app.py

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

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

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

# Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("## 🖼️ Upload an image to generate a caption using BLIP")
    image_input = gr.Image(type="pil", label="Image")
    caption_output = gr.Textbox(label="Caption")
    btn = gr.Button("Generate")
    btn.click(fn=generate_caption, inputs=image_input, outputs=caption_output)

demo.launch()