Kokoro-API / app.py
Yaron Koresh
Update app.py
a67a3c8 verified
raw
history blame
3.86 kB
import gradio as gr
import re
#from tempfile import NamedTemporaryFile
import numpy as np
import spaces
import random
import string
from diffusers import StableDiffusionPipeline as DiffusionPipeline
import torch
from pathos.multiprocessing import ProcessingPool as ProcessPoolExecutor
import requests
from lxml.html import fromstring
pool = ProcessPoolExecutor(16)
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 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'
]
resp = requests.post(
url = "https://www.bing.com/ttranslatev3?isVertical=1&&IG=13172331D0494B12ABFA8F4454EEB479&IID=translator.5026",
data = f"&fromLang=auto-detect&to={lang}&token=cdkbEXg93_iQE28MFPv9ScrPY_fs2OAw&key=1722124106496&text={text}&tryFetchingGenderDebiasedTranslations=true",
headers = {
"content-type": "application/x-www-form-urlencoded",
'User-Agent': random.choice(user_agents)
}
)
print(resp)
jsn = resp.json()
print(jsn)
translated = jsn[0]["translations"][0]["text"]
return translated
def generate_random_string(length):
characters = string.ascii_letters + string.digits
return ''.join(random.choice(characters) for _ in range(length))
@spaces.GPU(duration=20)
def infer(prompt):
name = generate_random_string(12)+".png"
english_prompt = "Real & Reasonable Scenario: " + re.sub(f'[{string.punctuation}]', '', re.sub('[\s+]', ' ', translate(prompt,"en"))).upper().strip() + ". Generate that scenario in an authentic form. Use realistic content!"
print(f'Final prompt: {english_prompt}')
image = pipe(english_prompt).images[0].save(name)
return name
css="""
#col-container {
margin: 0 auto;
max-width: 12cm;
}
#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()