import spaces
import gradio as gr
#from tempfile import NamedTemporaryFile
import numpy as np
import random
from diffusers import StableDiffusionPipeline as DiffusionPipeline
import torch
#from pathos.multiprocessing import ProcessingPool as ProcessPoolExecutor
import requests
from lxml.html.soupparser import fromstring

#pool = ProcessPoolExecutor(100)
#pool.__enter__()

model_id = "runwayml/stable-diffusion-v1-5"

device = "cuda" if torch.cuda.is_available() else "cpu"

if torch.cuda.is_available():
    torch.cuda.max_memory_allocated(device=device)
    pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
    pipe = pipe.to(device)
else: 
    pipe = DiffusionPipeline.from_pretrained(model_id, use_safetensors=True)
    pipe = pipe.to(device)

def he_to_en(prompt):
    html_str = requests.get( url = "https://translate.google.com", params = {"sl": "iw", "tl": "en", "op": "translate", "text": prompt} ).text()
    tree = fromstring(html_str)
    english = tree.xpath('span[lang="en"]/span/span/text()')[0]
    return english

def generate_random_string(length):
    characters = string.ascii_letters + string.digits
    return ''.join(random.choice(characters) for _ in range(length))

@spaces.GPU(25)
def infer(prompt):
    name = generate_random_string(12)+".png"
    image = pipe(he_to_en(prompt)).images[0].save(name)
    return name

css="""
#col-container {
    margin: 0 auto;
    max-width: 520px;
}
"""

if torch.cuda.is_available():
    power_device = "GPU"
else:
    power_device = "CPU"

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(f"""
            # Image Generator
            Currently running on {power_device}.
        """)
        with gr.Row():
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt",
                container=False,
            )
            run_button = gr.Button("Run", scale=0)
        result = gr.Image(label="Result", show_label=False, type='filepath')
    run_button.click(
        fn = infer,
        inputs = [prompt],
        outputs = [result]
    )

demo.queue().launch()