# This space used model: stabilityai/stable-diffusion-xl-base-1.0
# and model: stabilityai/stable-diffusion-xl-refiner-1.0


import numpy as np
import gradio as gr
import requests
import time
import json
import base64
import os
from PIL import Image
from io import BytesIO

batch_size=1
batch_count=1

class Prodia:
    def __init__(self, api_key, base=None):
        self.base = base or "https://api.prodia.com/v1"
        self.headers = {
            "X-Prodia-Key": api_key
        }

    def generate(self, params):
        response = self._post(f"{self.base}/sdxl/generate", params)
        return response.json()

    def get_job(self, job_id):
        response = self._get(f"{self.base}/job/{job_id}")
        return response.json()

    def wait(self, job):
        job_result = job

        while job_result['status'] not in ['succeeded', 'failed']:
            time.sleep(0.25)
            job_result = self.get_job(job['job'])

        return job_result

    def list_models(self):
        response = self._get(f"{self.base}/sdxl/models")
        return response.json()

    def list_samplers(self):
        response = self._get(f"{self.base}/sdxl/samplers")
        return response.json()

    def _post(self, url, params):
        headers = {
            **self.headers,
            "Content-Type": "application/json"
        }
        response = requests.post(url, headers=headers, data=json.dumps(params))

        if response.status_code != 200:
            raise Exception(f"Bad Prodia Response: {response.status_code}")

        return response

    def _get(self, url):
        response = requests.get(url, headers=self.headers)

        if response.status_code != 200:
            raise Exception(f"Bad Prodia Response: {response.status_code}")

        return response


def image_to_base64(image_path):
    # Open the image with PIL
    with Image.open(image_path) as image:
        # Convert the image to bytes
        buffered = BytesIO()
        image.save(buffered, format="PNG")  # You can change format to PNG if needed

        # Encode the bytes to base64
        img_str = base64.b64encode(buffered.getvalue())

    return img_str.decode('utf-8')  # Convert bytes to string



prodia_client = Prodia(api_key=os.getenv("API_KEY"))

def flip_text(prompt, negative_prompt, steps, cfg_scale, width, height, seed):
    result = prodia_client.generate({
        "prompt": prompt,
        "negative_prompt": negative_prompt,
        "model": "sd_xl_base_1.0.safetensors [be9edd61]",
        "steps": steps,
        "sampler": "DPM++ 2M Karras",
        "cfg_scale": cfg_scale,
        "width": width,
        "height": height,
        "seed": seed
    })

    job = prodia_client.wait(result)

    return job["imageUrl"]



with gr.Blocks() as demo:
    with gr.Row():
        with gr.Column(scale=1):
            gr.HTML(value=""""<h1><center>Fast SDXL on <a href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0" target="_blank">stabilityai/stable-diffusion-xl-base-1.0</a>""")
    with gr.Row():    
        with gr.Column(scale=6, min_width=600):  
            prompt = gr.Textbox(label="Prompt", placeholder="a cute cat, 8k", show_label=True, lines=1)
            text_button = gr.Button("Generate", variant='primary', elem_id="generate")
    with gr.Row():    
        with gr.Column(scale=1):
            image_output = gr.Image()
    with gr.Row():
        with gr.Accordion("Additionals inputs", open=False):
            with gr.Column(scale=1):
                negative_prompt = gr.Textbox(label="Negative Prompt", value="text, blurry", placeholder="What you don't want to see in the image", show_label=True, lines=1)
            with gr.Column(scale=1):
                steps = gr.Slider(label="Sampling Steps", minimum=1, maximum=30, value=25, step=1)
                cfg_scale = gr.Slider(label="CFG Scale", minimum=1, maximum=20, value=7, step=1)
                seed = gr.Number(label="Seed", value=-1)
            with gr.Column(scale=1):
                width = gr.Slider(label="↔️ Width", minimum=1024, maximum=1024, value=1024, step=8)
                height = gr.Slider(label="↕️ Height", minimum=1024, maximum=1024, value=1024, step=8)





        text_button.click(flip_text, inputs=[prompt, negative_prompt, steps, cfg_scale, width, height, seed], outputs=image_output)

demo.queue(concurrency_count=16, max_size=20, api_open=False).launch(max_threads=64)