app.py

import gradio as gr
# from PIL import Image
from transformers.utils import logging
from transformers import BlipForConditionalGeneration, AutoProcessor

logging.set_verbosity_error()

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

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

image_input = gr.inputs.Image()
caption_output = gr.outputs.Textbox()

gr.Interface(caption_image, image_input, caption_output).launch()