app.py

import gradio as gr
from urllib.parse import urlparse
import requests
import time
import base64
import os
from io import BytesIO
from PIL import Image
SECRET_TOKEN = os.getenv('SECRET_TOKEN', 'default_secret')

from utils.gradio_helpers import parse_outputs, process_outputs

def decode_data_uri_to_image(data_uri):
    # parse the data uri
    header, encoded = data_uri.split(",", 1)
    data = base64.b64decode(encoded)
    img = Image.open(BytesIO(data))
    return img
    
inputs = []
inputs.append(gr.Textbox(
    label="Secret Token", info="Secret Token"
))
inputs.append(gr.Textbox(
    label="Prompt", info='''Prompt'''
))

inputs.append(gr.Number(
    label="Seed", info='''Leave blank to randomize the seed''', value=None
))

names = ['secret_token', 'prompt', 'seed']

outputs = []
outputs.append(gr.Image())

expected_outputs = len(outputs)
def predict(request: gr.Request, *args, progress=gr.Progress(track_tqdm=True)):
    headers = {'Content-Type': 'application/json'}

    payload = {"input": {}}
    
    
    base_url = "http://0.0.0.0:7860"
    for i, key in enumerate(names):
        value = args[i]
        if name is "secret_token":
            if value is not SECRET_TOKEN:
                raise gr.Error("Invalid secret token! Please fork this space if you want to use it, and define your own secret token.") 
            continue
        if value and (os.path.exists(str(value))):
            value = f"{base_url}/file=" + value
        if value is not None and value != "":
            payload["input"][key] = value

    response = requests.post("http://0.0.0.0:5000/predictions", headers=headers, json=payload)

    
    if response.status_code == 201:
        follow_up_url = response.json()["urls"]["get"]
        response = requests.get(follow_up_url, headers=headers)
        while response.json()["status"] != "succeeded":
            if response.json()["status"] == "failed":
                raise gr.Error("The submission failed!")
            response = requests.get(follow_up_url, headers=headers)
            time.sleep(1)
    if response.status_code == 200:
        json_response = response.json()
        #If the output component is JSON return the entire output response 
        if(outputs[0].get_config()["name"] == "json"):
            return json_response["output"]
        predict_outputs = parse_outputs(json_response["output"])
        processed_outputs = process_outputs(predict_outputs)
        difference_outputs = expected_outputs - len(processed_outputs)
        # If less outputs than expected, hide the extra ones
        if difference_outputs > 0:
            extra_outputs = [gr.update(visible=False)] * difference_outputs
            processed_outputs.extend(extra_outputs)
        # If more outputs than expected, cap the outputs to the expected number
        elif difference_outputs < 0:
            processed_outputs = processed_outputs[:difference_outputs]
        
        return tuple(processed_outputs) if len(processed_outputs) > 1 else processed_outputs[0]
    else:
        if(response.status_code == 409):
            raise gr.Error(f"Sorry, the Cog image is still processing. Try again in a bit.")
        raise gr.Error(f"The submission failed! Error: {response.status_code}")

title = "Demo for sdxl-panoramic cog image by lucataco"
model_description = "360 Panorama SDXL image with inpainted wrapping seam"

gr.HTML("""
          <div style="z-index: 100; position: fixed; top: 0px; right: 0px; left: 0px; bottom: 0px; width: 100%; height: 100%; background: white; display: flex; align-items: center; justify-content: center; color: black;">
          <div style="text-align: center; color: black;">
          <p style="color: black;">This space is not a normal Gradio space you can use through a UI, but a microservice API designed for automated access.</p>
          <p style="color: black;">You can clone the original space here: <a href="https://huggingface.co/spaces/jbilcke-hf/panorama-space-you-can-duplicate" target="_blank">jbilcke-hf/panorama-space-you-can-duplicate</a>.</p>
          </div>
          </div>""")

app = gr.Interface(
    fn=predict,
    inputs=inputs,
    outputs=outputs,
    title=title,
    description=model_description,
    allow_flagging="never",
)
app.launch(share=True)