app.py

import gradio as gr
import torch

from gradio_caption import create_demo as create_caption
from gradio_vqa import create_demo as create_vqa


css = """
#img-display-input {
    height: auto;
    max-height: 40vh;
    }
#img-display-output {
    max-height: 40vh;
    }
"""


description = """
# Prismer 
The official demo for **Prismer: A Vision-Language Model with An Ensemble of Experts**.
Please refer to our [project page](https://shikun.io/projects/prismer) or [github](https://github.com/NVlabs/prismer) for more details.
"""

with gr.Blocks(css=css) as demo:
    gr.Markdown(description)
    with gr.Tab("Zero-shot Image Captioning"):
        create_caption()
    with gr.Tab("Visual Question Answering"):
        create_vqa()


if __name__ == '__main__':
    demo.queue().launch()