Create app.py

app.py

@@ -0,0 +1,35 @@
+import streamlit as st
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+import torch
+
+# Load the processor and model
+@st.cache_resource
+def load_model():
+    processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+    model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
+    return processor, model
+
+# Function to generate captions
+def generate_caption(image,max_new_tokens=20):
+    processor, model = load_model()
+    inputs = processor(image, return_tensors="pt")
+    out = model.generate(**inputs, max_new_tokens=max_new_tokens)
+    return processor.decode(out[0], skip_special_tokens=True)
+
+# Streamlit UI
+st.title("Image Captioning with BLIP")
+
+# Upload image
+uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
+
+if uploaded_file is not None:
+    # Display the uploaded image with size 400x400
+    image = Image.open(uploaded_file).convert('RGB')
+    resized_image = image.resize((400, 400))
+    st.image(resized_image, caption="Uploaded Image", use_column_width=False)
+
+    # Generate caption
+    if st.button("Generate Caption"):
+        caption = generate_caption(image)
+        st.write(f"**Caption:** {caption}")