app.py

#!/usr/bin/env python

from __future__ import annotations

import os
import gradio as gr

from app_caption import create_demo as create_demo_caption
from app_vqa import create_demo as create_demo_vqa
from prismer_model import build_deformable_conv, download_models


# Prepare model checkpoints
download_models()
build_deformable_conv()


# Demo file here
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.
Expert labels will be only computed once for the same image checked with md5sum.
"""

if (SPACE_ID := os.getenv('SPACE_ID')) is not None:
    description += f'For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings. <a href="https://huggingface.co/spaces/{SPACE_ID}?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a>'


with gr.Blocks(theme='sudeepshouche/minimalist') as demo:
    gr.Markdown(description)
    with gr.Tabs():
        with gr.TabItem('Zero-shot Image Captioning'):
            create_demo_caption()
        with gr.TabItem('Visual Question Answering'):
            create_demo_vqa()

demo.queue(api_open=False).launch()