app.py

import gradio as gr
import os
import re
#from tempfile import NamedTemporaryFile
import numpy as np
import spaces
import random
import string
from diffusers import AutoPipelineForText2Image
import torch
from pathos.multiprocessing import ProcessingPool as ProcessPoolExecutor
import requests
from lxml.html import fromstring

pool = ProcessPoolExecutor(4)
pool.__enter__()

#model_id = "runwayml/stable-diffusion-v1-5"
#model_id = "kandinsky-community/kandinsky-3"
model_id = "stabilityai/stable-diffusion-3-medium-diffusers"

device = "cuda" if torch.cuda.is_available() else "cpu"
if torch.cuda.is_available():
    torch.cuda.max_memory_allocated(device=device)
    pipe = AutoPipelineForText2Image.from_pretrained(model_id, torch_dtype=torch.float16, variant="fp16", use_safetensors=True, token=os.getenv('hf_token'))
    pipe = pipe.to(device)
else: 
    pipe = AutoPipelineForText2Image.from_pretrained(model_id, use_safetensors=True, token=os.getenv('hf_token'))
    pipe = pipe.to(device)

def translate(text,lang):
    
    if text == None or lang == None:
        return ""
        
    text = re.sub(f'[{string.punctuation}]', '', re.sub('[\s+]', ' ', text)).lower().strip()
    lang = re.sub(f'[{string.punctuation}]', '', re.sub('[\s+]', ' ', lang)).lower().strip()
    
    if text == "" or lang == "":
        return ""
        
    user_agents = [
        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
        'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.1 Safari/605.1.15',
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 13_1) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.1 Safari/605.1.15'
    ]

    url = 'https://www.google.com/search'

    resp = requests.get(
        url = url,
        params = {'q': f'{lang} translate {text}'},
        headers = {
            'User-Agent': random.choice(user_agents)
        }
    )
    
    content = resp.content
    html = fromstring(content)
    
    #src = html.xpath('//pre[@data-placeholder="Enter text"]/textarea')[0].text.strip()

    translated = text
    
    try:   
        trgt = html.xpath('//span[@class="target-language"]')[0].text.strip()
        rslt = html.xpath('//pre[@aria-label="Translated text"]/span')[0].text.strip()
        if trgt.lower() == lang.lower():
            translated = rslt
    except:
        raise Exception("Translation Error!")

    ret = re.sub(f'[{string.punctuation}]', '', re.sub('[\s+]', ' ', translated)).lower().strip()
    print(ret)
    return ret

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

@spaces.GPU(duration=120)
def Piper(_do,_dont):
    return pipe(
        _do,
        height=512,
        width=1024,
        negative_prompt=_dont,
        num_inference_steps=200,
        guidance_scale=10
    )

def infer(prompt,prompt2):
    name = generate_random_string(12)+".png"
    prompt_en = translate(prompt,"english")
    prompt2_en = translate(prompt2,"english")
    if prompt == None or prompt.strip() == "":
        _do = 'soft vivid colors, rough texture, dynamic poze, proportional arrangement, reasonable combination, amazing, realistic, award winning photograph, soft lighting, deep field, highly detailed, bright background, 16k'
    else:
        _do = f'{ prompt_en }, soft vivid colors, rough texture, dynamic poze, proportional arrangement, reasonable combination, amazing, realistic, award winning photograph, soft lighting, deep field, highly detailed, bright background, 16k'
    if prompt2 == None or prompt2.strip() == "":
        _dont = 'ugly, deformed, disfigured, poor details, bad anatomy, logos, texts, labels'
    else:
        _dont = f'ugly, deformed, disfigured, poor details, bad anatomy, {prompt2_en} where in {prompt_en}, {prompt2_en}, logos where in {prompt_en}, texts where in {prompt_en}, labels where in {prompt_en}'
    image = Piper(_do,_dont).images[0].save(name)
    return name

css="""
footer {
    display: none !important;
}
#col-container {
    margin: 0 auto;
    max-width: 15cm;
 }
#image-container {
    aspect-ratio: 1024 / 512;
}
.dropdown-arrow {
    display: none !important;
}
"""

js="""
function custom(){
    document.querySelector("div#prompt input").setAttribute("maxlength","38");
    document.querySelector("div#prompt2 input").setAttribute("maxlength","38");
}
"""

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

with gr.Blocks(theme=gr.themes.Soft(),css=css,js=js) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(f"""
            # Image Generator
            Currently running on {power_device}.
        """)
        with gr.Row():
            prompt = gr.Textbox(
                elem_id="prompt",
                placeholder="Photo Description",
                container=False,
                rtl=True,
                max_lines=1
            )
        with gr.Row():
            prompt2 = gr.Textbox(
                elem_id="prompt2",
                placeholder="Forbidden Content",
                container=False,
                rtl=True,
                max_lines=1
            )
        with gr.Row():
            run_button = gr.Button("Run")
        result = gr.Image(elem_id="image-container", label="Result", show_label=False, type='filepath', show_share_button=False)
    prompt.submit(
        fn = infer,
        inputs = [prompt,prompt2],
        outputs = [result]
    )
    prompt2.submit(
        fn = infer,
        inputs = [prompt,prompt2],
        outputs = [result]
    )
    run_button.click(
        fn = infer,
        inputs = [prompt,prompt2],
        outputs = [result]
    )

demo.queue().launch()