TrailBlazer/Pipeline/UNet3DConditionModelCall.py

# Copyright 2023 Alibaba DAMO-VILAB and The HuggingFace Team. All rights reserved.
# Copyright 2023 The ModelScope Team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from dataclasses import dataclass
from typing import Any, Dict, List, Optional, Tuple, Union

import torch
import torch.nn as nn
import torch.utils.checkpoint

from diffusers.configuration_utils import ConfigMixin, register_to_config
from diffusers.loaders import UNet2DConditionLoadersMixin
from diffusers.utils import BaseOutput, logging
from diffusers.models.attention_processor import (
    ADDED_KV_ATTENTION_PROCESSORS,
    CROSS_ATTENTION_PROCESSORS,
    AttentionProcessor,
    AttnAddedKVProcessor,
    AttnProcessor,
)
from diffusers.models.embeddings import TimestepEmbedding, Timesteps
from diffusers.models.modeling_utils import ModelMixin
from diffusers.models.transformer_temporal import TransformerTemporalModel
from diffusers.models.unet_3d_blocks import (
    CrossAttnDownBlock3D,
    CrossAttnUpBlock3D,
    DownBlock3D,
    UNetMidBlock3DCrossAttn,
    UpBlock3D,
    get_down_block,
    get_up_block,
)
from diffusers.models.unet_3d_condition import UNet3DConditionOutput



def unet3d_condition_model_forward(
        self,
        sample: torch.FloatTensor,
        timestep: Union[torch.Tensor, float, int],
        encoder_hidden_states: torch.Tensor,
        class_labels: Optional[torch.Tensor] = None,
        timestep_cond: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
        down_block_additional_residuals: Optional[Tuple[torch.Tensor]] = None,
        mid_block_additional_residual: Optional[torch.Tensor] = None,
        return_dict: bool = True,
    ) -> Union[UNet3DConditionOutput, Tuple]:
        r"""
        The [`UNet3DConditionModel`] forward method.

        Args:
            sample (`torch.FloatTensor`):
                The noisy input tensor with the following shape `(batch, num_frames, channel, height, width`.
            timestep (`torch.FloatTensor` or `float` or `int`): The number of timesteps to denoise an input.
            encoder_hidden_states (`torch.FloatTensor`):
                The encoder hidden states with shape `(batch, sequence_length, feature_dim)`.
            return_dict (`bool`, *optional*, defaults to `True`):
                Whether or not to return a [`~models.unet_3d_condition.UNet3DConditionOutput`] instead of a plain
                tuple.
            cross_attention_kwargs (`dict`, *optional*):
                A kwargs dictionary that if specified is passed along to the [`AttnProcessor`].

        Returns:
            [`~models.unet_3d_condition.UNet3DConditionOutput`] or `tuple`:
                If `return_dict` is True, an [`~models.unet_3d_condition.UNet3DConditionOutput`] is returned, otherwise
                a `tuple` is returned where the first element is the sample tensor.
        """
        # By default samples have to be AT least a multiple of the overall upsampling factor.
        # The overall upsampling factor is equal to 2 ** (# num of upsampling layears).
        # However, the upsampling interpolation output size can be forced to fit any upsampling size
        # on the fly if necessary.
        default_overall_up_factor = 2**self.num_upsamplers

        # upsample size should be forwarded when sample is not a multiple of `default_overall_up_factor`
        forward_upsample_size = False
        upsample_size = None

        if any(s % default_overall_up_factor != 0 for s in sample.shape[-2:]):
            logger.info("Forward upsample size to force interpolation output size.")
            forward_upsample_size = True

        # prepare attention_mask
        if attention_mask is not None:
            attention_mask = (1 - attention_mask.to(sample.dtype)) * -10000.0
            attention_mask = attention_mask.unsqueeze(1)

        # 1. time
        timesteps = timestep
        if not torch.is_tensor(timesteps):
            # TODO: this requires sync between CPU and GPU. So try to pass timesteps as tensors if you can
            # This would be a good case for the `match` statement (Python 3.10+)
            is_mps = sample.device.type == "mps"
            if isinstance(timestep, float):
                dtype = torch.float32 if is_mps else torch.float64
            else:
                dtype = torch.int32 if is_mps else torch.int64
            timesteps = torch.tensor([timesteps], dtype=dtype, device=sample.device)
        elif len(timesteps.shape) == 0:
            timesteps = timesteps[None].to(sample.device)

        # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
        num_frames = sample.shape[2]
        timesteps = timesteps.expand(sample.shape[0])

        t_emb = self.time_proj(timesteps)

        # timesteps does not contain any weights and will always return f32 tensors
        # but time_embedding might actually be running in fp16. so we need to cast here.
        # there might be better ways to encapsulate this.
        t_emb = t_emb.to(dtype=self.dtype)

        emb = self.time_embedding(t_emb, timestep_cond)
        emb = emb.repeat_interleave(repeats=num_frames, dim=0)
        # encoder_hidden_states = encoder_hidden_states.repeat_interleave(repeats=num_frames, dim=0)
        # print(encoder_hidden_states.shape)
        # quit()

        # 2. pre-process
        sample = sample.permute(0, 2, 1, 3, 4).reshape((sample.shape[0] * num_frames, -1) + sample.shape[3:])
        sample = self.conv_in(sample)

        sample = self.transformer_in(
            sample,
            num_frames=num_frames,
            cross_attention_kwargs=cross_attention_kwargs,
            return_dict=False,
        )[0]

        # 3. down
        down_block_res_samples = (sample,)
        for downsample_block in self.down_blocks:
            if hasattr(downsample_block, "has_cross_attention") and downsample_block.has_cross_attention:
                sample, res_samples = downsample_block(
                    hidden_states=sample,
                    temb=emb,
                    encoder_hidden_states=encoder_hidden_states,
                    attention_mask=attention_mask,
                    num_frames=num_frames,
                    cross_attention_kwargs=cross_attention_kwargs,
                )
            else:
                sample, res_samples = downsample_block(hidden_states=sample, temb=emb, num_frames=num_frames)

            down_block_res_samples += res_samples

        if down_block_additional_residuals is not None:
            new_down_block_res_samples = ()

            for down_block_res_sample, down_block_additional_residual in zip(
                down_block_res_samples, down_block_additional_residuals
            ):
                down_block_res_sample = down_block_res_sample + down_block_additional_residual
                new_down_block_res_samples += (down_block_res_sample,)

            down_block_res_samples = new_down_block_res_samples

        # 4. mid
        if self.mid_block is not None:
            sample = self.mid_block(
                sample,
                emb,
                encoder_hidden_states=encoder_hidden_states,
                attention_mask=attention_mask,
                num_frames=num_frames,
                cross_attention_kwargs=cross_attention_kwargs,
            )

        if mid_block_additional_residual is not None:
            sample = sample + mid_block_additional_residual

        # 5. up
        for i, upsample_block in enumerate(self.up_blocks):
            is_final_block = i == len(self.up_blocks) - 1

            res_samples = down_block_res_samples[-len(upsample_block.resnets) :]
            down_block_res_samples = down_block_res_samples[: -len(upsample_block.resnets)]

            # if we have not reached the final block and need to forward the
            # upsample size, we do it here
            if not is_final_block and forward_upsample_size:
                upsample_size = down_block_res_samples[-1].shape[2:]

            if hasattr(upsample_block, "has_cross_attention") and upsample_block.has_cross_attention:
                sample = upsample_block(
                    hidden_states=sample,
                    temb=emb,
                    res_hidden_states_tuple=res_samples,
                    encoder_hidden_states=encoder_hidden_states,
                    upsample_size=upsample_size,
                    attention_mask=attention_mask,
                    num_frames=num_frames,
                    cross_attention_kwargs=cross_attention_kwargs,
                )
            else:
                sample = upsample_block(
                    hidden_states=sample,
                    temb=emb,
                    res_hidden_states_tuple=res_samples,
                    upsample_size=upsample_size,
                    num_frames=num_frames,
                )

        # 6. post-process
        if self.conv_norm_out:
            sample = self.conv_norm_out(sample)
            sample = self.conv_act(sample)

        sample = self.conv_out(sample)

        # reshape to (batch, channel, framerate, width, height)
        sample = sample[None, :].reshape((-1, num_frames) + sample.shape[1:]).permute(0, 2, 1, 3, 4)

        if not return_dict:
            return (sample,)

        return UNet3DConditionOutput(sample=sample)