app.py

from transformers import BlipForQuestionAnswering
from transformers.utils import logging
from transformers import AutoProcessor
import gradio as gr
import torch
import requests
from PIL import Image

logging.set_verbosity_error()

model = BlipForQuestionAnswering.from_pretrained(
    "Salesforce/blip-vqa-base")
processor = AutoProcessor.from_pretrained(
    "Salesforce/blip-vqa-base")

def process_image(input_type, image_url, image_upload, question):
    if input_type == "URL":
        raw_image =  Image.open(requests.get(image_url, stream=True).raw).convert('RGB')
    else:
        raw_image = image_upload

    inputs = processor(raw_image, text=question, return_tensors="pt")
    out = model.generate(**inputs)[0]
    answer = str(processor.decode(out, skip_special_tokens=True)).capitalize()
    print(answer)
    answer = (
        f"""<div>
              <h2 style='text-align: center; font-size: 30px; color: blue;'>Answer to you question about the image</h2><br>
              <h1 style='text-align: center; font-size: 50px; color: orange;'>{answer}</h1>
        </div>"""
    )
    return answer

def display_image_from_url(image_url):
    if image_url:
        image = Image.open(requests.get(image_url, stream=True).raw).convert('RGB')
        return image
    return None

def toggle_inputs(input_type):
    if input_type == "URL":
        return gr.update(visible=True), gr.update(visible=True), gr.update(visible=False), gr.update(visible=True)
    else:
        return gr.update(visible=False), gr.update(visible=False), gr.update(visible=True), gr.update(visible=True)

with gr.Blocks() as demo:
    gr.Markdown(
    """
    # Question the Image - test & demo app by Srinivas.V..
    Paste either URL of an image or upload the image, type-in your question about the image and submit.
    """)

    input_type = gr.Radio(choices=["URL", "Upload"], label="Input Type")
    image_url = gr.Textbox(label="Image URL", visible=False)
    url_image = gr.Image(type="pil", label="URL Image", visible=False)
    image_upload = gr.Image(type="pil", label="Upload Image", visible=False)
    question = gr.Textbox(label="Type the question", visible=False, lines=2)

    input_type.change(fn=toggle_inputs, inputs=input_type, outputs=[image_url, url_image, image_upload, question])
    image_url.change(fn=display_image_from_url, inputs=image_url, outputs=url_image)

    submit_btn = gr.Button("Submit")
    processed_image = gr.HTML(label="Answer to your question about the image")
    submit_btn.click(fn=process_image, inputs=[input_type, image_url, image_upload, question], outputs=processed_image)

demo.launch(debug=True, share=True)