app.py

import gradio as gr
from transformers import BlipProcessor, BlipForConditionalGeneration

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

def generate_caption(image):
    if image is None:
        return "Please upload an image."

    image = image.convert("RGB")

    inputs = processor(image, return_tensors="pt")
    output = model.generate(**inputs, max_new_tokens=50)

    caption = processor.decode(output[0], skip_special_tokens=True)
    return caption

demo = gr.Interface(
    fn=generate_caption,
    inputs=gr.Image(type="pil", label="Upload an Image"),
    outputs=gr.Textbox(label="Generated Caption"),
    title="AI Image Captioning App",
    description="Upload an image and generate a caption using the BLIP image captioning model."
)

demo.launch()