Create app.py

app.py

@@ -0,0 +1,22 @@
+import streamlit as st
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+# Load model and processor
+model_id = "Salesforce/blip-2-captioning-base"
+model = BlipForConditionalGeneration.from_pretrained(model_id)
+processor = BlipProcessor.from_pretrained(model_id)
+
+def generate_caption(image):
+    inputs = processor(images=image, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    return processor.decode(outputs[0], skip_special_tokens=True)
+
+st.title('BLIP-2 Image Captioning Demo')
+
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "png", "jpeg"])
+if uploaded_file is not None:
+    # Display the image
+    st.image(uploaded_file, caption='Uploaded Image', use_column_width=True)
+    # Generate and display caption
+    caption = generate_caption(uploaded_file.getvalue())
+    st.write(f"Caption: {caption}")