app.py

import gradio as gr
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")

def execute(image): 
    model_inputs = processor(image, return_tensors="pt")
    output = processor.decode(model.generate(**model_inputs)[0], skip_special_tokens=True)
    return output
    
iface = gr.Interface(fn=execute, inputs="image", outputs="textbox")
iface.launch()