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

hf_tkn = os.environ.get("HF_TKN")
login(hf_tkn)

translator = Translator()
basemodel = "black-forest-labs/FLUX.1-dev"
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 handle_file(img_path):
    return Image.open(img_path)

def get_upscale_finegrain(prompt, img_path, upscale_factor):
    if upscale_factor == 0:
        return handle_file(img_path)
    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"
    )
    print(result)
    return result[1]

async def upscale_image(image, upscale_factor):
    try:
        result = get_upscale_finegrain(
            prompt="",
            img_path=image,
            upscale_factor=upscale_factor
        )
    except Exception as e:
        raise gr.Error(f"Error in {e}")
    
    return result

async def generate_image(
    prompt:str,
    model:str,
    lora_word:str,
    width:int=768,
    height:int=1024,
    scales:float=3.5,
    steps:int=24,
    seed:int=-1
):
    if seed == -1:
        seed = random.randint(0, MAX_SEED)
    seed = int(seed)
    print(f'prompt:{prompt}')
    
    text = str(translator.translate(prompt, 'English')) + "," + lora_word

    try:
        image = gr.Image(type="pil", image=gr.processing_utils.encode_pil_image(text_to_image(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:str,
    lora_add:str="XLabs-AI/flux-RealismLora",
    lora_word:str="",
    width:int=768,
    height:int=1024,
    scales:float=3.5,
    steps:int=24,
    seed:int=-1,
    upscale_factor:int=0
):
    model = enable_lora(lora_add)
    image, seed = await generate_image(prompt,model,lora_word,width,height,scales,steps,seed)
    
    upscaled_image = await upscale_image(image, upscale_factor)
    return upscaled_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='Imagen generada por Flux', height=600)
            with gr.Row():
                prompt = gr.Textbox(label='Ingresa tu prompt (Multi-Idiomas)', placeholder="Ingresa prompt...", scale=6)
                sendBtn = gr.Button(scale=1, variant='primary')
        with gr.Accordion("Opciones avanzadas", open=True):
            with gr.Column(scale=1):
                width = gr.Slider(label="Ancho", minimum=512, maximum=1280, step=8, value=768)
                height = gr.Slider(label="Alto", minimum=512, maximum=1280, step=8, value=1024)
                scales = gr.Slider(label="Guía", minimum=3.5, maximum=7, step=0.1, value=3.5)
                steps = gr.Slider(label="Pasos", minimum=1, maximum=50, step=1)
                upscale_factor = gr.Slider(label="Factor de escala", minimum=0, maximum=4, step=1, value=0)
                seed = gr.Number(label="Semilla", value=-1)
                sendBtn.click(gen, inputs=[prompt, lora_add, lora_word, width, height, scales, steps, seed, upscale_factor], outputs=[img])
demo.launch()