Create app.py

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
+
+# Load the model and processor
+processor = BlipProcessor.from_pretrained("umarigan/blip-image-captioning-base-chestxray-finetuned")
+model = BlipForConditionalGeneration.from_pretrained("umarigan/blip-image-captioning-base-chestxray-finetuned")
+
+# Define the prediction function
+def generate_caption(image):
+    text = "a photography of"
+    inputs = processor(image, text, return_tensors="pt")
+    out = model.generate(**inputs)
+    caption = processor.decode(out[0], skip_special_tokens=True)
+    return caption
+
+# Example images from your Hugging Face Space
+example_images = [
+    ("image.jpg", "Example 1"),
+    ("image1.jpg", "Example 2"),
+    ("image2.jpg", "Example 3")
+]
+
+# Create the Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# BLIP Image Captioning")
+
+    # Image input component with example images
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Image(type="pil", label="Upload an Image or Select an Example")
+            examples = gr.Examples(examples=example_images, inputs=image_input)
+
+        with gr.Column():
+            caption_output = gr.Textbox(label="Generated Caption")
+
+    # Generate button
+    generate_button = gr.Button("Generate Caption")
+    generate_button.click(fn=generate_caption, inputs=image_input, outputs=caption_output)
+
+# Launch the app
+demo.launch()