app.py

import os
import gradio as gr
import numpy as np
import random
from huggingface_hub import AsyncInferenceClient, login
from translatepy import Translator
import requests
import re
import asyncio
from PIL import Image
from gradio_client import Client, handle_file

translator = Translator()
HF_TOKEN = os.environ.get("HF_TOKEN", None)
basemodel = "black-forest-labs/FLUX.1-schnell"
MAX_SEED = np.iinfo(np.int32).max

CSS = "footer {visibility: hidden;}"
JS = "function () {gradioURL = window.location.href;if (!gradioURL.endsWith('?__theme=dark')) {window.location.replace(gradioURL + '?__theme=dark');}}"

def enable_lora(lora_add):
    if not lora_add: return basemodel
    else: return lora_add

def get_upscale_finegrain(prompt, img_path, upscale_factor):
    client = Client("finegrain/finegrain-image-enhancer")
    result = client.predict(input_image=handle_file(img_path), prompt=prompt, negative_prompt="", seed=42, upscale_factor=upscale_factor, controlnet_scale=0.6, controlnet_decay=1, condition_scale=6, tile_width=112, tile_height=144, denoise_strength=0.35, num_inference_steps=18, solver="DDIM", api_name="/process")
    return result[1]

async def generate_image(prompt, model, lora_word, width, height, scales, steps, seed):
    if seed == -1: seed = random.randint(0, MAX_SEED)
    seed = int(seed)
    text = str(translator.translate(prompt, 'English')) + "," + lora_word
    client = AsyncInferenceClient()
    try: image = await client.text_to_image(prompt=text, height=height, width=width, guidance_scale=scales, num_inference_steps=steps, model=model)
    except Exception as e: raise gr.Error(f"Error in {e}")
    return image, seed

async def gen(prompt, lora_add, lora_word, width, height, scales, steps, seed, upscale_factor):
    model = enable_lora(lora_add)
    image, seed = await generate_image(prompt, model, lora_word, width, height, scales, steps, seed)
    if upscale_factor != 0:
        upscaled_image = get_upscale_finegrain(prompt, image, upscale_factor)
        combined_image = Image.new('RGB', (image.width + upscaled_image.width, image.height))
        combined_image.paste(image, (0, 0))
        combined_image.paste(upscaled_image, (image.width, 0))
        return combined_image, seed
    else: return image, seed

with gr.Blocks(css=CSS, js=JS, theme="Nymbo/Nymbo_Theme") as demo:
    gr.HTML("<h1><center>Flux Lab Light</center></h1>")
    with gr.Row():
        with gr.Column(scale=4):
            with gr.Row(): img = gr.Image(type="filepath", label='Comparison Image', height=600)
            with gr.Row(): prompt = gr.Textbox(label='Enter Your Prompt (Multi-Languages)', placeholder="Enter prompt...", scale=6); sendBtn = gr.Button(scale=1, variant='primary')
        with gr.Accordion("Advanced Options", open=True):
            with gr.Column(scale=1):
                width = gr.Slider(label="Width", minimum=512, maximum=1280, step=8, value=768)
                height = gr.Slider(label="Height", minimum=512, maximum=1280, step=8, value=1024)
                scales = gr.Slider(label="Guidance", minimum=3.5, maximum=7, step=0.1, value=3.5)
                steps = gr.Slider(label="Steps", minimum=1, maximum=100, step=1, value=24)
            seed = gr.Slider(label="Seeds", minimum=-1, maximum=MAX_SEED, step=1, value=-1)
            lora_add = gr.Textbox(label="Add Flux LoRA", info="Copy the HF LoRA model name here", lines=1, placeholder="Please use Warm status model")
            lora_word = gr.Textbox(label="Add Flux LoRA Trigger Word", info="Add the Trigger Word", lines=1, value="")
            upscale_factor = gr.Radio(label="UpScale Factor", choices=[0, 2, 3, 4], value=0, scale=2)
    gr.on(triggers=[prompt.submit, sendBtn.click], fn=gen, inputs=[prompt, lora_add, lora_word, width