import gradio as gr
import numpy as np
import random
#import spaces #[uncomment to use ZeroGPU]
from pipeline import TextToImagePipeline
import torch

device ="cpu"


torch_dtype = torch.float32

pipe = TextToImagePipeline(device=device)

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024

#@spaces.GPU #[uncomment to use ZeroGPU]
def infer(prompt, num_inference_steps, amt, progress=gr.Progress(track_tqdm=True)):

    
    image = pipe(
        prompt, num_inference_steps, amt
    )
    
    return image

examples = [
    "An airplane is getting ready to land at the airport",
]

css="""
#col-container {
    margin: 0 auto;
    max-width: 640px;
}
"""

with gr.Blocks(css=css) as demo:
    
    with gr.Column(elem_id="col-container"):
        gr.Markdown(f"""
        # Text-to-Image, made by JBlitzar
        """)
        
        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(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=False):
            
            amt = gr.Slider(
                    label="Amount",
                    minimum=1,
                    maximum=8,
                    step=1,
                    value=8,
                )
            
            steps = gr.Slider(
                    label="Num inference steps",
                    minimum=10,
                    maximum=1000,
                    step=1,
                    value=1000,
                )
            
        
        gr.Examples(
            examples = examples,
            inputs = [prompt]
        )
    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn = infer,
        inputs = [prompt, steps,amt],
        outputs = [result]
    )

demo.queue().launch()