# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from collections.abc import Iterable
from types import SimpleNamespace
from typing import Any

import torch
from diffusers.models.embeddings import (
    TimestepEmbedding,
    Timesteps,
    get_1d_rotary_pos_embed,
)
from diffusers.models.modeling_outputs import Transformer2DModelOutput
from diffusers.models.normalization import AdaLayerNormContinuous
from diffusers.utils import is_torch_npu_available
from torch import nn
from vllm.model_executor.layers.layernorm import RMSNorm
from vllm.model_executor.layers.linear import (
    ColumnParallelLinear,
    MergedColumnParallelLinear,
    QKVParallelLinear,
    RowParallelLinear,
)
from vllm.model_executor.model_loader.weight_utils import default_weight_loader

from vllm_omni.diffusion.attention.backends.abstract import AttentionMetadata
from vllm_omni.diffusion.attention.layer import Attention
from vllm_omni.diffusion.layers.rope import RotaryEmbedding


class Flux2SwiGLU(nn.Module):
    """SwiGLU activation used by Flux2."""

    def __init__(self):
        super().__init__()
        self.gate_fn = nn.SiLU()

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x1, x2 = x.chunk(2, dim=-1)
        return self.gate_fn(x1) * x2


class Flux2FeedForward(nn.Module):
    def __init__(
        self,
        dim: int,
        dim_out: int | None = None,
        mult: float = 3.0,
        inner_dim: int | None = None,
        bias: bool = False,
    ):
        super().__init__()
        if inner_dim is None:
            inner_dim = int(dim * mult)
        dim_out = dim_out or dim

        self.linear_in = MergedColumnParallelLinear(
            dim,
            [inner_dim, inner_dim],
            bias=bias,
            return_bias=False,
        )
        self.act_fn = Flux2SwiGLU()
        self.linear_out = RowParallelLinear(
            inner_dim,
            dim_out,
            bias=bias,
            input_is_parallel=True,
            return_bias=False,
        )

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = self.linear_in(x)
        x = self.act_fn(x)
        return self.linear_out(x)


class Flux2Attention(nn.Module):
    def __init__(
        self,
        query_dim: int,
        heads: int = 8,
        dim_head: int = 64,
        dropout: float = 0.0,
        bias: bool = False,
        added_kv_proj_dim: int | None = None,
        added_proj_bias: bool | None = True,
        out_bias: bool = True,
        eps: float = 1e-5,
        out_dim: int = None,
        elementwise_affine: bool = True,
    ):
        super().__init__()
        self.head_dim = dim_head
        self.inner_dim = out_dim if out_dim is not None else dim_head * heads
        self.query_dim = query_dim
        self.out_dim = out_dim if out_dim is not None else query_dim
        self.heads = out_dim // dim_head if out_dim is not None else heads
        self.dropout = dropout
        self.added_kv_proj_dim = added_kv_proj_dim

        self.to_qkv = QKVParallelLinear(
            hidden_size=query_dim,
            head_size=self.head_dim,
            total_num_heads=self.heads,
            bias=bias,
        )
        self.query_num_heads = self.to_qkv.num_heads
        self.kv_num_heads = self.to_qkv.num_kv_heads

        self.norm_q = RMSNorm(dim_head, eps=eps)
        self.norm_k = RMSNorm(dim_head, eps=eps)

        self.to_out = nn.ModuleList(
            [
                RowParallelLinear(
                    self.inner_dim,
                    self.out_dim,
                    bias=out_bias,
                    input_is_parallel=True,
                    return_bias=False,
                ),
                nn.Dropout(dropout),
            ]
        )

        if added_kv_proj_dim is not None:
            self.norm_added_q = RMSNorm(dim_head, eps=eps)
            self.norm_added_k = RMSNorm(dim_head, eps=eps)
            self.add_kv_proj = QKVParallelLinear(
                hidden_size=added_kv_proj_dim,
                head_size=self.head_dim,
                total_num_heads=self.heads,
                bias=added_proj_bias,
            )
            self.add_query_num_heads = self.add_kv_proj.num_heads
            self.add_kv_num_heads = self.add_kv_proj.num_kv_heads
            self.to_add_out = RowParallelLinear(
                self.inner_dim,
                query_dim,
                bias=out_bias,
                input_is_parallel=True,
                return_bias=False,
            )

        self.rope = RotaryEmbedding(is_neox_style=False)
        self.attn = Attention(
            num_heads=self.query_num_heads,
            head_size=self.head_dim,
            softmax_scale=1.0 / (self.head_dim**0.5),
            causal=False,
            num_kv_heads=self.kv_num_heads,
        )

    def forward(
        self,
        hidden_states: torch.Tensor,
        encoder_hidden_states: torch.Tensor | None = None,
        attention_mask: torch.Tensor | None = None,
        image_rotary_emb: tuple[torch.Tensor, torch.Tensor] | None = None,
        **kwargs,
    ) -> torch.Tensor | tuple[torch.Tensor, torch.Tensor]:
        qkv, _ = self.to_qkv(hidden_states)
        query, key, value = qkv.chunk(3, dim=-1)

        encoder_query = encoder_key = encoder_value = None
        if encoder_hidden_states is not None and self.added_kv_proj_dim is not None:
            encoder_qkv, _ = self.add_kv_proj(encoder_hidden_states)
            encoder_query, encoder_key, encoder_value = encoder_qkv.chunk(3, dim=-1)

        query = query.unflatten(-1, (self.query_num_heads, -1))
        key = key.unflatten(-1, (self.kv_num_heads, -1))
        value = value.unflatten(-1, (self.kv_num_heads, -1))

        query = self.norm_q(query)
        key = self.norm_k(key)

        if encoder_hidden_states is not None and self.added_kv_proj_dim is not None:
            encoder_query = encoder_query.unflatten(-1, (self.add_query_num_heads, -1))
            encoder_key = encoder_key.unflatten(-1, (self.add_kv_num_heads, -1))
            encoder_value = encoder_value.unflatten(-1, (self.add_kv_num_heads, -1))

            encoder_query = self.norm_added_q(encoder_query)
            encoder_key = self.norm_added_k(encoder_key)

            query = torch.cat([encoder_query, query], dim=1)
            key = torch.cat([encoder_key, key], dim=1)
            value = torch.cat([encoder_value, value], dim=1)

        if image_rotary_emb is not None:
            cos, sin = image_rotary_emb
            cos = cos.to(query.dtype)
            sin = sin.to(query.dtype)
            query = self.rope(query, cos, sin)
            key = self.rope(key, cos, sin)

        attn_metadata = None
        if attention_mask is not None:
            if attention_mask.dim() == 3:
                attention_mask = attention_mask.unsqueeze(1)
            attn_metadata = AttentionMetadata(attn_mask=attention_mask)

        hidden_states = self.attn(query, key, value, attn_metadata)
        hidden_states = hidden_states.flatten(2, 3).to(query.dtype)

        if encoder_hidden_states is not None:
            context_len = encoder_hidden_states.shape[1]
            encoder_hidden_states, hidden_states = hidden_states.split_with_sizes(
                [context_len, hidden_states.shape[1] - context_len],
                dim=1,
            )
            # Contiguous for FP8 quantization in RowParallelLinear
            encoder_hidden_states = self.to_add_out(encoder_hidden_states.contiguous())

        hidden_states = self.to_out[0](hidden_states.contiguous())
        hidden_states = self.to_out[1](hidden_states)

        if encoder_hidden_states is not None:
            return hidden_states, encoder_hidden_states
        return hidden_states


class Flux2ParallelSelfAttention(nn.Module):
    """
    Parallel attention block that fuses QKV projections with MLP input projections.
    """

    def __init__(
        self,
        query_dim: int,
        heads: int = 8,
        dim_head: int = 64,
        dropout: float = 0.0,
        bias: bool = False,
        out_bias: bool = True,
        eps: float = 1e-5,
        out_dim: int = None,
        elementwise_affine: bool = True,
        mlp_ratio: float = 4.0,
        mlp_mult_factor: int = 2,
    ):
        super().__init__()
        self.head_dim = dim_head
        self.inner_dim = out_dim if out_dim is not None else dim_head * heads
        self.query_dim = query_dim
        self.out_dim = out_dim if out_dim is not None else query_dim
        self.heads = out_dim // dim_head if out_dim is not None else heads
        self.dropout = dropout

        self.mlp_ratio = mlp_ratio
        self.mlp_hidden_dim = int(query_dim * self.mlp_ratio)
        self.mlp_mult_factor = mlp_mult_factor

        self.to_qkv_mlp_proj = ColumnParallelLinear(
            self.query_dim,
            self.inner_dim * 3 + self.mlp_hidden_dim * self.mlp_mult_factor,
            bias=bias,
            gather_output=True,
        )
        self.mlp_act_fn = Flux2SwiGLU()

        self.norm_q = RMSNorm(dim_head, eps=eps)
        self.norm_k = RMSNorm(dim_head, eps=eps)

        self.to_out = ColumnParallelLinear(
            self.inner_dim + self.mlp_hidden_dim,
            self.out_dim,
            bias=out_bias,
            gather_output=True,
        )
        self.rope = RotaryEmbedding(is_neox_style=False)
        self.attn = Attention(
            num_heads=self.heads,
            head_size=self.head_dim,
            softmax_scale=1.0 / (self.head_dim**0.5),
            causal=False,
        )

    def forward(
        self,
        hidden_states: torch.Tensor,
        attention_mask: torch.Tensor | None = None,
        image_rotary_emb: tuple[torch.Tensor, torch.Tensor] | None = None,
        **kwargs,
    ) -> torch.Tensor:
        hidden_states, _ = self.to_qkv_mlp_proj(hidden_states)
        qkv, mlp_hidden_states = torch.split(
            hidden_states,
            [3 * self.inner_dim, self.mlp_hidden_dim * self.mlp_mult_factor],
            dim=-1,
        )

        query, key, value = qkv.chunk(3, dim=-1)
        query = query.unflatten(-1, (self.heads, -1))
        key = key.unflatten(-1, (self.heads, -1))
        value = value.unflatten(-1, (self.heads, -1))

        query = self.norm_q(query)
        key = self.norm_k(key)

        if image_rotary_emb is not None:
            cos, sin = image_rotary_emb
            cos = cos.to(query.dtype)
            sin = sin.to(query.dtype)
            query = self.rope(query, cos, sin)
            key = self.rope(key, cos, sin)

        attn_metadata = None
        if attention_mask is not None:
            if attention_mask.dim() == 3:
                attention_mask = attention_mask.unsqueeze(1)
            attn_metadata = AttentionMetadata(attn_mask=attention_mask)

        attn_output = self.attn(query, key, value, attn_metadata)
        attn_output = attn_output.flatten(2, 3).to(query.dtype)

        mlp_hidden_states = self.mlp_act_fn(mlp_hidden_states)
        hidden_states = torch.cat([attn_output, mlp_hidden_states], dim=-1)
        hidden_states, _ = self.to_out(hidden_states)
        return hidden_states


class Flux2SingleTransformerBlock(nn.Module):
    def __init__(
        self,
        dim: int,
        num_attention_heads: int,
        attention_head_dim: int,
        mlp_ratio: float = 3.0,
        eps: float = 1e-6,
        bias: bool = False,
    ):
        super().__init__()
        self.norm = nn.LayerNorm(dim, elementwise_affine=False, eps=eps)
        self.attn = Flux2ParallelSelfAttention(
            query_dim=dim,
            dim_head=attention_head_dim,
            heads=num_attention_heads,
            out_dim=dim,
            bias=bias,
            out_bias=bias,
            eps=eps,
            mlp_ratio=mlp_ratio,
            mlp_mult_factor=2,
        )

    def forward(
        self,
        hidden_states: torch.Tensor,
        encoder_hidden_states: torch.Tensor | None,
        temb_mod_params: tuple[torch.Tensor, torch.Tensor, torch.Tensor],
        image_rotary_emb: tuple[torch.Tensor, torch.Tensor] | None = None,
        joint_attention_kwargs: dict[str, Any] | None = None,
        split_hidden_states: bool = False,
        text_seq_len: int | None = None,
    ) -> torch.Tensor | tuple[torch.Tensor, torch.Tensor]:
        if encoder_hidden_states is not None:
            text_seq_len = encoder_hidden_states.shape[1]
            hidden_states = torch.cat([encoder_hidden_states, hidden_states], dim=1)

        mod_shift, mod_scale, mod_gate = temb_mod_params

        norm_hidden_states = self.norm(hidden_states)
        norm_hidden_states = (1 + mod_scale) * norm_hidden_states + mod_shift

        joint_attention_kwargs = joint_attention_kwargs or {}
        attn_output = self.attn(
            hidden_states=norm_hidden_states,
            image_rotary_emb=image_rotary_emb,
            **joint_attention_kwargs,
        )

        hidden_states = hidden_states + mod_gate * attn_output
        if hidden_states.dtype == torch.float16:
            hidden_states = hidden_states.clip(-65504, 65504)

        if split_hidden_states:
            encoder_hidden_states, hidden_states = hidden_states[:, :text_seq_len], hidden_states[:, text_seq_len:]
            return encoder_hidden_states, hidden_states
        return hidden_states


class Flux2TransformerBlock(nn.Module):
    def __init__(
        self,
        dim: int,
        num_attention_heads: int,
        attention_head_dim: int,
        mlp_ratio: float = 3.0,
        eps: float = 1e-6,
        bias: bool = False,
    ):
        super().__init__()
        self.mlp_hidden_dim = int(dim * mlp_ratio)

        self.norm1 = nn.LayerNorm(dim, elementwise_affine=False, eps=eps)
        self.norm1_context = nn.LayerNorm(dim, elementwise_affine=False, eps=eps)

        self.attn = Flux2Attention(
            query_dim=dim,
            added_kv_proj_dim=dim,
            dim_head=attention_head_dim,
            heads=num_attention_heads,
            out_dim=dim,
            bias=bias,
            added_proj_bias=bias,
            out_bias=bias,
            eps=eps,
        )

        self.norm2 = nn.LayerNorm(dim, elementwise_affine=False, eps=eps)
        self.ff = Flux2FeedForward(dim=dim, dim_out=dim, mult=mlp_ratio, bias=bias)

        self.norm2_context = nn.LayerNorm(dim, elementwise_affine=False, eps=eps)
        self.ff_context = Flux2FeedForward(dim=dim, dim_out=dim, mult=mlp_ratio, bias=bias)

    def forward(
        self,
        hidden_states: torch.Tensor,
        encoder_hidden_states: torch.Tensor,
        temb_mod_params_img: tuple[tuple[torch.Tensor, torch.Tensor, torch.Tensor], ...],
        temb_mod_params_txt: tuple[tuple[torch.Tensor, torch.Tensor, torch.Tensor], ...],
        image_rotary_emb: tuple[torch.Tensor, torch.Tensor] | None = None,
        joint_attention_kwargs: dict[str, Any] | None = None,
    ) -> tuple[torch.Tensor, torch.Tensor]:
        joint_attention_kwargs = joint_attention_kwargs or {}

        (shift_msa, scale_msa, gate_msa), (shift_mlp, scale_mlp, gate_mlp) = temb_mod_params_img
        (c_shift_msa, c_scale_msa, c_gate_msa), (c_shift_mlp, c_scale_mlp, c_gate_mlp) = temb_mod_params_txt

        norm_hidden_states = self.norm1(hidden_states)
        norm_hidden_states = (1 + scale_msa) * norm_hidden_states + shift_msa

        norm_encoder_hidden_states = self.norm1_context(encoder_hidden_states)
        norm_encoder_hidden_states = (1 + c_scale_msa) * norm_encoder_hidden_states + c_shift_msa

        attn_output, context_attn_output = self.attn(
            hidden_states=norm_hidden_states,
            encoder_hidden_states=norm_encoder_hidden_states,
            image_rotary_emb=image_rotary_emb,
            **joint_attention_kwargs,
        )

        attn_output = gate_msa * attn_output
        hidden_states = hidden_states + attn_output

        norm_hidden_states = self.norm2(hidden_states)
        norm_hidden_states = norm_hidden_states * (1 + scale_mlp) + shift_mlp
        ff_output = self.ff(norm_hidden_states)
        hidden_states = hidden_states + gate_mlp * ff_output

        context_attn_output = c_gate_msa * context_attn_output
        encoder_hidden_states = encoder_hidden_states + context_attn_output

        norm_encoder_hidden_states = self.norm2_context(encoder_hidden_states)
        norm_encoder_hidden_states = norm_encoder_hidden_states * (1 + c_scale_mlp) + c_shift_mlp
        context_ff_output = self.ff_context(norm_encoder_hidden_states)
        encoder_hidden_states = encoder_hidden_states + c_gate_mlp * context_ff_output
        if encoder_hidden_states.dtype == torch.float16:
            encoder_hidden_states = encoder_hidden_states.clip(-65504, 65504)

        return encoder_hidden_states, hidden_states


class Flux2PosEmbed(nn.Module):
    def __init__(self, theta: int, axes_dim: list[int]):
        super().__init__()
        self.theta = theta
        self.axes_dim = axes_dim

    def forward(self, ids: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]:
        # Expected ids shape: [S, len(self.axes_dim)]
        cos_out = []
        sin_out = []
        pos = ids.float()
        is_mps = ids.device.type == "mps"
        is_npu = ids.device.type == "npu"
        freqs_dtype = torch.float32 if (is_mps or is_npu) else torch.float64
        # Unlike Flux 1, loop over len(self.axes_dim) rather than ids.shape[-1]
        for i in range(len(self.axes_dim)):
            freqs_cis = get_1d_rotary_pos_embed(
                self.axes_dim[i],
                pos[..., i],
                theta=self.theta,
                use_real=False,
                freqs_dtype=freqs_dtype,
            )
            cos_out.append(freqs_cis.real)
            sin_out.append(freqs_cis.imag)
        freqs_cos = torch.cat(cos_out, dim=-1).to(ids.device)
        freqs_sin = torch.cat(sin_out, dim=-1).to(ids.device)
        return freqs_cos, freqs_sin


class Flux2TimestepGuidanceEmbeddings(nn.Module):
    def __init__(
        self,
        in_channels: int = 256,
        embedding_dim: int = 6144,
        bias: bool = False,
        guidance_embeds: bool = True,
    ):
        super().__init__()
        self.time_proj = Timesteps(num_channels=in_channels, flip_sin_to_cos=True, downscale_freq_shift=0)
        self.timestep_embedder = TimestepEmbedding(
            in_channels=in_channels,
            time_embed_dim=embedding_dim,
            sample_proj_bias=bias,
        )

        if guidance_embeds:
            self.guidance_embedder = TimestepEmbedding(
                in_channels=in_channels,
                time_embed_dim=embedding_dim,
                sample_proj_bias=bias,
            )
        else:
            self.guidance_embedder = None

    def forward(self, timestep: torch.Tensor, guidance: torch.Tensor | None) -> torch.Tensor:
        timesteps_proj = self.time_proj(timestep)
        timesteps_emb = self.timestep_embedder(timesteps_proj.to(timestep.dtype))

        if guidance is not None and self.guidance_embedder is not None:
            guidance_proj = self.time_proj(guidance)
            guidance_emb = self.guidance_embedder(guidance_proj.to(guidance.dtype))
            return timesteps_emb + guidance_emb
        return timesteps_emb


class Flux2Modulation(nn.Module):
    def __init__(self, dim: int, mod_param_sets: int = 2, bias: bool = False):
        super().__init__()
        self.mod_param_sets = mod_param_sets

        self.linear = nn.Linear(dim, dim * 3 * self.mod_param_sets, bias=bias)
        self.act_fn = nn.SiLU()

    def forward(self, temb: torch.Tensor) -> tuple[tuple[torch.Tensor, torch.Tensor, torch.Tensor], ...]:
        mod = self.act_fn(temb)
        mod = self.linear(mod)

        if mod.ndim == 2:
            mod = mod.unsqueeze(1)
        mod_params = torch.chunk(mod, 3 * self.mod_param_sets, dim=-1)
        # Return tuple of 3-tuples of modulation params shift/scale/gate
        return tuple(mod_params[3 * i : 3 * (i + 1)] for i in range(self.mod_param_sets))


class Flux2Transformer2DModel(nn.Module):
    """
    The Transformer model introduced in Flux 2.
    """

    _repeated_blocks = ["Flux2TransformerBlock", "Flux2SingleTransformerBlock"]

    @staticmethod
    def _is_transformer_block(name: str, module) -> bool:
        return ("transformer_blocks" in name or "single_transformer_blocks" in name) and name.split(".")[-1].isdigit()

    _hsdp_shard_conditions = [_is_transformer_block]

    def __init__(
        self,
        patch_size: int = 1,
        in_channels: int = 128,
        out_channels: int | None = None,
        num_layers: int = 8,
        num_single_layers: int = 48,
        attention_head_dim: int = 128,
        num_attention_heads: int = 48,
        joint_attention_dim: int = 15360,
        timestep_guidance_channels: int = 256,
        mlp_ratio: float = 3.0,
        axes_dims_rope: tuple[int, ...] = (32, 32, 32, 32),
        rope_theta: int = 2000,
        eps: float = 1e-6,
        guidance_embeds: bool = True,
    ):
        super().__init__()
        self.guidance_embeds = guidance_embeds
        self.stacked_params_mapping = None
        self.out_channels = out_channels or in_channels
        self.inner_dim = num_attention_heads * attention_head_dim

        self.config = SimpleNamespace(
            patch_size=patch_size,
            in_channels=in_channels,
            out_channels=self.out_channels,
            num_layers=num_layers,
            num_single_layers=num_single_layers,
            attention_head_dim=attention_head_dim,
            num_attention_heads=num_attention_heads,
            joint_attention_dim=joint_attention_dim,
            timestep_guidance_channels=timestep_guidance_channels,
            mlp_ratio=mlp_ratio,
            axes_dims_rope=axes_dims_rope,
            rope_theta=rope_theta,
            eps=eps,
            guidance_embeds=guidance_embeds,
        )

        self.pos_embed = Flux2PosEmbed(theta=rope_theta, axes_dim=axes_dims_rope)
        self.time_guidance_embed = Flux2TimestepGuidanceEmbeddings(
            in_channels=timestep_guidance_channels,
            embedding_dim=self.inner_dim,
            bias=False,
            guidance_embeds=guidance_embeds,
        )

        self.double_stream_modulation_img = Flux2Modulation(self.inner_dim, mod_param_sets=2, bias=False)
        self.double_stream_modulation_txt = Flux2Modulation(self.inner_dim, mod_param_sets=2, bias=False)
        self.single_stream_modulation = Flux2Modulation(self.inner_dim, mod_param_sets=1, bias=False)

        self.x_embedder = nn.Linear(in_channels, self.inner_dim, bias=False)
        self.context_embedder = nn.Linear(joint_attention_dim, self.inner_dim, bias=False)

        self.transformer_blocks = nn.ModuleList(
            [
                Flux2TransformerBlock(
                    dim=self.inner_dim,
                    num_attention_heads=num_attention_heads,
                    attention_head_dim=attention_head_dim,
                    mlp_ratio=mlp_ratio,
                    eps=eps,
                    bias=False,
                )
                for _ in range(num_layers)
            ]
        )

        self.single_transformer_blocks = nn.ModuleList(
            [
                Flux2SingleTransformerBlock(
                    dim=self.inner_dim,
                    num_attention_heads=num_attention_heads,
                    attention_head_dim=attention_head_dim,
                    mlp_ratio=mlp_ratio,
                    eps=eps,
                    bias=False,
                )
                for _ in range(num_single_layers)
            ]
        )

        self.norm_out = AdaLayerNormContinuous(
            self.inner_dim, self.inner_dim, elementwise_affine=False, eps=eps, bias=False
        )
        self.proj_out = nn.Linear(self.inner_dim, patch_size * patch_size * self.out_channels, bias=False)

    @property
    def dtype(self) -> torch.dtype:
        return next(self.parameters()).dtype

    def forward(
        self,
        hidden_states: torch.Tensor,
        encoder_hidden_states: torch.Tensor = None,
        timestep: torch.LongTensor = None,
        img_ids: torch.Tensor = None,
        txt_ids: torch.Tensor = None,
        guidance: torch.Tensor | None = None,
        joint_attention_kwargs: dict[str, Any] | None = None,
        return_dict: bool = True,
    ) -> torch.Tensor | Transformer2DModelOutput:
        joint_attention_kwargs = joint_attention_kwargs or {}

        num_txt_tokens = encoder_hidden_states.shape[1]

        timestep = timestep.to(hidden_states.dtype) * 1000
        if guidance is not None:
            guidance = guidance.to(hidden_states.dtype) * 1000

        temb = self.time_guidance_embed(timestep, guidance)

        double_stream_mod_img = self.double_stream_modulation_img(temb)
        double_stream_mod_txt = self.double_stream_modulation_txt(temb)
        single_stream_mod = self.single_stream_modulation(temb)[0]

        hidden_states = self.x_embedder(hidden_states)
        encoder_hidden_states = self.context_embedder(encoder_hidden_states)

        if img_ids.ndim == 3:
            img_ids = img_ids[0]
        if txt_ids.ndim == 3:
            txt_ids = txt_ids[0]

        if is_torch_npu_available():
            freqs_cos_image, freqs_sin_image = self.pos_embed(img_ids.cpu())
            image_rotary_emb = (freqs_cos_image.npu(), freqs_sin_image.npu())
            freqs_cos_text, freqs_sin_text = self.pos_embed(txt_ids.cpu())
            text_rotary_emb = (freqs_cos_text.npu(), freqs_sin_text.npu())
        else:
            image_rotary_emb = self.pos_embed(img_ids)
            text_rotary_emb = self.pos_embed(txt_ids)
        concat_rotary_emb = (
            torch.cat([text_rotary_emb[0], image_rotary_emb[0]], dim=0),
            torch.cat([text_rotary_emb[1], image_rotary_emb[1]], dim=0),
        )

        for index_block, block in enumerate(self.transformer_blocks):
            encoder_hidden_states, hidden_states = block(
                hidden_states=hidden_states,
                encoder_hidden_states=encoder_hidden_states,
                temb_mod_params_img=double_stream_mod_img,
                temb_mod_params_txt=double_stream_mod_txt,
                image_rotary_emb=concat_rotary_emb,
                joint_attention_kwargs=joint_attention_kwargs,
            )

        hidden_states = torch.cat([encoder_hidden_states, hidden_states], dim=1)

        for index_block, block in enumerate(self.single_transformer_blocks):
            hidden_states = block(
                hidden_states=hidden_states,
                encoder_hidden_states=None,
                temb_mod_params=single_stream_mod,
                image_rotary_emb=concat_rotary_emb,
                joint_attention_kwargs=joint_attention_kwargs,
            )

        hidden_states = hidden_states[:, num_txt_tokens:, ...]
        hidden_states = self.norm_out(hidden_states, temb)
        output = self.proj_out(hidden_states)

        if not return_dict:
            return (output,)

        return Transformer2DModelOutput(sample=output)

    def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]) -> set[str]:
        stacked_params_mapping = [
            (".to_qkv.", ".to_q.", "q"),
            (".to_qkv.", ".to_k.", "k"),
            (".to_qkv.", ".to_v.", "v"),
            (".add_kv_proj", ".add_q_proj", "q"),
            (".add_kv_proj", ".add_k_proj", "k"),
            (".add_kv_proj", ".add_v_proj", "v"),
        ]
        # Expose packed shard mappings for LoRA handling of fused projections.
        self.stacked_params_mapping = stacked_params_mapping

        params_dict = dict(self.named_parameters())

        for name, buffer in self.named_buffers():
            if name.endswith(".beta") or name.endswith(".eps"):
                params_dict[name] = buffer

        loaded_params: set[str] = set()
        for name, loaded_weight in weights:
            original_name = name
            mapped = False
            for param_name, weight_name, shard_id in stacked_params_mapping:
                if weight_name not in original_name:
                    continue
                name = original_name.replace(weight_name, param_name)
                param = params_dict.get(name)
                if param is None:
                    break
                weight_loader = param.weight_loader
                weight_loader(param, loaded_weight, shard_id)
                loaded_params.add(name)
                mapped = True
                break
            if mapped:
                continue

            name = original_name
            if name not in params_dict and ".to_out.0." in name:
                name = name.replace(".to_out.0.", ".to_out.")
            # Some GGUF checkpoints include quantized tensors for modules that
            # are intentionally left unquantized in this model.
            param = params_dict.get(name)
            if param is None:
                continue
            weight_loader = getattr(param, "weight_loader", default_weight_loader)
            weight_loader(param, loaded_weight)
            loaded_params.add(name)
        return loaded_params