Create app.py

app.py

@@ -0,0 +1,26 @@
+import streamlit as st
+from transformers import AutoFeatureExtractor, AutoModelForImageCaptioning
+from PIL import Image
+import requests
+from io import BytesIO
+
+st.title("Image Captioning App")
+
+feature_extractor = AutoFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+model = AutoModelForImageCaptioning.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
+
+def generate_caption(image):
+    inputs = feature_extractor(images=image, return_tensors="pt")
+    caption = model.generate(**inputs)
+    return caption[0]
+
+uploaded_image = st.file_uploader("Upload an image", type=["jpg", "png", "jpeg"])
+
+if uploaded_image:
+    image = Image.open(uploaded_image)
+    st.image(image, caption="Uploaded Image", use_column_width=True)
+
+    caption = generate_caption(image)
+
+    st.subheader("Generated Caption:")
+    st.write(caption)