Create app.py

app.py

@@ -0,0 +1,25 @@
+from transformers import BlipProcessor, BlipForConditionalGeneration
+import torch
+import gradio as gr
+from PIL import Image
+
+# Load model and processor
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+
+def generate_caption(image):
+    inputs = processor(image, return_tensors="pt")
+    out = model.generate(**inputs)
+    caption = processor.decode(out[0], skip_special_tokens=True)
+    return caption
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=generate_caption,
+    inputs=gr.Image(type="pil"),
+    outputs="text",
+    title="Image Captioning App"
+)
+
+if __name__ == "__main__":
+    iface.launch()