app.py

import gradio as gr
from PIL import Image
from transformers import pipeline

# Initialize the pipeline with the image captioning model
caption_pipeline = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")

def generate_caption(image):
    # Convert the PIL Image to the format expected by the model
    image = Image.open(image).convert("RGB")
    
    # Use the pipeline to generate a caption
    result = caption_pipeline(image)
    caption = result[0]["generated_text"]
    
    return caption

# Setup the Gradio interface
interface = gr.Interface(fn=generate_caption,
                         inputs=gr.inputs.Image(type="pil", label="Upload an Image"),
                         outputs=gr.outputs.Textbox(label="Generated Caption"))
interface.launch()