app.py

# app.py

import io
from PIL import Image
import requests
import warnings
import gradio as gr
from transformers import pipeline

# Suppress warnings
warnings.filterwarnings("ignore", message=".*Using the model-agnostic default `max_length`.*")

# Load BLIP image captioning model via Hugging Face pipeline
captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")

# Helper function to download/process image and generate caption
def caption_image(image_url):
    try:
        # Load image from URL
        response = requests.get(image_url)
        response.raise_for_status()
        image = Image.open(io.BytesIO(response.content)).convert("RGB")

        # Generate caption using the pipeline
        caption = captioner(image)[0]["generated_text"]
        return caption

    except Exception as e:
        return f"Error processing image: {str(e)}"

# Gradio interface with JPEG examples
demo = gr.Interface(
    fn=caption_image,
    inputs=gr.Textbox(label="Image URL"),
    outputs="text",
    title="Image Captioning App",
    description=(
        "Upload an image or use one of the predefined examples to generate a caption. "
        "This app uses `Salesforce/blip-image-captioning-base`."
    ),
    examples=[
        ['https://free-images.com/lg/9e46/white_bengal_tiger_tiger_0.jpg']
    ],
    flagging_mode="never"
)

if __name__ == "__main__":
    demo.launch()