import gradio as gr
import numpy as np
import random
from diffusers import DiffusionPipeline, DDPMPipeline, DDPMScheduler
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
noise_scheduler = DDPMScheduler(num_train_timesteps=1000)
if torch.cuda.is_available():
    torch.cuda.max_memory_allocated(device=device)
    pipe = DDPMPipeline.from_pretrained("FrozenScar/cartoon_face", torch_dtype=torch.float16, variant="fp16", use_safetensors=True,scheduler=noise_scheduler)
    pipe.enable_xformers_memory_efficient_attention()
    pipe = pipe.to(device)
else: 
    pipe = DDPMPipeline.from_pretrained("FrozenScar/cartoon_face", scheduler=noise_scheduler, use_safetensors=True)
    pipe = pipe.to(device)

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

def infer(num_inference_steps,prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale):

    #if randomize_seed:
    seed = random.randint(0, MAX_SEED)
    generator = torch.Generator().manual_seed(seed)
    
    image = pipe(generator=generator,num_inference_steps=num_inference_steps).images[0] 
    
    return image

examples = [
    "OK broo",
   "Nothing brooo"
]

css="""
#col-container {
    margin: 0 auto;
    max-width: 520px;
}
"""

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"""
        # FACE GENERATOR
        Currently running on {power_device}.
        """)
        
        with gr.Row(): 
            num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=20,
                    step=1,
                    value=6,
                )
            
            run_button = gr.Button("Run", scale=0)
        
        result = gr.Image(label="Result", show_label=False)

        # with gr.Accordion("Advanced Settings", open=False):
            
        #     negative_prompt = gr.Text(
        #         label="Negative prompt",
        #         max_lines=1,
        #         placeholder="Enter a negative prompt",
        #         visible=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():
                
        #         width = gr.Slider(
        #             label="Width",
        #             minimum=256,
        #             maximum=MAX_IMAGE_SIZE,
        #             step=32,
        #             value=512,
        #         )
                
        #         height = gr.Slider(
        #             label="Height",
        #             minimum=256,
        #             maximum=MAX_IMAGE_SIZE,
        #             step=32,
        #             value=512,
        #         )
            
        #     with gr.Row():
                
        #         guidance_scale = gr.Slider(
        #             label="Guidance scale",
        #             minimum=0.0,
        #             maximum=10.0,
        #             step=0.1,
        #             value=0.0,
        #         )
                
        #         num_inference_steps = gr.Slider(
        #             label="Number of inference steps",
        #             minimum=1,
        #             maximum=120,
        #             step=1,
        #             value=2,
        #         )
        
        # gr.Examples(
        #     examples = examples,
        #     inputs = [prompt]
        # )

    run_button.click(
        fn = infer,
        inputs = [ num_inference_steps],
        outputs = [result]
    )

demo.queue().launch()