# adopted from
# https://github.com/openai/improved-diffusion/blob/main/improved_diffusion/gaussian_diffusion.py
# and
# https://github.com/lucidrains/denoising-diffusion-pytorch/blob/7706bdfc6f527f58d33f84b7b522e61e6e3164b3/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
# and
# https://github.com/openai/guided-diffusion/blob/0ba878e517b276c45d1195eb29f6f5f72659a05b/guided_diffusion/nn.py
#
# thanks!


import math
import logging
import torch
import torch.nn as nn
import numpy as np
from einops import repeat, rearrange

from comfy.ldm.util import instantiate_from_config

class AlphaBlender(nn.Module):
    strategies = ["learned", "fixed", "learned_with_images"]

    def __init__(
        self,
        alpha: float,
        merge_strategy: str = "learned_with_images",
        rearrange_pattern: str = "b t -> (b t) 1 1",
    ):
        super().__init__()
        self.merge_strategy = merge_strategy
        self.rearrange_pattern = rearrange_pattern

        assert (
            merge_strategy in self.strategies
        ), f"merge_strategy needs to be in {self.strategies}"

        if self.merge_strategy == "fixed":
            self.register_buffer("mix_factor", torch.Tensor([alpha]))
        elif (
            self.merge_strategy == "learned"
            or self.merge_strategy == "learned_with_images"
        ):
            self.register_parameter(
                "mix_factor", torch.nn.Parameter(torch.Tensor([alpha]))
            )
        else:
            raise ValueError(f"unknown merge strategy {self.merge_strategy}")

    def get_alpha(self, image_only_indicator: torch.Tensor, device) -> torch.Tensor:
        # skip_time_mix = rearrange(repeat(skip_time_mix, 'b -> (b t) () () ()', t=t), '(b t) 1 ... -> b 1 t ...', t=t)
        if self.merge_strategy == "fixed":
            # make shape compatible
            # alpha = repeat(self.mix_factor, '1 -> b () t  () ()', t=t, b=bs)
            alpha = self.mix_factor.to(device)
        elif self.merge_strategy == "learned":
            alpha = torch.sigmoid(self.mix_factor.to(device))
            # make shape compatible
            # alpha = repeat(alpha, '1 -> s () ()', s = t * bs)
        elif self.merge_strategy == "learned_with_images":
            if image_only_indicator is None:
                alpha = rearrange(torch.sigmoid(self.mix_factor.to(device)), "... -> ... 1")
            else:
                alpha = torch.where(
                    image_only_indicator.bool(),
                    torch.ones(1, 1, device=image_only_indicator.device),
                    rearrange(torch.sigmoid(self.mix_factor.to(image_only_indicator.device)), "... -> ... 1"),
                )
            alpha = rearrange(alpha, self.rearrange_pattern)
            # make shape compatible
            # alpha = repeat(alpha, '1 -> s () ()', s = t * bs)
        else:
            raise NotImplementedError()
        return alpha

    def forward(
        self,
        x_spatial,
        x_temporal,
        image_only_indicator=None,
    ) -> torch.Tensor:
        alpha = self.get_alpha(image_only_indicator, x_spatial.device)
        x = (
            alpha.to(x_spatial.dtype) * x_spatial
            + (1.0 - alpha).to(x_spatial.dtype) * x_temporal
        )
        return x


def make_beta_schedule(schedule, n_timestep, linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
    if schedule == "linear":
        betas = (
                torch.linspace(linear_start ** 0.5, linear_end ** 0.5, n_timestep, dtype=torch.float64) ** 2
        )

    elif schedule == "cosine":
        timesteps = (
                torch.arange(n_timestep + 1, dtype=torch.float64) / n_timestep + cosine_s
        )
        alphas = timesteps / (1 + cosine_s) * np.pi / 2
        alphas = torch.cos(alphas).pow(2)
        alphas = alphas / alphas[0]
        betas = 1 - alphas[1:] / alphas[:-1]
        betas = torch.clamp(betas, min=0, max=0.999)

    elif schedule == "squaredcos_cap_v2":  # used for karlo prior
        # return early
        return betas_for_alpha_bar(
            n_timestep,
            lambda t: math.cos((t + 0.008) / 1.008 * math.pi / 2) ** 2,
        )

    elif schedule == "sqrt_linear":
        betas = torch.linspace(linear_start, linear_end, n_timestep, dtype=torch.float64)
    elif schedule == "sqrt":
        betas = torch.linspace(linear_start, linear_end, n_timestep, dtype=torch.float64) ** 0.5
    else:
        raise ValueError(f"schedule '{schedule}' unknown.")
    return betas


def make_ddim_timesteps(ddim_discr_method, num_ddim_timesteps, num_ddpm_timesteps, verbose=True):
    if ddim_discr_method == 'uniform':
        c = num_ddpm_timesteps // num_ddim_timesteps
        ddim_timesteps = np.asarray(list(range(0, num_ddpm_timesteps, c)))
    elif ddim_discr_method == 'quad':
        ddim_timesteps = ((np.linspace(0, np.sqrt(num_ddpm_timesteps * .8), num_ddim_timesteps)) ** 2).astype(int)
    else:
        raise NotImplementedError(f'There is no ddim discretization method called "{ddim_discr_method}"')

    # assert ddim_timesteps.shape[0] == num_ddim_timesteps
    # add one to get the final alpha values right (the ones from first scale to data during sampling)
    steps_out = ddim_timesteps + 1
    if verbose:
        logging.info(f'Selected timesteps for ddim sampler: {steps_out}')
    return steps_out


def make_ddim_sampling_parameters(alphacums, ddim_timesteps, eta, verbose=True):
    # select alphas for computing the variance schedule
    alphas = alphacums[ddim_timesteps]
    alphas_prev = np.asarray([alphacums[0]] + alphacums[ddim_timesteps[:-1]].tolist())

    # according the the formula provided in https://arxiv.org/abs/2010.02502
    sigmas = eta * np.sqrt((1 - alphas_prev) / (1 - alphas) * (1 - alphas / alphas_prev))
    if verbose:
        logging.info(f'Selected alphas for ddim sampler: a_t: {alphas}; a_(t-1): {alphas_prev}')
        logging.info(f'For the chosen value of eta, which is {eta}, '
              f'this results in the following sigma_t schedule for ddim sampler {sigmas}')
    return sigmas, alphas, alphas_prev


def betas_for_alpha_bar(num_diffusion_timesteps, alpha_bar, max_beta=0.999):
    """
    Create a beta schedule that discretizes the given alpha_t_bar function,
    which defines the cumulative product of (1-beta) over time from t = [0,1].
    :param num_diffusion_timesteps: the number of betas to produce.
    :param alpha_bar: a lambda that takes an argument t from 0 to 1 and
                      produces the cumulative product of (1-beta) up to that
                      part of the diffusion process.
    :param max_beta: the maximum beta to use; use values lower than 1 to
                     prevent singularities.
    """
    betas = []
    for i in range(num_diffusion_timesteps):
        t1 = i / num_diffusion_timesteps
        t2 = (i + 1) / num_diffusion_timesteps
        betas.append(min(1 - alpha_bar(t2) / alpha_bar(t1), max_beta))
    return np.array(betas)


def extract_into_tensor(a, t, x_shape):
    b, *_ = t.shape
    out = a.gather(-1, t)
    return out.reshape(b, *((1,) * (len(x_shape) - 1)))


def checkpoint(func, inputs, params, flag):
    """
    Evaluate a function without caching intermediate activations, allowing for
    reduced memory at the expense of extra compute in the backward pass.
    :param func: the function to evaluate.
    :param inputs: the argument sequence to pass to `func`.
    :param params: a sequence of parameters `func` depends on but does not
                   explicitly take as arguments.
    :param flag: if False, disable gradient checkpointing.
    """
    if flag:
        args = tuple(inputs) + tuple(params)
        return CheckpointFunction.apply(func, len(inputs), *args)
    else:
        return func(*inputs)


class CheckpointFunction(torch.autograd.Function):
    @staticmethod
    def forward(ctx, run_function, length, *args):
        ctx.run_function = run_function
        ctx.input_tensors = list(args[:length])
        ctx.input_params = list(args[length:])
        ctx.gpu_autocast_kwargs = {"enabled": torch.is_autocast_enabled(),
                                   "dtype": torch.get_autocast_gpu_dtype(),
                                   "cache_enabled": torch.is_autocast_cache_enabled()}
        with torch.no_grad():
            output_tensors = ctx.run_function(*ctx.input_tensors)
        return output_tensors

    @staticmethod
    def backward(ctx, *output_grads):
        ctx.input_tensors = [x.detach().requires_grad_(True) for x in ctx.input_tensors]
        with torch.enable_grad(), \
                torch.cuda.amp.autocast(**ctx.gpu_autocast_kwargs):
            # Fixes a bug where the first op in run_function modifies the
            # Tensor storage in place, which is not allowed for detach()'d
            # Tensors.
            shallow_copies = [x.view_as(x) for x in ctx.input_tensors]
            output_tensors = ctx.run_function(*shallow_copies)
        input_grads = torch.autograd.grad(
            output_tensors,
            ctx.input_tensors + ctx.input_params,
            output_grads,
            allow_unused=True,
        )
        del ctx.input_tensors
        del ctx.input_params
        del output_tensors
        return (None, None) + input_grads


def timestep_embedding(timesteps, dim, max_period=10000, repeat_only=False):
    """
    Create sinusoidal timestep embeddings.
    :param timesteps: a 1-D Tensor of N indices, one per batch element.
                      These may be fractional.
    :param dim: the dimension of the output.
    :param max_period: controls the minimum frequency of the embeddings.
    :return: an [N x dim] Tensor of positional embeddings.
    """
    if not repeat_only:
        half = dim // 2
        freqs = torch.exp(
            -math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32, device=timesteps.device) / half
        )
        args = timesteps[:, None].float() * freqs[None]
        embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
        if dim % 2:
            embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
    else:
        embedding = repeat(timesteps, 'b -> b d', d=dim)
    return embedding


def zero_module(module):
    """
    Zero out the parameters of a module and return it.
    """
    for p in module.parameters():
        p.detach().zero_()
    return module


def scale_module(module, scale):
    """
    Scale the parameters of a module and return it.
    """
    for p in module.parameters():
        p.detach().mul_(scale)
    return module


def mean_flat(tensor):
    """
    Take the mean over all non-batch dimensions.
    """
    return tensor.mean(dim=list(range(1, len(tensor.shape))))


def avg_pool_nd(dims, *args, **kwargs):
    """
    Create a 1D, 2D, or 3D average pooling module.
    """
    if dims == 1:
        return nn.AvgPool1d(*args, **kwargs)
    elif dims == 2:
        return nn.AvgPool2d(*args, **kwargs)
    elif dims == 3:
        return nn.AvgPool3d(*args, **kwargs)
    raise ValueError(f"unsupported dimensions: {dims}")


class HybridConditioner(nn.Module):

    def __init__(self, c_concat_config, c_crossattn_config):
        super().__init__()
        self.concat_conditioner = instantiate_from_config(c_concat_config)
        self.crossattn_conditioner = instantiate_from_config(c_crossattn_config)

    def forward(self, c_concat, c_crossattn):
        c_concat = self.concat_conditioner(c_concat)
        c_crossattn = self.crossattn_conditioner(c_crossattn)
        return {'c_concat': [c_concat], 'c_crossattn': [c_crossattn]}


def noise_like(shape, device, repeat=False):
    repeat_noise = lambda: torch.randn((1, *shape[1:]), device=device).repeat(shape[0], *((1,) * (len(shape) - 1)))
    noise = lambda: torch.randn(shape, device=device)
    return repeat_noise() if repeat else noise()