import gradio as gr
import numpy as np
import os 
import random
import requests
from PIL import Image
from io import BytesIO

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 2048

class APIClient:
    def __init__(self, api_key=os.getenv("API_KEY"), base_url="inference.prodia.com"):
        self.headers = {
            "Content-Type": "application/json",
            "Accept": "image/jpeg",
            "Authorization": f"Bearer {api_key}"
        }
        self.base_url = f"https://{base_url}"

    def _post(self, url, json=None):
        r = requests.post(url, headers=self.headers, json=json)
        r.raise_for_status()

        return Image.open(BytesIO(r.content)).convert("RGB")

    def job(self, config):
        body = {"type": "inference.flux.dev.txt2img.v1", "config": config}

        try:
            return self._post(f"{self.base_url}/v2/job", json=body)
        except Exception as e:
            raise gr.Error(f"Job failed: {e}")
    

def infer(prompt, seed=42, randomize_seed=False, resolution="1024x1024", guidance_scale=5.0, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)

    width, height = resolution.split("x")
        
    image = generative_api.job({
        "prompt": prompt,
        "width": int(width),
        "height": int(height),
        "seed": seed,
        "steps": num_inference_steps,
        "guidance_scale": guidance_scale
    })
    return image, seed

generative_api = APIClient()

with open("header.md", "r") as file:
    header = file.read()
 
examples = [
    "a tiny astronaut hatching from an egg on the moon",
    "a cat holding a sign that says hello world",
    "an anime illustration of a wiener schnitzel",
]

css="""
#col-container {
    margin: 0 auto;
    max-width: 520px;
}
.image-container img {
    max-width: 512px;
    max-height: 512px;
    margin: 0 auto;
    border-radius: 0px;
}
"""

with gr.Blocks(css=css) as demo:
    
    with gr.Column(elem_id="col-container"):
        gr.Markdown(header)
        with gr.Row():
            
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt"
            )
            
            run_button = gr.Button("Run", scale=0)
        
        result = gr.Image(label="Result", show_label=False, format="jpeg")
        
        with gr.Accordion("Advanced Settings", open=False):
            
            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=0,
            )
            
            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
            
            with gr.Row():
                
                resolution = gr.Dropdown(
                    label="Resolution",
                    value="1024x1024",
                    choices=[
                        "1024x1024",
                        "1024x576",
                        "576x1024"
                    ]
                )
            
            with gr.Row():

                guidance_scale = gr.Slider(
                    label="Guidance Scale",
                    minimum=1,
                    maximum=15,
                    step=0.1,
                    value=3.5,
                )
  
                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=28,
                )
        
        gr.Examples(
            examples = examples,
            fn = infer,
            inputs = [prompt],
            outputs = [result, seed],
            cache_examples="lazy"
        )

    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn = infer,
        inputs = [prompt, seed, randomize_seed, resolution, guidance_scale, num_inference_steps],
        outputs = [result, seed]
    )


demo.queue(default_concurrency_limit=10, max_size=12, api_open=False).launch(max_threads=32, show_api=False)