from transformers import pipeline
import gradio as gr

# Load pre-trained image captioning model
captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")

# Define function to get caption
def get_image_caption(image):
    if image is None:
        return "Please upload an image."
    caption = captioner(image)[0]['generated_text']
    return caption

# Build Gradio app
with gr.Blocks() as image_captioning_app:
    gr.Markdown("## 🖼️ Image Captioning App")
    with gr.Row():
        image_input = gr.Image(type="pil", label="Upload an Image")
        caption_output = gr.Textbox(label="Image Caption")
    generate_button = gr.Button("Generate Caption")
    generate_button.click(fn=get_image_caption, inputs=image_input, outputs=caption_output)

image_captioning_app.launch()