import os
import gradio as gr
import torch
import yaml
import numpy as np

from munch import munchify
import torchvision.transforms as transforms
from torchvision.transforms import functional as F
from diffusers import (
    AutoPipelineForInpainting,
)
from generate_dataset import outpainting_generator_rectangle


transform = transforms.Compose([
        transforms.ToPILImage(),
        transforms.Resize((512, 512), interpolation=F.InterpolationMode.LANCZOS),
    ])

def pref_inpainting(image,
                    box_width_ratio,
                    mask_random_start,
                    steps,
                    ):
    with open("/data0/kendong/Diffusions/zero123-live/configs/imagereward_train_configs.yaml") as file:
        config_dict= yaml.safe_load(file)
        config = munchify(config_dict)

    pipe = AutoPipelineForInpainting.from_pretrained(
                '/data1/kendong/joint-rl-diffusion/alignment_log/exp_reward_group_regression_all_1w_1.6boundary/iteration_2560', num_inference_steps=steps)
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    pipe = pipe.to(device)

   
    color, mask = outpainting_generator_rectangle(image, box_width_ratio/100, mask_random_start)
    mask = mask.convert('L')
   
    color, mask = np.array(color).transpose(2, 0, 1), np.array(mask)
    mask = mask[None, ...]
    mask_ = np.zeros_like(mask)
    mask_[mask < 125] = 0
    mask_[mask >= 125] = 1
    
    color = torch.from_numpy(color).to(device)
    mask = torch.from_numpy(mask).to(device)


    color, mask = transform(color), transform(mask)
    res = pipe(prompt='', image=color, mask_image=mask, eta=config.eta).images[0]
    
    
    # res.save(os.path.join('./',  'test.png'))
    
    return color, res


inputs = [
    gr.Image(type="pil", image_mode="RGBA", label='Input Image'), # shape=[512, 512]
    gr.Slider(30, 45, value=35, step=1, label="box_width_ratio"),
    gr.Slider(0, 256, value=125, step=1, label="mask_random_start"),
    gr.Slider(30, 100, value=50, step=5, label="steps"),
]

outputs = [
    gr.Image(type="pil", image_mode="RGBA", label='Mask RGB Image', container=True, width="65%"),
    gr.Image(type="pil", image_mode="RGBA", label='Results', container=True, width="65%"), 
]

examples = [
    ["/data0/kendong/Diffusions/zero123-live/test_demo/assets/ILSVRC2012_test_00000003.JPEG", 35, 125, 50],
    ["/data0/kendong/Diffusions/zero123-live/test_demo/assets/ILSVRC2012_test_00000181.JPEG", 35, 125, 50],
    ["/data0/kendong/Diffusions/zero123-live/test_demo/assets/ILSVRC2012_test_00002334.JPEG", 35, 125, 50],
    ["/data0/kendong/Diffusions/zero123-live/test_demo/assets/ILSVRC2012_test_00002613.JPEG", 35, 125, 50],
]


        
iface = gr.Interface(
    fn=pref_inpainting,
    inputs=inputs,
    outputs=outputs,
    title="Inpainting with Human Preference (Utilizing Free CPU Resources)",
    description="Upload an image and start your inpainting (currently only supporting outpainting masks; other mask types coming soon).",
    theme="default",
    examples= examples,
    allow_flagging="never"
)


iface.launch(share=True)