import math
from inspect import isfunction

import torch
import torch.nn.functional as F
from einops import rearrange, repeat
from torch import einsum, nn

from extern.ldm_zero123.modules.diffusionmodules.util import checkpoint


def exists(val):
    return val is not None


def uniq(arr):
    return {el: True for el in arr}.keys()


def default(val, d):
    if exists(val):
        return val
    return d() if isfunction(d) else d


def max_neg_value(t):
    return -torch.finfo(t.dtype).max


def init_(tensor):
    dim = tensor.shape[-1]
    std = 1 / math.sqrt(dim)
    tensor.uniform_(-std, std)
    return tensor


# feedforward
class GEGLU(nn.Module):
    def __init__(self, dim_in, dim_out):
        super().__init__()
        self.proj = nn.Linear(dim_in, dim_out * 2)

    def forward(self, x):
        x, gate = self.proj(x).chunk(2, dim=-1)
        return x * F.gelu(gate)


class FeedForward(nn.Module):
    def __init__(self, dim, dim_out=None, mult=4, glu=False, dropout=0.0):
        super().__init__()
        inner_dim = int(dim * mult)
        dim_out = default(dim_out, dim)
        project_in = (
            nn.Sequential(nn.Linear(dim, inner_dim), nn.GELU())
            if not glu
            else GEGLU(dim, inner_dim)
        )

        self.net = nn.Sequential(
            project_in, nn.Dropout(dropout), nn.Linear(inner_dim, dim_out)
        )

    def forward(self, x):
        return self.net(x)


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 Normalize(in_channels):
    return torch.nn.GroupNorm(
        num_groups=32, num_channels=in_channels, eps=1e-6, affine=True
    )


class LinearAttention(nn.Module):
    def __init__(self, dim, heads=4, dim_head=32):
        super().__init__()
        self.heads = heads
        hidden_dim = dim_head * heads
        self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, bias=False)
        self.to_out = nn.Conv2d(hidden_dim, dim, 1)

    def forward(self, x):
        b, c, h, w = x.shape
        qkv = self.to_qkv(x)
        q, k, v = rearrange(
            qkv, "b (qkv heads c) h w -> qkv b heads c (h w)", heads=self.heads, qkv=3
        )
        k = k.softmax(dim=-1)
        context = torch.einsum("bhdn,bhen->bhde", k, v)
        out = torch.einsum("bhde,bhdn->bhen", context, q)
        out = rearrange(
            out, "b heads c (h w) -> b (heads c) h w", heads=self.heads, h=h, w=w
        )
        return self.to_out(out)


class SpatialSelfAttention(nn.Module):
    def __init__(self, in_channels):
        super().__init__()
        self.in_channels = in_channels

        self.norm = Normalize(in_channels)
        self.q = torch.nn.Conv2d(
            in_channels, in_channels, kernel_size=1, stride=1, padding=0
        )
        self.k = torch.nn.Conv2d(
            in_channels, in_channels, kernel_size=1, stride=1, padding=0
        )
        self.v = torch.nn.Conv2d(
            in_channels, in_channels, kernel_size=1, stride=1, padding=0
        )
        self.proj_out = torch.nn.Conv2d(
            in_channels, in_channels, kernel_size=1, stride=1, padding=0
        )

    def forward(self, x):
        h_ = x
        h_ = self.norm(h_)
        q = self.q(h_)
        k = self.k(h_)
        v = self.v(h_)

        # compute attention
        b, c, h, w = q.shape
        q = rearrange(q, "b c h w -> b (h w) c")
        k = rearrange(k, "b c h w -> b c (h w)")
        w_ = torch.einsum("bij,bjk->bik", q, k)

        w_ = w_ * (int(c) ** (-0.5))
        w_ = torch.nn.functional.softmax(w_, dim=2)

        # attend to values
        v = rearrange(v, "b c h w -> b c (h w)")
        w_ = rearrange(w_, "b i j -> b j i")
        h_ = torch.einsum("bij,bjk->bik", v, w_)
        h_ = rearrange(h_, "b c (h w) -> b c h w", h=h)
        h_ = self.proj_out(h_)

        return x + h_


class LoRALinearLayer(nn.Module):
    def __init__(self, in_features, out_features, rank=4, network_alpha=None):
        super().__init__()

        if rank > min(in_features, out_features):
            raise ValueError(f"LoRA rank {rank} must be less or equal than {min(in_features, out_features)}")

        self.down = nn.Linear(in_features, rank, bias=False)
        self.up = nn.Linear(rank, out_features, bias=False)
        # This value has the same meaning as the `--network_alpha` option in the kohya-ss trainer script.
        # See https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning
        self.network_alpha = network_alpha
        self.rank = rank

        nn.init.normal_(self.down.weight, std=1 / rank)
        nn.init.zeros_(self.up.weight)

    def forward(self, hidden_states):
        orig_dtype = hidden_states.dtype
        dtype = self.down.weight.dtype

        down_hidden_states = self.down(hidden_states.to(dtype))
        up_hidden_states = self.up(down_hidden_states)

        if self.network_alpha is not None:
            up_hidden_states *= self.network_alpha / self.rank

        return up_hidden_states.to(orig_dtype)


class CrossAttention(nn.Module):
    def __init__(self, query_dim, context_dim=None, heads=8, dim_head=64, dropout=0.0):
        super().__init__()
        inner_dim = dim_head * heads
        context_dim = default(context_dim, query_dim)

        self.scale = dim_head**-0.5
        self.heads = heads

        self.to_q = nn.Linear(query_dim, inner_dim, bias=False)
        self.to_k = nn.Linear(context_dim, inner_dim, bias=False)
        self.to_v = nn.Linear(context_dim, inner_dim, bias=False)

        self.to_out = nn.Sequential(
            nn.Linear(inner_dim, query_dim), nn.Dropout(dropout)
        )

        self.lora = False
        self.query_dim = query_dim
        self.inner_dim = inner_dim
        self.context_dim = context_dim

    def setup_lora(self, rank=4, network_alpha=None):
        self.lora = True
        self.rank = rank
        self.to_q_lora = LoRALinearLayer(self.query_dim, self.inner_dim, rank, network_alpha)
        self.to_k_lora = LoRALinearLayer(self.context_dim, self.inner_dim, rank, network_alpha)
        self.to_v_lora = LoRALinearLayer(self.context_dim, self.inner_dim, rank, network_alpha)
        self.to_out_lora = LoRALinearLayer(self.inner_dim, self.query_dim, rank, network_alpha)
        self.lora_layers = nn.ModuleList()
        self.lora_layers.append(self.to_q_lora)
        self.lora_layers.append(self.to_k_lora)
        self.lora_layers.append(self.to_v_lora)
        self.lora_layers.append(self.to_out_lora)

    def forward(self, x, context=None, mask=None):
        h = self.heads

        q = self.to_q(x)
        context = default(context, x)
        k = self.to_k(context)
        v = self.to_v(context)

        if self.lora:
            q += self.to_q_lora(x)
            k += self.to_k_lora(context)
            v += self.to_v_lora(context)

        q, k, v = map(lambda t: rearrange(t, "b n (h d) -> (b h) n d", h=h), (q, k, v))

        sim = einsum("b i d, b j d -> b i j", q, k) * self.scale

        if exists(mask):
            mask = rearrange(mask, "b ... -> b (...)")
            max_neg_value = -torch.finfo(sim.dtype).max
            mask = repeat(mask, "b j -> (b h) () j", h=h)
            sim.masked_fill_(~mask, max_neg_value)

        # attention, what we cannot get enough of
        attn = sim.softmax(dim=-1)

        out = einsum("b i j, b j d -> b i d", attn, v)
        out = rearrange(out, "(b h) n d -> b n (h d)", h=h)
        # return self.to_out(out)

        # linear proj
        o = self.to_out[0](out)
        if self.lora:
            o += self.to_out_lora(out)
        # dropout
        out = self.to_out[1](o)

        return out


class BasicTransformerBlock(nn.Module):
    def __init__(
        self,
        dim,
        n_heads,
        d_head,
        dropout=0.0,
        context_dim=None,
        gated_ff=True,
        checkpoint=True,
        disable_self_attn=False,
    ):
        super().__init__()
        self.disable_self_attn = disable_self_attn
        self.attn1 = CrossAttention(
            query_dim=dim,
            heads=n_heads,
            dim_head=d_head,
            dropout=dropout,
            context_dim=context_dim if self.disable_self_attn else None,
        )  # is a self-attention if not self.disable_self_attn
        self.ff = FeedForward(dim, dropout=dropout, glu=gated_ff)
        self.attn2 = CrossAttention(
            query_dim=dim,
            context_dim=context_dim,
            heads=n_heads,
            dim_head=d_head,
            dropout=dropout,
        )  # is self-attn if context is none
        self.norm1 = nn.LayerNorm(dim)
        self.norm2 = nn.LayerNorm(dim)
        self.norm3 = nn.LayerNorm(dim)
        self.checkpoint = checkpoint

    def forward(self, x, context=None):
        # return checkpoint(
        #     self._forward, (x, context), self.parameters(), self.checkpoint
        # )
        return self._forward(x, context)

    def _forward(self, x, context=None):
        x = (
            self.attn1(
                self.norm1(x), context=context if self.disable_self_attn else None
            )
            + x
        )
        x = self.attn2(self.norm2(x), context=context) + x
        x = self.ff(self.norm3(x)) + x
        return x


class SpatialTransformer(nn.Module):
    """
    Transformer block for image-like data.
    First, project the input (aka embedding)
    and reshape to b, t, d.
    Then apply standard transformer action.
    Finally, reshape to image
    """

    def __init__(
        self,
        in_channels,
        n_heads,
        d_head,
        depth=1,
        dropout=0.0,
        context_dim=None,
        disable_self_attn=False,
    ):
        super().__init__()
        self.in_channels = in_channels
        inner_dim = n_heads * d_head
        self.norm = Normalize(in_channels)

        self.proj_in = nn.Conv2d(
            in_channels, inner_dim, kernel_size=1, stride=1, padding=0
        )

        self.transformer_blocks = nn.ModuleList(
            [
                BasicTransformerBlock(
                    inner_dim,
                    n_heads,
                    d_head,
                    dropout=dropout,
                    context_dim=context_dim,
                    disable_self_attn=disable_self_attn,
                )
                for d in range(depth)
            ]
        )

        self.proj_out = zero_module(
            nn.Conv2d(inner_dim, in_channels, kernel_size=1, stride=1, padding=0)
        )

    def forward(self, x, context=None):
        # note: if no context is given, cross-attention defaults to self-attention
        b, c, h, w = x.shape
        x_in = x
        x = self.norm(x)
        x = self.proj_in(x)
        x = rearrange(x, "b c h w -> b (h w) c").contiguous()
        for block in self.transformer_blocks:
            x = block(x, context=context)
        x = rearrange(x, "b (h w) c -> b c h w", h=h, w=w).contiguous()
        x = self.proj_out(x)
        return x + x_in