app.py

import gradio as gr

import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

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

def caption_image(raw_image):
    inputs = processor(raw_image, return_tensors="pt")
    out = model.generate(**inputs)
    return processor.decode(out[0], skip_special_tokens=True)

demo = gr.Interface(fn=caption_image, inputs="image", outputs="caption")
demo.launch()