apps/image_captioning.py

import gradio as gr 
from transformers import AutoProcessor
from transformers import BlipForConditionalGeneration 

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

def caption_image(image):
    inputs = processor(image, return_tensors="pt")
    output = model.generate(**inputs)
    caption = processor.decode(output[0], skip_special_tokens=True)

    return caption 

img_captioning_interface = gr.Interface(
    fn=caption_image,
    inputs=gr.Image(label="Input Image", type="pil"),
    outputs=gr.Textbox(label="Predicted Caption"),
    title="Image Caption Generator App",
    description="This app generates a caption for an image.",
    examples=["./examples/image1.jpg"]
)