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

# Load BLIP model and processor
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")

def caption_image(image):
    """
    Generates a caption for the given image.
    """
    try:
        # Prepare inputs for image captioning
        inputs = processor(images=image, return_tensors="pt")

        # Generate caption
        outputs = model.generate(**inputs)
        caption = processor.decode(outputs[0], skip_special_tokens=True)

        return caption
    except Exception as e:
        return f"An error occurred: {str(e)}"

# Gradio Interface
iface = gr.Interface(
    fn=caption_image,
    inputs=gr.Image(type="pil"),
    outputs="text",
    title="Image Captioning with BLIP",
    description="Upload an image to generate a descriptive caption."
)

iface.launch()