahad-b/Image-database/blob/main/sea.jpg?raw=true"
+sea = wget.download(url1)
 # Function to generate images based on the image's caption
 def generate_image_and_translate(image, num_images=1):
+    # Generate caption in English from the uploaded image
     caption_en = caption_image(image)[0]['generated_text']
+
+    # Translate the English caption to Arabic
     caption_ar = translator(caption_en, src_lang="eng_Latn", tgt_lang="arb_Arab")[0]['translation_text']
 
     generated_images = []
+
+    # Generate the specified number of images based on the English caption
     for _ in range(num_images):
         generated_image = sd_pipeline(prompt=caption_en).images[0]
         generated_images.append(generated_image)
 
+    # Return the generated images along with both captions
     return generated_images, caption_en, caption_ar
 
 # Set up the Gradio interface
 interface = gr.Interface(
-    fn=generate_image_and_translate,
+    fn=generate_image_and_translate,   # Function to call when processing input
     inputs=[
-        gr.Image(type="pil", label="Upload Image"),
-        gr.Slider(minimum=1, maximum=10, label="Number of Images", value=1, step=1)
+        gr.Image(type="pil", label="Upload Image"), # Input for image upload
+        gr.Slider(minimum=1, maximum=10, label="Number of Images", value=1, step=1) # Slider to select number of images
     ],
     outputs=[
-        gr.Gallery(label="Generated Images"),
-        gr.Textbox(label="Generated Caption (English)", interactive=False),
-        gr.Textbox(label="Translated Caption (Arabic)", interactive=False)
+        gr.Gallery(label="Generated Images"),  # Output for displaying generated images
+        gr.Textbox(label="Generated Caption (English)", interactive=False),  # Output for English caption
+        gr.Textbox(label="Translated Caption (Arabic)", interactive=False)# Output for Arabic caption
+
     ],
-    title="Image Generation and Translation",
-    description="Upload an image to generate new images based on its caption and translate the caption into Arabic.",
-    examples=[
+    title="Image Generation and Translation",  # Title of the interface
+    description="Upload an image to generate new images based on its caption and translate the caption into Arabic.",  # Description
+    examples=[ # Example input
         ["sea.jpg", 3]
+        # ["Cat.jpeg", 4],
+        # ["Car.jpeg", 2]
     ]
 )
 
 # Launch the Gradio application
-if __name__ == "__main__":
-    interface.launch()
+interface.launch()