app.py

import gradio as gr
from transformers import pipeline

# Load the image-to-text pipeline
image_to_text_pipelines = {
    "Salesforce/blip-image-captioning-base": pipeline("image-to-text", model="Salesforce/blip-image-captioning-base"),
    # Add more models if needed
}

def generate_caption(input_image, model_name="Salesforce/blip-image-captioning-base"):
    # Generate caption for the input image using the selected model
    image_to_text_pipeline = image_to_text_pipelines[model_name]
    caption = image_to_text_pipeline(input_image)[0]['generated_text']
    return caption

# Interface for launching the model
interface = gr.Interface(
    fn=generate_caption,
    inputs=gr.Image(type='pil', label="Input Image"),
    outputs="text",
    title="Image Captioning Model",
    description="This model generates captions for images.",
    theme="default",
)

# Launch the interface
interface.launch()