"""
Diffusers-native Mage-VAE (DConvEncoder + DConvDenoiser/CoD decoder).

AutoencoderKLMage mirrors the AutoencoderKLFlux2Asym API surface used in this
project — ModelMixin/ConfigMixin, `from_pretrained`/`save_pretrained`,
`encode(x).latent_dist`, `decode(z, return_dict=False)[0]` — while exposing
latents shaped AND valued like the raw Flux.2 VAE: (B, 32, H/8, W/8),
2x2-unpatchified from the native 128ch @ H/16 code and denormalized with the
Flux.2 BN latent stats stored in the model config (anchor-latent
regularization, arXiv:2607.19064). No dependency on the Flux.2 VAE at runtime.

Convert the original CoD checkpoint layout once:

    python autoencoder_kl_mage.py            # MageFlow/vae -> MageFlow/vae_diffusers

then load with:

    vae = AutoencoderKLMage.from_pretrained("MageFlow/vae_diffusers", torch_dtype=torch.bfloat16)
"""

from typing import List, Optional
import math
from functools import lru_cache

import torch
import torch.nn as nn
import torch.nn.functional as F
from diffusers.configuration_utils import ConfigMixin, register_to_config
from diffusers.models.autoencoders.vae import DecoderOutput, DiagonalGaussianDistribution
from diffusers.models.modeling_outputs import AutoencoderKLOutput
from diffusers.models.modeling_utils import ModelMixin
from loguru import logger


# ---------------------------------------------------------------------------
# Primitive layers (vendored from GenCodec, inference subset)
# ---------------------------------------------------------------------------
def nonlinearity(x):
    return x * torch.sigmoid(x)


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


def modulate(x, shift, scale):
    if x.dim() == 4:
        b, c = x.shape[:2]
        return x * (1 + scale.view(b, c, 1, 1)) + shift.view(b, c, 1, 1)
    return x * (1 + scale.unsqueeze(1)) + shift.unsqueeze(1)


class LayerNorm2d(nn.LayerNorm):
    def __init__(self, num_channels, eps=1e-6, affine=True):
        super().__init__(num_channels, eps=eps, elementwise_affine=affine)

    def forward(self, x):
        # .contiguous() prevents a channels_last-strided NCHW view from
        # propagating into downstream depthwise convs, which would otherwise
        # hit a slow cuDNN path with a per-shape heuristic search.
        x = x.permute(0, 2, 3, 1).contiguous()
        x = F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
        return x.permute(0, 3, 1, 2).contiguous()


class _EncoderLayerNorm2d(LayerNorm2d):
    pass


class RMSNorm(nn.Module):
    def __init__(self, hidden_size, eps=1e-6):
        super().__init__()
        self.weight = nn.Parameter(torch.ones(hidden_size))
        self.variance_epsilon = eps

    def forward(self, x):
        in_dtype = x.dtype
        x = x.to(torch.float32)
        var = x.pow(2).mean(-1, keepdim=True)
        x = x * torch.rsqrt(var + self.variance_epsilon)
        return self.weight * x.to(in_dtype)


class TimestepEmbedder(nn.Module):
    """DConv-style timestep MLP (max_period=10000, freq_size=256, hidden=384)."""

    def __init__(self, hidden_size, frequency_embedding_size=256):
        super().__init__()
        self.mlp = nn.Sequential(
            nn.Linear(frequency_embedding_size, hidden_size, bias=True),
            nn.SiLU(),
            nn.Linear(hidden_size, hidden_size, bias=True),
        )
        self.frequency_embedding_size = frequency_embedding_size

    @staticmethod
    def timestep_embedding(t, dim, max_period=10000):
        half = dim // 2
        freqs = torch.exp(
            -math.log(max_period) * torch.arange(0, half, dtype=torch.float32) / half
        ).to(t.device)
        args = t[:, None].float() * freqs[None]
        emb = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
        if dim % 2:
            emb = torch.cat([emb, torch.zeros_like(emb[:, :1])], dim=-1)
        return emb

    def forward(self, t):
        emb = self.timestep_embedding(t, self.frequency_embedding_size)
        return self.mlp(emb.to(self.mlp[0].weight.dtype))


class BottleneckPatchEmbed(nn.Module):
    """Image patch embed concatenated with a per-patch conditioning vector."""

    def __init__(self, patch_size=16, in_chans=3, pca_dim=128, embed_dim=384, bias=True):
        super().__init__()
        self.proj1 = nn.Conv2d(in_chans, pca_dim, kernel_size=patch_size, stride=patch_size, bias=False)
        self.proj2 = nn.Conv2d(pca_dim + embed_dim, embed_dim, kernel_size=1, bias=bias)

    def forward(self, x, cond):
        return self.proj2(torch.cat([self.proj1(x), cond], dim=1))


class DiCoBlock(nn.Module):
    """DConv block with adaLN modulation."""

    def __init__(self, hidden_size, mlp_ratio=4.0):
        super().__init__()
        self.conv1 = nn.Conv2d(hidden_size, hidden_size, 1, bias=True)
        self.conv2 = nn.Conv2d(hidden_size, hidden_size, 3, padding=1, groups=hidden_size, bias=True)
        self.conv3 = nn.Conv2d(hidden_size, hidden_size, 1, bias=True)

        self.ca = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(hidden_size, hidden_size, 1, bias=True),
            nn.Sigmoid(),
        )

        ffn = int(mlp_ratio * hidden_size)
        self.conv4 = nn.Conv2d(hidden_size, ffn, 1, bias=True)
        self.conv5 = nn.Conv2d(ffn, hidden_size, 1, bias=True)

        self.norm1 = LayerNorm2d(hidden_size, affine=False)
        self.norm2 = LayerNorm2d(hidden_size, affine=False)

        self.adaLN_modulation = nn.Sequential(
            nn.SiLU(),
            nn.Linear(hidden_size, 6 * hidden_size, bias=True),
        )

    def forward(self, inp, c):
        shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = self.adaLN_modulation(c).chunk(6, dim=1)
        x = modulate(self.norm1(inp), shift_msa, scale_msa)
        x = F.gelu(self.conv2(self.conv1(x)))
        x = x * self.ca(x)
        x = self.conv3(x)
        x = inp + gate_msa[..., None, None] * x
        x = x + gate_mlp[..., None, None] * self.conv5(
            F.gelu(self.conv4(modulate(self.norm2(x), shift_mlp, scale_mlp)))
        )
        return x


class _EncoderDiCoBlock(nn.Module):
    """DiCoBlock without adaLN, for the encoder pathway."""

    def __init__(self, hidden_size, mlp_ratio=4.0):
        super().__init__()
        self.conv1 = nn.Conv2d(hidden_size, hidden_size, 1, bias=True)
        self.conv2 = nn.Conv2d(hidden_size, hidden_size, 3, padding=1, groups=hidden_size, bias=True)
        self.conv3 = nn.Conv2d(hidden_size, hidden_size, 1, bias=True)
        self.ca = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(hidden_size, hidden_size, 1, bias=True),
            nn.Sigmoid(),
        )
        ffn = int(mlp_ratio * hidden_size)
        self.conv4 = nn.Conv2d(hidden_size, ffn, 1, bias=True)
        self.conv5 = nn.Conv2d(ffn, hidden_size, 1, bias=True)
        self.norm1 = _EncoderLayerNorm2d(hidden_size)
        self.norm2 = _EncoderLayerNorm2d(hidden_size)

    def forward(self, inp):
        x = self.norm1(inp)
        x = F.gelu(self.conv2(self.conv1(x)))
        x = x * self.ca(x)
        x = self.conv3(x)
        x = inp + x
        return x + self.conv5(F.gelu(self.conv4(self.norm2(x))))


class NerfEmbedder(nn.Module):
    """Patch-position embedder used by the DConv decoder x-pathway."""

    def __init__(self, in_channels, hidden_size_input, max_freqs=8):
        super().__init__()
        self.max_freqs = max_freqs
        self.embedder = nn.Sequential(
            nn.Linear(in_channels + max_freqs ** 2, hidden_size_input, bias=True),
        )

    @lru_cache
    def fetch_pos(self, patch_size, device, dtype):
        pos = torch.linspace(0, 1, patch_size, device=device, dtype=dtype)
        pos_y, pos_x = torch.meshgrid(pos, pos, indexing="ij")
        pos_x = pos_x.reshape(-1, 1, 1)
        pos_y = pos_y.reshape(-1, 1, 1)
        freqs = torch.linspace(0, self.max_freqs, self.max_freqs, dtype=dtype, device=device)
        fx = freqs[None, :, None]
        fy = freqs[None, None, :]
        coeffs = (1 + fx * fy) ** -1
        dct_x = torch.cos(pos_x * fx * torch.pi)
        dct_y = torch.cos(pos_y * fy * torch.pi)
        return (dct_x * dct_y * coeffs).view(1, -1, self.max_freqs ** 2)

    def forward(self, x):
        B, P2, _ = x.shape
        ps = int(P2 ** 0.5)
        dct = self.fetch_pos(ps, x.device, x.dtype).expand(B, -1, -1)
        return self.embedder(torch.cat([x, dct], dim=-1))


class NerfFinalLayer(nn.Module):
    def __init__(self, hidden_size, out_channels):
        super().__init__()
        self.norm = RMSNorm(hidden_size)
        self.linear = nn.Linear(hidden_size, out_channels, bias=True)

    def forward(self, x):
        return self.linear(self.norm(x))


class SimpleMLPAdaLN(nn.Module):
    """Final small MLP that maps NerfEmbedder features to per-patch RGB."""

    def __init__(self, in_channels, model_channels, out_channels, z_channels, num_res_blocks, patch_size):
        super().__init__()
        self.in_channels = in_channels
        self.model_channels = model_channels
        self.out_channels = out_channels
        self.num_res_blocks = num_res_blocks
        self.patch_size = patch_size

        self.cond_embed = nn.Linear(z_channels, patch_size ** 2 * model_channels)
        self.input_proj = nn.Linear(in_channels, model_channels)

        self.res_blocks = nn.ModuleList(_MLPResBlock(model_channels) for _ in range(num_res_blocks))

    def forward(self, x, c):
        x = self.input_proj(x)
        c = self.cond_embed(c).reshape(c.shape[0], self.patch_size ** 2, -1)
        for block in self.res_blocks:
            x = block(x, c)
        return x


class _MLPResBlock(nn.Module):
    def __init__(self, channels):
        super().__init__()
        self.in_ln = nn.LayerNorm(channels, eps=1e-6)
        self.mlp = nn.Sequential(
            nn.Linear(channels, channels, bias=True),
            nn.SiLU(),
            nn.Linear(channels, channels, bias=True),
        )
        self.adaLN_modulation = nn.Sequential(
            nn.SiLU(),
            nn.Linear(channels, 3 * channels, bias=True),
        )

    def forward(self, x, y):
        shift, scale, gate = self.adaLN_modulation(y).chunk(3, dim=-1)
        h = self.in_ln(x) * (1 + scale) + shift
        return x + gate * self.mlp(h)


class ResnetBlock(nn.Module):
    """GroupNorm + Conv ResBlock used by the CoD Decoder."""

    def __init__(self, *, in_channels, out_channels=None, dropout=0.0):
        super().__init__()
        out_channels = out_channels or in_channels
        self.in_channels = in_channels
        self.out_channels = out_channels

        self.norm1 = Normalize(in_channels)
        self.conv1 = nn.Conv2d(in_channels, out_channels, 3, padding=1)
        self.norm2 = Normalize(out_channels)
        self.dropout = nn.Dropout(dropout)
        self.conv2 = nn.Conv2d(out_channels, out_channels, 3, padding=1)
        if in_channels != out_channels:
            self.nin_shortcut = nn.Conv2d(in_channels, out_channels, 1)

    def forward(self, x):
        h = self.conv1(nonlinearity(self.norm1(x)))
        h = self.conv2(self.dropout(nonlinearity(self.norm2(h))))
        if self.in_channels != self.out_channels:
            x = self.nin_shortcut(x)
        return x + h


class AttnBlock(nn.Module):
    """Patched self-attention used at inference (eval mode of the original)."""

    def __init__(self, in_channels, patch_size=32):
        super().__init__()
        self.in_channels = in_channels
        self.patch_size = patch_size
        self.norm = Normalize(in_channels)
        self.q = nn.Conv2d(in_channels, in_channels, 1)
        self.k = nn.Conv2d(in_channels, in_channels, 1)
        self.v = nn.Conv2d(in_channels, in_channels, 1)
        self.proj_out = nn.Conv2d(in_channels, in_channels, 1)

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

        d = self.patch_size
        b, c, H, W = Q.shape
        pad_h = (d - H % d) % d
        pad_w = (d - W % d) % d
        if pad_h or pad_w:
            Q = F.pad(Q, (0, pad_w, 0, pad_h), mode="replicate")
            K = F.pad(K, (0, pad_w, 0, pad_h), mode="replicate")
            V = F.pad(V, (0, pad_w, 0, pad_h), mode="replicate")
        _, _, H_pad, W_pad = Q.shape
        nph, npw = H_pad // d, W_pad // d
        np_ = nph * npw

        def to_patches(t):
            return (t.reshape(b, c, nph, d, npw, d)
                    .permute(0, 2, 4, 1, 3, 5)
                    .reshape(b * np_, c, d * d))

        Q = to_patches(Q)
        K = to_patches(K)
        V = to_patches(V)

        w_ = torch.bmm(Q.permute(0, 2, 1), K) * (c ** -0.5)
        w_ = F.softmax(w_, dim=2).permute(0, 2, 1)
        h_ = torch.bmm(V, w_).reshape(b, nph, npw, c, d, d).permute(0, 3, 1, 4, 2, 5).reshape(b, c, H_pad, W_pad)
        if pad_h or pad_w:
            h_ = h_[:, :, :H, :W]
        return x + self.proj_out(h_)


# ---------------------------------------------------------------------------
# adaLN constant-folding: at fixed t=0, adaLN_modulation(c) is constant.
# Replace the MLP with a buffer so DiCoBlock.forward stays unchanged and
# torch.compile can fuse the surrounding ops normally.
# ---------------------------------------------------------------------------
class _ConstAdaLN(nn.Module):
    def __init__(self, modulation: torch.Tensor):
        super().__init__()
        self.register_buffer("modulation", modulation.detach().clone())

    def forward(self, c):
        b = c.shape[0]
        if self.modulation.shape[0] != b:
            return self.modulation.expand(b, *self.modulation.shape[1:])
        return self.modulation


def _replace_adaln_with_const(module: nn.Module, c: torch.Tensor) -> int:
    # Only DiCoBlock is targeted: its adaLN is conditioned solely on t.
    # Other adaLN_modulation submodules (e.g. _MLPResBlock in the decoder MLP)
    # take a per-position latent and must not be folded.
    n = 0
    for child in module.modules():
        if not isinstance(child, DiCoBlock):
            continue
        adaln = child.adaLN_modulation
        if isinstance(adaln, _ConstAdaLN):
            continue
        with torch.no_grad():
            mod = adaln(c)
        child.adaLN_modulation = _ConstAdaLN(mod)
        n += 1
    return n


# ---------------------------------------------------------------------------
# CoD Decoder: latent → conditioning features for the denoiser
# ---------------------------------------------------------------------------
class _Decoder(nn.Module):
    """ds=16, up2x=True, light=True only."""

    def __init__(self, out_ch=384, z_ch=128):
        super().__init__()
        self.conv_in = nn.Conv2d(z_ch, out_ch, kernel_size=3, stride=1, padding=1)
        self.block = nn.Sequential(
            ResnetBlock(in_channels=out_ch, out_channels=out_ch),
            AttnBlock(out_ch, patch_size=32),
            ResnetBlock(in_channels=out_ch, out_channels=out_ch),
            AttnBlock(out_ch, patch_size=32),
            ResnetBlock(in_channels=out_ch, out_channels=out_ch),
        )
        self.norm_out = Normalize(out_ch)
        self.conv_out = nn.Conv2d(out_ch, out_ch, kernel_size=3, stride=1, padding=1)
        self.ada = nn.Identity()

    def forward(self, z):
        h = self.block(self.conv_in(z))
        h = self.conv_out(nonlinearity(self.norm_out(h)))
        return self.ada(h)


# ---------------------------------------------------------------------------
# DConvEncoder: image → packed (mean, logvar) latent
# ---------------------------------------------------------------------------
class _DConvEncoder(nn.Module):
    def __init__(
        self,
        z_ch=128,
        hidden_size=384,
        num_blocks=21,
        patch_size=16,
        mlp_ratio=4.0,
        head_size=768,
        num_head_blocks=2,
        out_ch_mult=2,
    ):
        super().__init__()
        self.z_ch = z_ch
        self.patch_size = patch_size
        self.patch_cond_embed = nn.Conv2d(3, head_size, kernel_size=patch_size, stride=patch_size, bias=True)
        self.head_blocks = nn.ModuleList([
            _EncoderDiCoBlock(head_size, mlp_ratio=mlp_ratio) for _ in range(num_head_blocks)
        ])
        self.proj_down = nn.Conv2d(head_size, hidden_size, kernel_size=1, bias=True)
        self.z_proj = nn.Conv2d(z_ch, hidden_size, kernel_size=1, bias=True)
        self.fuse_proj = nn.Conv2d(hidden_size * 2, hidden_size, kernel_size=1, bias=True)
        self.t_embedder = TimestepEmbedder(hidden_size)
        self.blocks = nn.ModuleList([
            DiCoBlock(hidden_size, mlp_ratio=mlp_ratio) for _ in range(num_blocks)
        ])
        self.norm_out = LayerNorm2d(hidden_size)
        self.proj_out = nn.Conv2d(hidden_size, z_ch * out_ch_mult, kernel_size=1, bias=True)

    def forward_pred(self, z_t, t, y):
        cond = self.patch_cond_embed(y)
        for block in self.head_blocks:
            cond = block(cond)
        cond = self.proj_down(cond)

        s = self.fuse_proj(torch.cat([cond, self.z_proj(z_t)], dim=1))
        c = self.t_embedder(t.view(-1))
        for block in self.blocks:
            s = block(s, c)
        return self.proj_out(self.norm_out(s))


# ---------------------------------------------------------------------------
# DConv denoiser: latent (via cond) + zero noise → reconstructed image
# ---------------------------------------------------------------------------
class _YEmbedder(nn.Module):
    """Holds only the CoD decoder; the original Flux2 VAE encoder side is omitted."""

    def __init__(self, ch=384, z_ch=128):
        super().__init__()
        self.decoder = _Decoder(out_ch=ch, z_ch=z_ch)


class _DConvDenoiser(nn.Module):
    def __init__(
        self,
        patch_size=16,
        in_channels=3,
        hidden_size=384,
        hidden_size_x=32,
        mlp_ratio=4.0,
        num_blocks=24,
        num_cond_blocks=21,
        bottleneck_dim=128,
    ):
        super().__init__()
        self.in_channels = in_channels
        self.patch_size = patch_size
        self.hidden_size = hidden_size
        self.num_cond_blocks = num_cond_blocks

        self.t_embedder = TimestepEmbedder(hidden_size)
        self.y_embedder_x = nn.Conv2d(hidden_size, hidden_size_x * patch_size ** 2, 1, 1, 0)
        self.x_embedder = NerfEmbedder(in_channels + hidden_size_x, hidden_size_x, max_freqs=8)
        self.s_embedder = BottleneckPatchEmbed(patch_size, in_channels, bottleneck_dim, hidden_size, bias=True)
        self.blocks = nn.ModuleList([
            DiCoBlock(hidden_size, mlp_ratio=mlp_ratio) for _ in range(num_cond_blocks)
        ])
        self.dec_net = SimpleMLPAdaLN(
            in_channels=hidden_size_x,
            model_channels=hidden_size_x,
            out_channels=in_channels,
            z_channels=hidden_size,
            num_res_blocks=num_blocks - num_cond_blocks,
            patch_size=patch_size,
        )
        self.final_layer = NerfFinalLayer(hidden_size_x, in_channels)
        self.y_embedder = _YEmbedder(ch=hidden_size, z_ch=bottleneck_dim)

    def forward(self, x, t, cond, chunk_size=None):
        b, _, h, w = x.shape
        c = self.t_embedder(t.view(-1))

        s = self.s_embedder(x, cond)
        for block in self.blocks:
            s = block(s, c)

        length = s.shape[-2] * s.shape[-1]
        s = s.permute(0, 2, 3, 1).reshape(b, length, self.hidden_size)

        p2 = self.patch_size ** 2
        x = torch.nn.functional.unfold(x, kernel_size=self.patch_size, stride=self.patch_size)

        if chunk_size is None or chunk_size >= length:
            x = torch.cat([x, self.y_embedder_x(cond).flatten(2)], dim=1)
            x = x.reshape(b, -1, p2, length).permute(0, 3, 2, 1).flatten(0, 1)
            x = self.x_embedder(x)
            x = self.dec_net(x, s.reshape(-1, self.hidden_size))
            x = self.final_layer(x)
            x = x.transpose(1, 2).reshape(b, length, -1)
            return torch.nn.functional.fold(
                x.transpose(1, 2).contiguous(), (h, w),
                kernel_size=self.patch_size, stride=self.patch_size,
            )

        # Chunked per-patch tail: each 16x16 output patch is independent here,
        # so peak memory is capped at ~chunk_size patches with identical output.
        cond_flat = cond.flatten(2)
        out_cols = x.new_empty(b, self.in_channels * p2, length)
        for i0 in range(0, length, chunk_size):
            i1 = min(i0 + chunk_size, length)
            n = i1 - i0
            yx = self.y_embedder_x(cond_flat[:, :, i0:i1].unsqueeze(-1)).squeeze(-1)
            xc = torch.cat([x[:, :, i0:i1], yx], dim=1)
            xc = xc.reshape(b, -1, p2, n).permute(0, 3, 2, 1).flatten(0, 1)
            xc = self.x_embedder(xc)
            xc = self.dec_net(xc, s[:, i0:i1].reshape(-1, self.hidden_size))
            xc = self.final_layer(xc)
            out_cols[:, :, i0:i1] = xc.transpose(1, 2).reshape(b, n, -1).permute(0, 2, 1)
        return torch.nn.functional.fold(
            out_cols, (h, w), kernel_size=self.patch_size, stride=self.patch_size,
        )


# ---------------------------------------------------------------------------
# Wrapper
# ---------------------------------------------------------------------------


class AutoencoderKLMage(ModelMixin, ConfigMixin):
    """
    Encode: DConvEncoder (one-step diffusion, t=0) → latent_dist over (B, 32, H/8, W/8)
    Decode: DConvDenoiser + CoD Decoder (t=0)      → image (B, 3, H, W) in [-1, 1]

    With `flux_bn_mean`/`flux_bn_std` in the config, latents are emitted in and
    accepted from the raw Flux.2 VAE latent space; without them, the normalized
    anchor space. `latent_dist` is a DiagonalGaussianDistribution in the public
    latent space (mean and logvar are transformed consistently), so both
    `.mode()` and `.sample()` behave like the Flux.2 VAE's.
    """

    @register_to_config
    def __init__(
        self,
        latent_channels: int = 32,
        downsample_factor: int = 8,
        code_channels: int = 128,
        code_downsample_factor: int = 16,
        flux_bn_mean: Optional[List[float]] = None,
        flux_bn_std: Optional[List[float]] = None,
        decode_chunk_size: Optional[int] = 4096,
        folded: bool = False,
    ):
        super().__init__()
        self.encoder = _DConvEncoder()
        self.decoder = _DConvDenoiser()

        if folded:
            # Checkpoint carries precomputed t=0 modulation buffers instead of
            # the adaLN MLPs — install placeholder buffers so keys line up.
            for mod in (self.encoder, self.decoder):
                for child in mod.modules():
                    if isinstance(child, DiCoBlock):
                        out = child.adaLN_modulation[1].out_features
                        child.adaLN_modulation = _ConstAdaLN(torch.zeros(1, out))

        if flux_bn_mean is not None and flux_bn_std is not None:
            if len(flux_bn_mean) != code_channels or len(flux_bn_std) != code_channels:
                raise ValueError(
                    f"flux_bn stats must have {code_channels} entries, "
                    f"got {len(flux_bn_mean)}/{len(flux_bn_std)}"
                )
            mean = torch.tensor(flux_bn_mean, dtype=torch.float32).view(1, -1, 1, 1)
            std = torch.tensor(flux_bn_std, dtype=torch.float32).view(1, -1, 1, 1)
            self.register_buffer("bn_mean", mean, persistent=False)
            self.register_buffer("bn_std", std, persistent=False)
            self.register_buffer("bn_2logstd", 2.0 * std.log(), persistent=False)
        else:
            self.register_buffer("bn_mean", None, persistent=False)
            self.register_buffer("bn_std", None, persistent=False)
            self.register_buffer("bn_2logstd", None, persistent=False)

    # -- Flux2 2x2 latent (un)packing, diffusers channel order ---------------
    @staticmethod
    def _patchify_latents(latents: torch.Tensor) -> torch.Tensor:
        b, c, h, w = latents.shape
        latents = latents.view(b, c, h // 2, 2, w // 2, 2)
        latents = latents.permute(0, 1, 3, 5, 2, 4)
        return latents.reshape(b, c * 4, h // 2, w // 2)

    @staticmethod
    def _unpatchify_latents(latents: torch.Tensor) -> torch.Tensor:
        b, c, h, w = latents.shape
        latents = latents.reshape(b, c // 4, 2, 2, h, w)
        latents = latents.permute(0, 1, 4, 2, 5, 3)
        return latents.reshape(b, c // 4, h * 2, w * 2)

    def encode(self, x: torch.Tensor, return_dict: bool = True):
        ds = self.config.code_downsample_factor
        B, _, H, W = x.shape
        if H % ds or W % ds:
            raise ValueError(f"H, W must be multiples of {ds}, got ({H}, {W})")
        z_t = torch.zeros(B, self.config.code_channels, H // ds, W // ds, device=x.device, dtype=x.dtype)
        t = torch.zeros(B, device=x.device, dtype=x.dtype)
        out = self.encoder.forward_pred(z_t, t, x)
        mean = out[:, : self.config.code_channels]
        logvar = out[:, self.config.code_channels :].clamp(min=-20.0, max=10.0)
        if self.bn_mean is not None:
            mean = mean * self.bn_std.to(mean.dtype) + self.bn_mean.to(mean.dtype)
            logvar = logvar + self.bn_2logstd.to(logvar.dtype)
        moments = torch.cat(
            [self._unpatchify_latents(mean), self._unpatchify_latents(logvar)], dim=1
        )
        posterior = DiagonalGaussianDistribution(moments)
        if not return_dict:
            return (posterior,)
        return AutoencoderKLOutput(latent_dist=posterior)

    def decode(self, z: torch.Tensor, return_dict: bool = True):
        if z.shape[1] != self.config.latent_channels or z.shape[2] % 2 or z.shape[3] % 2:
            raise ValueError(
                f"expected Flux.2-shaped latent (B, {self.config.latent_channels}, H/8, W/8) "
                f"with even spatial dims, got {tuple(z.shape)}"
            )
        z = self._patchify_latents(z)
        if self.bn_mean is not None:
            z = (z - self.bn_mean.to(z.dtype)) / self.bn_std.to(z.dtype)
        cond = self.decoder.y_embedder.decoder(z)
        B = z.shape[0]
        H = z.shape[2] * self.config.code_downsample_factor
        W = z.shape[3] * self.config.code_downsample_factor
        noise = torch.zeros(B, 3, H, W, device=z.device, dtype=z.dtype)
        t = torch.zeros(B, device=z.device, dtype=z.dtype)
        sample = self.decoder.forward(noise, t, cond, chunk_size=self.config.decode_chunk_size)
        if not return_dict:
            return (sample,)
        return DecoderOutput(sample=sample)

    def forward(self, sample: torch.Tensor, return_dict: bool = True):
        z = self.encode(sample, return_dict=False)[0].mode()
        return self.decode(z, return_dict=return_dict)

    @torch.no_grad()
    def fold_adaln(self) -> int:
        """Constant-fold the DiCoBlock adaLN MLPs at t=0 (we only run t=0).

        Same optimization as mage_vae.MageVAE, folded in fp32 for numerical
        parity with it (MageVAE folds before its bf16 cast). Mutates the module
        structure (MLPs become buffers). No-op on checkpoints converted with
        fold=True (already folded at conversion time).
        """
        if self.config.folded:
            return 0
        p = next(self.parameters())
        n = 0
        for mod in (self.encoder, self.decoder):
            t = torch.zeros(1, device=p.device, dtype=torch.float32)
            c = mod.t_embedder.float()(t)
            for child in mod.modules():
                if isinstance(child, DiCoBlock) and not isinstance(child.adaLN_modulation, _ConstAdaLN):
                    child.adaLN_modulation = _ConstAdaLN(
                        child.adaLN_modulation.float()(c).to(p.dtype)
                    )
                    n += 1
            mod.t_embedder.to(p.dtype)
        return n

    @classmethod
    def from_pretrained(cls, *args, fold_adaln: bool = True, **kwargs):
        model = super().from_pretrained(*args, **kwargs)
        if fold_adaln:
            model.fold_adaln()
        return model


def convert_mage_ckpt(
    src_ckpt: str = "MageFlow/vae/diffusion_pytorch_model.safetensors",
    src_config: str = "MageFlow/vae/config.json",
    dst_dir: str = "MageFlow/vae_diffusers",
    dtype: torch.dtype = torch.bfloat16,
    fold: bool = True,
) -> AutoencoderKLMage:
    """One-time conversion from the CoD checkpoint layout to diffusers layout.

    'student.dconv_encoder.*' -> 'encoder.*', 'pipeline.*' -> 'decoder.*'
    (dropping the unused original-VAE 'y_embedder.encoder/bottleneck' branch);
    BN stats are carried over from the source config.json. With fold=True the
    t=0 adaLN MLPs are constant-folded in fp32 before the dtype cast and the
    checkpoint stores the modulation buffers instead (~74 MB smaller,
    ready-to-run on load with no fold step).
    """
    import json

    from safetensors.torch import load_file

    sd = load_file(src_ckpt, device="cpu")
    new_sd = {}
    for k, v in sd.items():
        if k.startswith("student.dconv_encoder."):
            new_sd["encoder." + k[len("student.dconv_encoder.") :]] = v
        elif k.startswith("pipeline."):
            nk = k[len("pipeline.") :]
            if nk.startswith("y_embedder.encoder.") or nk.startswith("y_embedder.bottleneck."):
                continue
            new_sd["decoder." + nk] = v

    with open(src_config) as f:
        cfg = json.load(f)
    model = AutoencoderKLMage(
        flux_bn_mean=cfg.get("flux_bn_mean"), flux_bn_std=cfg.get("flux_bn_std")
    )
    missing, unexpected = model.load_state_dict(new_sd, strict=False)
    logger.info(
        f"convert_mage_ckpt: {len(new_sd)} keys mapped, missing={len(missing)}, "
        f"unexpected={len(unexpected)}"
    )
    if missing:
        raise RuntimeError(f"convert_mage_ckpt: missing model keys: {missing[:10]}")
    if fold:
        n = model.fold_adaln()
        model.register_to_config(folded=True)
        logger.info(f"convert_mage_ckpt: constant-folded {n} adaLN blocks at t=0")
    model.to(dtype).save_pretrained(dst_dir)
    logger.info(f"convert_mage_ckpt: saved to {dst_dir} ({dtype})")
    return model


if __name__ == "__main__":
    convert_mage_ckpt()