app.py

import os
import io
from PIL import Image
import base64 

from transformers import pipeline
import gradio as gr

hf_api_key = os.environ['HF_API_KEY']

# Load the image-to-text pipeline with BLIP model
get_completion = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")

def image_to_base64_str(pil_image):
    byte_arr = io.BytesIO()
    pil_image.save(byte_arr, format='PNG')
    byte_arr = byte_arr.getvalue()

    return str(base64.b64encode(byte_arr).decode('utf-8'))

def captioner(image):
    # The BLIP model expects a PIL image directly
    result = get_completion(image)

    return result[0]['generated_text']

demo = gr.Interface(fn=captioner,
                    inputs=[gr.Image(label="Upload image", type="pil")],
                    outputs=[gr.Textbox(label="Caption")],
                    title="Image Captioning with BLIP",
                    description="Caption any image using the BLIP model",
                    flagging_mode="never",  # Updated from allow_flagging
                    examples=["images/christmas_dog.jpg", "images/bird_flight.jpg", "images/cow.jpg"])

demo.launch(
    share=True, 
    # server_port=int(os.environ.get('PORT3', 7860))  # Uncomment if needed
)