Create app.py

app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+# Load the BLIP model and processor from Hugging Face
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+
+def generate_caption(image):
+    # Process the image
+    inputs = processor(images=image, return_tensors="pt")
+    
+    # Generate caption using BLIP model
+    out = model.generate(**inputs)
+    
+    # Decode the output into a string
+    caption = processor.decode(out[0], skip_special_tokens=True)
+    
+    # Custom description to match the theme of surroundings
+    custom_description = """
+    A tropical escape where the azure waves meet the golden sand, sheltered by palm trees and embraced by the distant hills. 
+    A place to unwind, breathe, and reconnect with nature.
+    """
+    
+    return caption + "\n" + custom_description
+
+# Create the Gradio interface
+iface = gr.Interface(fn=generate_caption, 
+                     inputs=gr.Image(type="pil"), 
+                     outputs=gr.Textbox(), 
+                     title="Image Caption Generator", 
+                     description="Upload an image and get a description with the surroundings of the image.")
+
+if __name__ == "__main__":
+    iface.launch()