app.py

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

# Load an advanced image captioning model
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")

# Function to generate a descriptive caption
def generate_caption(image):
    inputs = processor(image, return_tensors="pt")
    out = model.generate(**inputs, max_length=50, num_beams=5, repetition_penalty=1.5)
    caption = processor.decode(out[0], skip_special_tokens=True)
    return caption

# Gradio interface with webcam support
iface = gr.Interface(
    fn=generate_caption,
    inputs=[gr.Image(type="pil", source="webcam", label="Capture an image")],
    outputs=gr.Textbox(label="Image Description"),
    title="📷 Image Capture & Description App",
    description="Capture an image using your webcam and let AI describe what's happening in the image!",
    live=True,
)

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