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

model_id = "GusRot/blip-flickr8k-finetuned"
processor = BlipProcessor.from_pretrained(model_id)
model = BlipForConditionalGeneration.from_pretrained(model_id)

def generate_caption(image):
    inputs = processor(images=image, return_tensors="pt")
    output_ids = model.generate(**inputs, max_new_tokens=30)
    caption = processor.decode(output_ids[0], skip_special_tokens=True)
    return caption

demo = gr.Interface(
    fn=generate_caption,
    inputs=gr.Image(type="pil"),
    outputs="text",
    title="Alt Text Generator",
    description="Generate accessible alt text from images using BLIP"
)

demo.launch()