import gradio as gr
from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image
import requests

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

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

iface = gr.Interface(
    fn=generate_caption,
    inputs=gr.Image(type="pil"),
    outputs="text",
    title="🖼️ AI Image Captioning",
    description="Upload an image, and the AI will generate a descriptive caption!"
)

iface.launch(share=True)