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 StableDiffusion3Pipeline import torch from pathos.multiprocessing import ProcessingPool as ProcessPoolExecutor import requests from lxml.html import fromstring pool = ProcessPoolExecutor(64) pool.__enter__() #model_id = "runwayml/stable-diffusion-v1-5" 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 = StableDiffusion3Pipeline.from_pretrained(model_id, torch_dtype=torch.float16, variant="fp16", use_safetensors=True, token=os.getenv('token')) pipe = pipe.to(device) else: pipe = StableDiffusion3Pipeline.from_pretrained(model_id, use_safetensors=True) pipe = pipe.to(device) def translate(text,lang): 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 = f'https://www.google.com/search?q=translate to {lang}: {text}' print(url) resp = requests.get( url = url, headers = { 'User-Agent': random.choice(user_agents) } ) print(resp) content = resp.content html = fromstring(content) rslt = html.xpath('//pre[@aria-label="Translated text"]/span') translated = rslt[0].text.strip() 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 infer(prompt): name = generate_random_string(12)+".png" english_prompt = f'TRUE {translate(prompt,"english").upper()}:' print(f'Final prompt: {english_prompt}') image = pipe( english_prompt, height=4096, width=4096, negative_prompt="", num_inference_steps=100, guidance_scale=10.0 ).images[0].save(name) return name css=""" #col-container { margin: 0 auto; max-width: 16cm; } #image-container { aspect-ratio: 1 / 1; } """ 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(elem_id="image-container", label="Result", show_label=False, type='filepath') run_button.click( fn = infer, inputs = [prompt], outputs = [result] ) demo.queue().launch()