pipeline.py

# Copyright 2024 PixArt-Sigma Authors and The HuggingFace Team. All rights reserved.
#
# 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.

import html
import inspect
import re
import urllib.parse as ul
from typing import Callable, List, Optional, Tuple, Union

import torch
from transformers import T5EncoderModel, T5Tokenizer

from diffusers.image_processor import PixArtImageProcessor, PipelineImageInput
from diffusers.models import AutoencoderKL, PixArtTransformer2DModel
from diffusers.schedulers import KarrasDiffusionSchedulers
from diffusers.utils import (
    BACKENDS_MAPPING,
    deprecate,
    is_bs4_available,
    is_ftfy_available,
    logging,
    replace_example_docstring,
)
from diffusers.utils.torch_utils import randn_tensor
from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput
from diffusers.pipelines.pixart_alpha.pipeline_pixart_alpha import (
    ASPECT_RATIO_256_BIN,
    ASPECT_RATIO_512_BIN,
    ASPECT_RATIO_1024_BIN,
)


# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.retrieve_latents
def retrieve_latents(
    encoder_output: torch.Tensor,
    generator: Optional[torch.Generator] = None,
    sample_mode: str = "sample",
):
    if hasattr(encoder_output, "latent_dist") and sample_mode == "sample":
        return encoder_output.latent_dist.sample(generator)
    elif hasattr(encoder_output, "latent_dist") and sample_mode == "argmax":
        return encoder_output.latent_dist.mode()
    elif hasattr(encoder_output, "latents"):
        return encoder_output.latents
    else:
        raise AttributeError("Could not access latents of provided encoder_output")


logger = logging.get_logger(__name__)  # pylint: disable=invalid-name

if is_bs4_available():
    from bs4 import BeautifulSoup

if is_ftfy_available():
    import ftfy

def debug_print(message: str):
    #print(message)
    pass

ASPECT_RATIO_2048_BIN = {
    "0.25": [1024.0, 4096.0],
    "0.26": [1024.0, 3968.0],
    "0.27": [1024.0, 3840.0],
    "0.28": [1024.0, 3712.0],
    "0.32": [1152.0, 3584.0],
    "0.33": [1152.0, 3456.0],
    "0.35": [1152.0, 3328.0],
    "0.4": [1280.0, 3200.0],
    "0.42": [1280.0, 3072.0],
    "0.48": [1408.0, 2944.0],
    "0.5": [1408.0, 2816.0],
    "0.52": [1408.0, 2688.0],
    "0.57": [1536.0, 2688.0],
    "0.6": [1536.0, 2560.0],
    "0.68": [1664.0, 2432.0],
    "0.72": [1664.0, 2304.0],
    "0.78": [1792.0, 2304.0],
    "0.82": [1792.0, 2176.0],
    "0.88": [1920.0, 2176.0],
    "0.94": [1920.0, 2048.0],
    "1.0": [2048.0, 2048.0],
    "1.07": [2048.0, 1920.0],
    "1.13": [2176.0, 1920.0],
    "1.21": [2176.0, 1792.0],
    "1.29": [2304.0, 1792.0],
    "1.38": [2304.0, 1664.0],
    "1.46": [2432.0, 1664.0],
    "1.67": [2560.0, 1536.0],
    "1.75": [2688.0, 1536.0],
    "2.0": [2816.0, 1408.0],
    "2.09": [2944.0, 1408.0],
    "2.4": [3072.0, 1280.0],
    "2.5": [3200.0, 1280.0],
    "2.89": [3328.0, 1152.0],
    "3.0": [3456.0, 1152.0],
    "3.11": [3584.0, 1152.0],
    "3.62": [3712.0, 1024.0],
    "3.75": [3840.0, 1024.0],
    "3.88": [3968.0, 1024.0],
    "4.0": [4096.0, 1024.0],
}


EXAMPLE_DOC_STRING = """
    Examples:
        ```py
        >>> import torch
        >>> from diffusers import PixArtSigmaPipeline

        >>> # You can replace the checkpoint id with "PixArt-alpha/PixArt-Sigma-XL-2-512-MS" too.
        >>> pipe = PixArtSigmaPipeline.from_pretrained(
        ...     "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS", torch_dtype=torch.float16
        ... )
        >>> # Enable memory optimizations.
        >>> # pipe.enable_model_cpu_offload()

        >>> prompt = "A small cactus with a happy face in the Sahara desert."
        >>> image = pipe(prompt).images[0]
        ```
"""


# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.retrieve_timesteps
def retrieve_timesteps(
    scheduler,
    num_inference_steps: Optional[int] = None,
    device: Optional[Union[str, torch.device]] = None,
    timesteps: Optional[List[int]] = None,
    sigmas: Optional[List[float]] = None,
    **kwargs,
):
    """
    Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles
    custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`.

    Args:
        scheduler (`SchedulerMixin`):
            The scheduler to get timesteps from.
        num_inference_steps (`int`):
            The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps`
            must be `None`.
        device (`str` or `torch.device`, *optional*):
            The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
        timesteps (`List[int]`, *optional*):
            Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed,
            `num_inference_steps` and `sigmas` must be `None`.
        sigmas (`List[float]`, *optional*):
            Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed,
            `num_inference_steps` and `timesteps` must be `None`.

    Returns:
        `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
        second element is the number of inference steps.
    """
    if timesteps is not None and sigmas is not None:
        raise ValueError(
            "Only one of `timesteps` or `sigmas` can be passed. Please choose one to set custom values"
        )
    if timesteps is not None:
        accepts_timesteps = "timesteps" in set(
            inspect.signature(scheduler.set_timesteps).parameters.keys()
        )
        if not accepts_timesteps:
            raise ValueError(
                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
                f" timestep schedules. Please check whether you are using the correct scheduler."
            )
        scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs)
        timesteps = scheduler.timesteps
        num_inference_steps = len(timesteps)
    elif sigmas is not None:
        accept_sigmas = "sigmas" in set(
            inspect.signature(scheduler.set_timesteps).parameters.keys()
        )
        if not accept_sigmas:
            raise ValueError(
                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
                f" sigmas schedules. Please check whether you are using the correct scheduler."
            )
        scheduler.set_timesteps(sigmas=sigmas, device=device, **kwargs)
        timesteps = scheduler.timesteps
        num_inference_steps = len(timesteps)
    else:
        scheduler.set_timesteps(num_inference_steps, device=device, **kwargs)
        timesteps = scheduler.timesteps
    return timesteps, num_inference_steps


class PixArtSigmaPipeline(DiffusionPipeline):
    r"""
    Pipeline for text-to-image generation using PixArt-Sigma.
    """

    bad_punct_regex = re.compile(
        r"["
        + "#®•©™&@·º½¾¿¡§~"
        + r"\)"
        + r"\("
        + r"\]"
        + r"\["
        + r"\}"
        + r"\{"
        + r"\|"
        + "\\"
        + r"\/"
        + r"\*"
        + r"]{1,}"
    )  # noqa

    _optional_components = ["tokenizer", "text_encoder"]
    model_cpu_offload_seq = "text_encoder->transformer->vae"

    def __init__(
        self,
        tokenizer: T5Tokenizer,
        text_encoder: T5EncoderModel,
        vae: AutoencoderKL,
        transformer: PixArtTransformer2DModel,
        scheduler: KarrasDiffusionSchedulers,
    ):
        super().__init__()

        self.register_modules(
            tokenizer=tokenizer,
            text_encoder=text_encoder,
            vae=vae,
            transformer=transformer,
            scheduler=scheduler,
        )

        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
        self.image_processor = PixArtImageProcessor(
            vae_scale_factor=self.vae_scale_factor
        )

    def get_timesteps(
        self, num_inference_steps, strength, device, denoising_start=None
    ):
        # get the original timestep using init_timestep
        if denoising_start is None and strength is not None:
            init_timestep = min(
                int(num_inference_steps * strength), num_inference_steps
            )
            debug_print(f"Init timestep: {init_timestep}")
            t_start = max(num_inference_steps - init_timestep, 0)
            debug_print(
                f"t_start = max({num_inference_steps} - {init_timestep}, 0) = {t_start}"
            )
        else:
            debug_print(f"denoising_start: {denoising_start}")
            t_start = 0

        timesteps = self.scheduler.timesteps[t_start * self.scheduler.order :]
        # Strength is irrelevant if we directly request a timestep to start at;
        # that is, strength is determined by the denoising_start instead.
        if denoising_start is not None:
            discrete_timestep_cutoff = int(
                round(
                    self.scheduler.config.num_train_timesteps
                    - (denoising_start * self.scheduler.config.num_train_timesteps)
                )
            )

            num_inference_steps = (timesteps < discrete_timestep_cutoff).sum().item()
            if self.scheduler.order == 2 and num_inference_steps % 2 == 0:
                # if the scheduler is a 2nd order scheduler we might have to do +1
                # because `num_inference_steps` might be even given that every timestep
                # (except the highest one) is duplicated. If `num_inference_steps` is even it would
                # mean that we cut the timesteps in the middle of the denoising step
                # (between 1st and 2nd derivative) which leads to incorrect results. By adding 1
                # we ensure that the denoising process always ends after the 2nd derivate step of the scheduler
                num_inference_steps = num_inference_steps + 1

            # because t_n+1 >= t_n, we slice the timesteps starting from the end
            timesteps = timesteps[-num_inference_steps:]
            return timesteps, num_inference_steps

        return timesteps, num_inference_steps - t_start

    # Copied from diffusers.pipelines.pixart_alpha.pipeline_pixart_alpha.PixArtAlphaPipeline.encode_prompt with 120->300
    def encode_prompt(
        self,
        prompt: Union[str, List[str]],
        do_classifier_free_guidance: bool = True,
        negative_prompt: str = "",
        num_images_per_prompt: int = 1,
        device: Optional[torch.device] = None,
        prompt_embeds: Optional[torch.Tensor] = None,
        negative_prompt_embeds: Optional[torch.Tensor] = None,
        prompt_attention_mask: Optional[torch.Tensor] = None,
        negative_prompt_attention_mask: Optional[torch.Tensor] = None,
        clean_caption: bool = False,
        max_sequence_length: int = 300,
        **kwargs,
    ):
        r"""
        Encodes the prompt into text encoder hidden states.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt not to guide the image generation. If not defined, one has to pass `negative_prompt_embeds`
                instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`). For
                PixArt-Alpha, this should be "".
            do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
                whether to use classifier free guidance or not
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                number of images that should be generated per prompt
            device: (`torch.device`, *optional*):
                torch device to place the resulting embeddings on
            prompt_embeds (`torch.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            negative_prompt_embeds (`torch.Tensor`, *optional*):
                Pre-generated negative text embeddings. For PixArt-Alpha, it's should be the embeddings of the ""
                string.
            clean_caption (`bool`, defaults to `False`):
                If `True`, the function will preprocess and clean the provided caption before encoding.
            max_sequence_length (`int`, defaults to 300): Maximum sequence length to use for the prompt.
        """

        if "mask_feature" in kwargs:
            deprecation_message = "The use of `mask_feature` is deprecated. It is no longer used in any computation and that doesn't affect the end results. It will be removed in a future version."
            deprecate("mask_feature", "1.0.0", deprecation_message, standard_warn=False)

        if device is None:
            device = self._execution_device

        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        # See Section 3.1. of the paper.
        max_length = max_sequence_length

        if prompt_embeds is None:
            prompt = self._text_preprocessing(prompt, clean_caption=clean_caption)
            text_inputs = self.tokenizer(
                prompt,
                padding="max_length",
                max_length=max_length,
                truncation=True,
                add_special_tokens=True,
                return_tensors="pt",
            )
            text_input_ids = text_inputs.input_ids
            untruncated_ids = self.tokenizer(
                prompt, padding="longest", return_tensors="pt"
            ).input_ids

            if untruncated_ids.shape[-1] >= text_input_ids.shape[
                -1
            ] and not torch.equal(text_input_ids, untruncated_ids):
                removed_text = self.tokenizer.batch_decode(
                    untruncated_ids[:, max_length - 1 : -1]
                )
                logger.warning(
                    "The following part of your input was truncated because T5 can only handle sequences up to"
                    f" {max_length} tokens: {removed_text}"
                )

            prompt_attention_mask = text_inputs.attention_mask
            prompt_attention_mask = prompt_attention_mask.to(device)

            prompt_embeds = self.text_encoder(
                text_input_ids.to(device), attention_mask=prompt_attention_mask
            )
            prompt_embeds = prompt_embeds[0]

        if self.text_encoder is not None:
            dtype = self.text_encoder.dtype
        elif self.transformer is not None:
            dtype = self.transformer.dtype
        else:
            dtype = None

        prompt_embeds = prompt_embeds.to(dtype=dtype, device=device)

        bs_embed, seq_len, _ = prompt_embeds.shape
        # duplicate text embeddings and attention mask for each generation per prompt, using mps friendly method
        prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
        prompt_embeds = prompt_embeds.view(
            bs_embed * num_images_per_prompt, seq_len, -1
        )
        prompt_attention_mask = prompt_attention_mask.view(bs_embed, -1)
        prompt_attention_mask = prompt_attention_mask.repeat(num_images_per_prompt, 1)

        # get unconditional embeddings for classifier free guidance
        if do_classifier_free_guidance and negative_prompt_embeds is None:
            uncond_tokens = (
                [negative_prompt] * batch_size
                if isinstance(negative_prompt, str)
                else negative_prompt
            )
            uncond_tokens = self._text_preprocessing(
                uncond_tokens, clean_caption=clean_caption
            )
            max_length = prompt_embeds.shape[1]
            uncond_input = self.tokenizer(
                uncond_tokens,
                padding="max_length",
                max_length=max_length,
                truncation=True,
                return_attention_mask=True,
                add_special_tokens=True,
                return_tensors="pt",
            )
            negative_prompt_attention_mask = uncond_input.attention_mask
            negative_prompt_attention_mask = negative_prompt_attention_mask.to(device)

            negative_prompt_embeds = self.text_encoder(
                uncond_input.input_ids.to(device),
                attention_mask=negative_prompt_attention_mask,
            )
            negative_prompt_embeds = negative_prompt_embeds[0]

        if do_classifier_free_guidance:
            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
            seq_len = negative_prompt_embeds.shape[1]

            negative_prompt_embeds = negative_prompt_embeds.to(
                dtype=dtype, device=device
            )

            negative_prompt_embeds = negative_prompt_embeds.repeat(
                1, num_images_per_prompt, 1
            )
            negative_prompt_embeds = negative_prompt_embeds.view(
                batch_size * num_images_per_prompt, seq_len, -1
            )

            negative_prompt_attention_mask = negative_prompt_attention_mask.view(
                bs_embed, -1
            )
            negative_prompt_attention_mask = negative_prompt_attention_mask.repeat(
                num_images_per_prompt, 1
            )
        else:
            negative_prompt_embeds = None
            negative_prompt_attention_mask = None

        return (
            prompt_embeds,
            prompt_attention_mask,
            negative_prompt_embeds,
            negative_prompt_attention_mask,
        )

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
    def prepare_extra_step_kwargs(self, generator, eta):
        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
        # and should be between [0, 1]

        accepts_eta = "eta" in set(
            inspect.signature(self.scheduler.step).parameters.keys()
        )
        extra_step_kwargs = {}
        if accepts_eta:
            extra_step_kwargs["eta"] = eta

        # check if the scheduler accepts generator
        accepts_generator = "generator" in set(
            inspect.signature(self.scheduler.step).parameters.keys()
        )
        if accepts_generator:
            extra_step_kwargs["generator"] = generator
        return extra_step_kwargs

    # Copied from diffusers.pipelines.pixart_alpha.pipeline_pixart_alpha.PixArtAlphaPipeline.check_inputs
    def check_inputs(
        self,
        prompt,
        height,
        width,
        strength,
        num_inference_steps,
        negative_prompt,
        callback_steps,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        prompt_attention_mask=None,
        negative_prompt_attention_mask=None,
    ):
        if strength is None:
            if height % 8 != 0 or width % 8 != 0:
                raise ValueError(
                    f"`height` and `width` have to be divisible by 8 but are {height} and {width}."
                )
        else:
            if strength < 0 or strength > 1:
                raise ValueError(
                    f"The value of strength should in [0.0, 1.0] but is {strength}"
                )
            if num_inference_steps is None:
                raise ValueError("`num_inference_steps` cannot be None.")
            elif not isinstance(num_inference_steps, int) or num_inference_steps <= 0:
                raise ValueError(
                    f"`num_inference_steps` has to be a positive integer but is {num_inference_steps} of type"
                    f" {type(num_inference_steps)}."
                )
        if (callback_steps is None) or (
            callback_steps is not None
            and (not isinstance(callback_steps, int) or callback_steps <= 0)
        ):
            raise ValueError(
                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
                f" {type(callback_steps)}."
            )

        if prompt is not None and prompt_embeds is not None:
            prompt = None

        if prompt is None and prompt_embeds is None:
            raise ValueError(
                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
            )
        elif prompt is not None and (
            not isinstance(prompt, str) and not isinstance(prompt, list)
        ):
            raise ValueError(
                f"`prompt` has to be of type `str` or `list` but is {type(prompt)}"
            )

        if prompt is not None and negative_prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt`: {prompt} and `negative_prompt_embeds`:"
                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
            )

        if negative_prompt is not None and negative_prompt_embeds is not None:
            negative_prompt = None

        if prompt_embeds is not None and prompt_attention_mask is None:
            raise ValueError(
                "Must provide `prompt_attention_mask` when specifying `prompt_embeds`."
            )

        if (
            negative_prompt_embeds is not None
            and negative_prompt_attention_mask is None
        ):
            raise ValueError(
                "Must provide `negative_prompt_attention_mask` when specifying `negative_prompt_embeds`."
            )

        if prompt_embeds is not None and negative_prompt_embeds is not None:
            if prompt_embeds.shape != negative_prompt_embeds.shape:
                raise ValueError(
                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
                    f" {negative_prompt_embeds.shape}."
                )
            if prompt_attention_mask.shape != negative_prompt_attention_mask.shape:
                raise ValueError(
                    "`prompt_attention_mask` and `negative_prompt_attention_mask` must have the same shape when passed directly, but"
                    f" got: `prompt_attention_mask` {prompt_attention_mask.shape} != `negative_prompt_attention_mask`"
                    f" {negative_prompt_attention_mask.shape}."
                )

    # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline._text_preprocessing
    def _text_preprocessing(self, text, clean_caption=False):
        if clean_caption and not is_bs4_available():
            logger.warning(
                BACKENDS_MAPPING["bs4"][-1].format("Setting `clean_caption=True`")
            )
            logger.warning("Setting `clean_caption` to False...")
            clean_caption = False

        if clean_caption and not is_ftfy_available():
            logger.warning(
                BACKENDS_MAPPING["ftfy"][-1].format("Setting `clean_caption=True`")
            )
            logger.warning("Setting `clean_caption` to False...")
            clean_caption = False

        if not isinstance(text, (tuple, list)):
            text = [text]

        def process(text: str):
            if clean_caption:
                text = self._clean_caption(text)
                text = self._clean_caption(text)
            else:
                text = text.lower().strip()
            return text

        return [process(t) for t in text]

    # Copied from diffusers.pipelines.deepfloyd_if.pipeline_if.IFPipeline._clean_caption
    def _clean_caption(self, caption):
        caption = str(caption)
        caption = ul.unquote_plus(caption)
        caption = caption.strip().lower()
        caption = re.sub("<person>", "person", caption)
        # urls:
        caption = re.sub(
            r"\b((?:https?:(?:\/{1,3}|[a-zA-Z0-9%])|[a-zA-Z0-9.\-]+[.](?:com|co|ru|net|org|edu|gov|it)[\w/-]*\b\/?(?!@)))",  # noqa
            "",
            caption,
        )  # regex for urls
        caption = re.sub(
            r"\b((?:www:(?:\/{1,3}|[a-zA-Z0-9%])|[a-zA-Z0-9.\-]+[.](?:com|co|ru|net|org|edu|gov|it)[\w/-]*\b\/?(?!@)))",  # noqa
            "",
            caption,
        )  # regex for urls
        # html:
        caption = BeautifulSoup(caption, features="html.parser").text

        # @<nickname>
        caption = re.sub(r"@[\w\d]+\b", "", caption)

        # 31C0—31EF CJK Strokes
        # 31F0—31FF Katakana Phonetic Extensions
        # 3200—32FF Enclosed CJK Letters and Months
        # 3300—33FF CJK Compatibility
        # 3400—4DBF CJK Unified Ideographs Extension A
        # 4DC0—4DFF Yijing Hexagram Symbols
        # 4E00—9FFF CJK Unified Ideographs
        caption = re.sub(r"[\u31c0-\u31ef]+", "", caption)
        caption = re.sub(r"[\u31f0-\u31ff]+", "", caption)
        caption = re.sub(r"[\u3200-\u32ff]+", "", caption)
        caption = re.sub(r"[\u3300-\u33ff]+", "", caption)
        caption = re.sub(r"[\u3400-\u4dbf]+", "", caption)
        caption = re.sub(r"[\u4dc0-\u4dff]+", "", caption)
        caption = re.sub(r"[\u4e00-\u9fff]+", "", caption)
        #######################################################

        # все виды тире / all types of dash --> "-"
        caption = re.sub(
            r"[\u002D\u058A\u05BE\u1400\u1806\u2010-\u2015\u2E17\u2E1A\u2E3A\u2E3B\u2E40\u301C\u3030\u30A0\uFE31\uFE32\uFE58\uFE63\uFF0D]+",  # noqa
            "-",
            caption,
        )

        # кавычки к одному стандарту
        caption = re.sub(r"[`´«»“”¨]", '"', caption)
        caption = re.sub(r"[‘’]", "'", caption)

        # &quot;
        caption = re.sub(r"&quot;?", "", caption)
        # &amp
        caption = re.sub(r"&amp", "", caption)

        # ip adresses:
        caption = re.sub(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}", " ", caption)

        # article ids:
        caption = re.sub(r"\d:\d\d\s+$", "", caption)

        # \n
        caption = re.sub(r"\\n", " ", caption)

        # "#123"
        caption = re.sub(r"#\d{1,3}\b", "", caption)
        # "#12345.."
        caption = re.sub(r"#\d{5,}\b", "", caption)
        # "123456.."
        caption = re.sub(r"\b\d{6,}\b", "", caption)
        # filenames:
        caption = re.sub(
            r"[\S]+\.(?:png|jpg|jpeg|bmp|webp|eps|pdf|apk|mp4)", "", caption
        )

        #
        caption = re.sub(r"[\"\']{2,}", r'"', caption)  # """AUSVERKAUFT"""
        caption = re.sub(r"[\.]{2,}", r" ", caption)  # """AUSVERKAUFT"""

        caption = re.sub(
            self.bad_punct_regex, r" ", caption
        )  # ***AUSVERKAUFT***, #AUSVERKAUFT
        caption = re.sub(r"\s+\.\s+", r" ", caption)  # " . "

        # this-is-my-cute-cat / this_is_my_cute_cat
        regex2 = re.compile(r"(?:\-|\_)")
        if len(re.findall(regex2, caption)) > 3:
            caption = re.sub(regex2, " ", caption)

        caption = ftfy.fix_text(caption)
        caption = html.unescape(html.unescape(caption))

        caption = re.sub(r"\b[a-zA-Z]{1,3}\d{3,15}\b", "", caption)  # jc6640
        caption = re.sub(r"\b[a-zA-Z]+\d+[a-zA-Z]+\b", "", caption)  # jc6640vc
        caption = re.sub(r"\b\d+[a-zA-Z]+\d+\b", "", caption)  # 6640vc231

        caption = re.sub(r"(worldwide\s+)?(free\s+)?shipping", "", caption)
        caption = re.sub(r"(free\s)?download(\sfree)?", "", caption)
        caption = re.sub(r"\bclick\b\s(?:for|on)\s\w+", "", caption)
        caption = re.sub(
            r"\b(?:png|jpg|jpeg|bmp|webp|eps|pdf|apk|mp4)(\simage[s]?)?", "", caption
        )
        caption = re.sub(r"\bpage\s+\d+\b", "", caption)

        caption = re.sub(
            r"\b\d*[a-zA-Z]+\d+[a-zA-Z]+\d+[a-zA-Z\d]*\b", r" ", caption
        )  # j2d1a2a...

        caption = re.sub(r"\b\d+\.?\d*[xх×]\d+\.?\d*\b", "", caption)

        caption = re.sub(r"\b\s+\:\s+", r": ", caption)
        caption = re.sub(r"(\D[,\./])\b", r"\1 ", caption)
        caption = re.sub(r"\s+", " ", caption)

        caption.strip()

        caption = re.sub(r"^[\"\']([\w\W]+)[\"\']$", r"\1", caption)
        caption = re.sub(r"^[\'\_,\-\:;]", r"", caption)
        caption = re.sub(r"[\'\_,\-\:\-\+]$", r"", caption)
        caption = re.sub(r"^\.\S+$", "", caption)

        return caption.strip()

    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
    def prepare_latents(
        self,
        batch_size,
        num_channels_latents,
        height,
        width,
        dtype,
        device,
        generator,
        _latents=None,
        timestep=None,
        add_noise=False,
        image=None,
    ):
        shape = (
            batch_size,
            num_channels_latents,
            int(height) // self.vae_scale_factor,
            int(width) // self.vae_scale_factor,
        )
        if isinstance(generator, list) and len(generator) != batch_size:
            raise ValueError(
                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
            )

        if _latents is not None:
            init_latents = _latents.to(device)
        elif image is None and _latents is None:
            debug_print("Make random latents tensor")
            init_latents = randn_tensor(
                shape, generator=generator, device=device, dtype=dtype
            )

        latents_mean = latents_std = None
        if (
            hasattr(self.vae.config, "latents_mean")
            and self.vae.config.latents_mean is not None
        ):
            latents_mean = torch.tensor(self.vae.config.latents_mean).view(1, 4, 1, 1)
        if (
            hasattr(self.vae.config, "latents_std")
            and self.vae.config.latents_std is not None
        ):
            latents_std = torch.tensor(self.vae.config.latents_std).view(1, 4, 1, 1)
        if image is not None and hasattr(image, "shape") and image.shape[1] == 4:
            debug_print("Received valid latent image input.")
            init_latents = image

        if init_latents is not None:
            # scale the initial noise by the standard deviation required by the scheduler
            debug_print(f"Scaling the initial noise by the std required by the scheduler.")
            init_latents = init_latents * self.scheduler.init_noise_sigma

        if image is not None and image.shape[1] < 4:
            debug_print("Received RGB or similar image. Processing..")
            # make sure the VAE is in float32 mode, as it overflows in float16
            if self.vae.config.force_upcast:
                image = image.float()
                self.vae.to(dtype=torch.float32)

            if isinstance(generator, list) and len(generator) != batch_size:
                raise ValueError(
                    f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                    f" size of {batch_size}. Make sure the batch size matches the length of the generators."
                )

            elif isinstance(generator, list):
                init_latents = [
                    retrieve_latents(
                        self.vae.encode(image[i : i + 1]), generator=generator[i]
                    )
                    for i in range(batch_size)
                ]
                init_latents = torch.cat(init_latents, dim=0)
            else:
                debug_print("Encode image to latents.")
                init_latents = retrieve_latents(
                    self.vae.encode(image), generator=generator
                )

            if self.vae.config.force_upcast:
                self.vae.to(dtype)

            debug_print("Set initial latents..")
            init_latents = init_latents.to(dtype)
            if latents_mean is not None and latents_std is not None:
                debug_print("Scaling latents by mean/std")
                latents_mean = latents_mean.to(device=device, dtype=dtype)
                latents_std = latents_std.to(device=device, dtype=dtype)
                init_latents = (
                    (init_latents - latents_mean)
                    * self.vae.config.scaling_factor
                    / latents_std
                )
            else:
                debug_print("Scaling latents only by scaling_factor")
                init_latents = self.vae.config.scaling_factor * init_latents

            if (
                batch_size > init_latents.shape[0]
                and batch_size % init_latents.shape[0] == 0
            ):
                # expand init_latents for batch_size
                additional_image_per_prompt = batch_size // init_latents.shape[0]
                init_latents = torch.cat(
                    [init_latents] * additional_image_per_prompt, dim=0
                )
            elif (
                batch_size > init_latents.shape[0]
                and batch_size % init_latents.shape[0] != 0
            ):
                raise ValueError(
                    f"Cannot duplicate `image` of batch size {init_latents.shape[0]} to {batch_size} text prompts."
                )
            else:
                init_latents = torch.cat([init_latents], dim=0)

        if (
            add_noise
            and timestep is not None
            and (_latents is not None or image is not None)
        ):
            shape = init_latents.shape
            noise = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
            # get latents
            debug_print(f"Adding noise to tensor for timestep: {timestep}")
            init_latents = self.scheduler.add_noise(init_latents, noise, timestep)

        return init_latents

    @property
    def denoising_start(self):
        return self._denoising_start

    @property
    def denoising_end(self):
        return self._denoising_end

    @property
    def num_timesteps(self):
        return self._num_timesteps

    @torch.no_grad()
    @replace_example_docstring(EXAMPLE_DOC_STRING)
    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        negative_prompt: str = "",
        strength: float = None,
        num_inference_steps: int = 20,
        timesteps: List[int] = None,
        sigmas: List[float] = None,
        denoising_start: Optional[float] = None,
        denoising_end: Optional[float] = None,
        guidance_scale: float = 4.5,
        num_images_per_prompt: Optional[int] = 1,
        height: Optional[int] = None,
        width: Optional[int] = None,
        eta: float = 0.0,
        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
        image: Optional[PipelineImageInput] = None,
        latents: Optional[torch.Tensor] = None,
        prompt_embeds: Optional[torch.Tensor] = None,
        prompt_attention_mask: Optional[torch.Tensor] = None,
        negative_prompt_embeds: Optional[torch.Tensor] = None,
        negative_prompt_attention_mask: Optional[torch.Tensor] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = True,
        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
        callback_steps: int = 1,
        clean_caption: bool = True,
        use_resolution_binning: bool = True,
        max_sequence_length: int = 300,
        **kwargs,
    ) -> Union[ImagePipelineOutput, Tuple]:
        """
        Function invoked when calling the pipeline for generation.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
                instead.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                less than `1`).
            strength (`float`, *optional*, defaults to 0.3):
                Conceptually, indicates how much to transform the reference `image`. Must be between 0 and 1. `image`
                will be used as a starting point, adding more noise to it the larger the `strength`. The number of
                denoising steps depends on the amount of noise initially added. When `strength` is 1, added noise will
                be maximum and the denoising process will run for the full number of iterations specified in
                `num_inference_steps`. A value of 1, therefore, essentially ignores `image`. Note that in the case of
                `denoising_start` being declared as an integer, the value of `strength` will be ignored.
            num_inference_steps (`int`, *optional*, defaults to 100):
                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                expense of slower inference.
            denoising_start (`float`, *optional*):
                When specified, indicates the fraction (between 0.0 and 1.0) of the total denoising process to be
                bypassed before it is initiated. Consequently, the initial part of the denoising process is skipped and
                it is assumed that the passed `image` is a partly denoised image. Note that when this is specified,
                strength will be ignored. The `denoising_start` parameter is particularly beneficial when this pipeline
                is integrated into a "Mixture of Denoisers" multi-pipeline setup, as detailed in [**Refine Image
                Quality**](https://huggingface.co/docs/diffusers/using-diffusers/sdxl#refine-image-quality).
            denoising_end (`float`, *optional*):
                When specified, determines the fraction (between 0.0 and 1.0) of the total denoising process to be
                completed before it is intentionally prematurely terminated. As a result, the returned sample will
                still retain a substantial amount of noise as determined by the discrete timesteps selected by the
                scheduler. The denoising_end parameter should ideally be utilized when this pipeline forms a part of a
                "Mixture of Denoisers" multi-pipeline setup, as elaborated in [**Refining the Image
                Output**](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl#refining-the-image-output)
            timesteps (`List[int]`, *optional*):
                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                passed will be used. Must be in descending order.
            sigmas (`List[float]`, *optional*):
                Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
                their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
                will be used.
            guidance_scale (`float`, *optional*, defaults to 4.5):
                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
                `guidance_scale` is defined as `w` of equation 2. of [Imagen
                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
                usually at the expense of lower image quality.
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            height (`int`, *optional*, defaults to self.unet.config.sample_size):
                The height in pixels of the generated image.
            width (`int`, *optional*, defaults to self.unet.config.sample_size):
                The width in pixels of the generated image.
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
                [`schedulers.DDIMScheduler`], will be ignored for others.
            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                to make generation deterministic.
            latents (`torch.Tensor`, *optional*):
                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor will ge generated by sampling using the supplied random `generator`.
            prompt_embeds (`torch.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            prompt_attention_mask (`torch.Tensor`, *optional*): Pre-generated attention mask for text embeddings.
            negative_prompt_embeds (`torch.Tensor`, *optional*):
                Pre-generated negative text embeddings. For PixArt-Sigma this negative prompt should be "". If not
                provided, negative_prompt_embeds will be generated from `negative_prompt` input argument.
            negative_prompt_attention_mask (`torch.Tensor`, *optional*):
                Pre-generated attention mask for negative text embeddings.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generate image. Choose between
                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `True`):
                Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a plain tuple.
            callback (`Callable`, *optional*):
                A function that will be called every `callback_steps` steps during inference. The function will be
                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
            callback_steps (`int`, *optional*, defaults to 1):
                The frequency at which the `callback` function will be called. If not specified, the callback will be
                called at every step.
            clean_caption (`bool`, *optional*, defaults to `True`):
                Whether or not to clean the caption before creating embeddings. Requires `beautifulsoup4` and `ftfy` to
                be installed. If the dependencies are not installed, the embeddings will be created from the raw
                prompt.
            use_resolution_binning (`bool` defaults to `True`):
                If set to `True`, the requested height and width are first mapped to the closest resolutions using
                `ASPECT_RATIO_1024_BIN`. After the produced latents are decoded into images, they are resized back to
                the requested resolution. Useful for generating non-square images.
            max_sequence_length (`int` defaults to 300): Maximum sequence length to use with the `prompt`.

        Examples:

        Returns:
            [`~pipelines.ImagePipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.ImagePipelineOutput`] is returned, otherwise a `tuple` is
                returned where the first element is a list with the generated images
        """
        # 1. Check inputs. Raise error if not correct
        height = height or self.transformer.config.sample_size * self.vae_scale_factor
        width = width or self.transformer.config.sample_size * self.vae_scale_factor
        if use_resolution_binning:
            if self.transformer.config.sample_size == 256:
                aspect_ratio_bin = ASPECT_RATIO_2048_BIN
            elif self.transformer.config.sample_size == 128:
                aspect_ratio_bin = ASPECT_RATIO_1024_BIN
            elif self.transformer.config.sample_size == 64:
                aspect_ratio_bin = ASPECT_RATIO_512_BIN
            elif self.transformer.config.sample_size == 32:
                aspect_ratio_bin = ASPECT_RATIO_256_BIN
            else:
                raise ValueError("Invalid sample size")
            orig_height, orig_width = height, width
            height, width = self.image_processor.classify_height_width_bin(
                height, width, ratios=aspect_ratio_bin
            )

        self.check_inputs(
            prompt,
            height,
            width,
            strength,
            num_inference_steps,
            negative_prompt,
            callback_steps,
            prompt_embeds,
            negative_prompt_embeds,
            prompt_attention_mask,
            negative_prompt_attention_mask,
        )

        # 2. Default height and width to transformer
        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        device = self._execution_device
        self._denoising_start = denoising_start
        self._num_timesteps = num_inference_steps
        self._denoising_end = denoising_end

        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
        # corresponds to doing no classifier free guidance.
        do_classifier_free_guidance = guidance_scale > 1.0

        # 3. Encode input prompt
        (
            prompt_embeds,
            prompt_attention_mask,
            negative_prompt_embeds,
            negative_prompt_attention_mask,
        ) = self.encode_prompt(
            prompt,
            do_classifier_free_guidance,
            negative_prompt=negative_prompt,
            num_images_per_prompt=num_images_per_prompt,
            device=device,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            prompt_attention_mask=prompt_attention_mask,
            negative_prompt_attention_mask=negative_prompt_attention_mask,
            clean_caption=clean_caption,
            max_sequence_length=max_sequence_length,
        )
        if do_classifier_free_guidance:
            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
            prompt_attention_mask = torch.cat(
                [negative_prompt_attention_mask, prompt_attention_mask], dim=0
            )

        # 4. Prepare timesteps
        def denoising_value_valid(dnv):
            return isinstance(dnv, float) and 0 < dnv < 1

        timesteps, num_inference_steps = retrieve_timesteps(
            self.scheduler, num_inference_steps, device, timesteps, sigmas
        )

        # 5. Prepare latents.
        if image is not None:
            image = self.image_processor.preprocess(image)
            image = image.to(device=self.vae.device, dtype=self.vae.dtype)

        latent_channels = self.transformer.config.in_channels
        latent_timestep = None
        if (
            denoising_end is not None
            or denoising_start is not None
            or strength is not None
        ):
            timesteps, num_inference_steps = self.get_timesteps(
                num_inference_steps,
                strength,
                device,
                denoising_start=(
                    self.denoising_start
                    if denoising_value_valid(self.denoising_start)
                    else None
                ),
            )
            latent_timestep = timesteps[:1].repeat(batch_size * num_images_per_prompt)
            if latents is not None:
                height, width = latents.shape[-2:]
                height = height * self.vae_scale_factor
                width = width * self.vae_scale_factor
        add_noise = (
            True
            if (
                self.denoising_start is None
                and (image is not None or latents is not None)
            )
            else False
        )
        debug_print(f"Add_noise: {add_noise}")
        if latents is None:
            debug_print("Prepare latents..")
            latents = self.prepare_latents(
                batch_size * num_images_per_prompt,
                latent_channels,
                height,
                width,
                prompt_embeds.dtype,
                device,
                generator,
                latents,
                timestep=latent_timestep,
                add_noise=add_noise,
                image=image,
            )

        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

        # 6.1 Prepare micro-conditions.
        added_cond_kwargs = {"resolution": None, "aspect_ratio": None}

        # 7. Denoising loop
        num_warmup_steps = max(
            len(timesteps) - num_inference_steps * self.scheduler.order, 0
        )
        if (
            self.denoising_end is not None
            and self.denoising_start is not None
            and denoising_value_valid(self.denoising_end)
            and denoising_value_valid(self.denoising_start)
            and self.denoising_start >= self.denoising_end
        ):
            raise ValueError(
                f"`denoising_start`: {self.denoising_start} cannot be larger than or equal to `denoising_end`: "
                + f" {self.denoising_end} when using type float."
            )
        if self.denoising_start is not None:
            if denoising_value_valid(self.denoising_start):
                discrete_timestep_cutoff = int(
                    round(
                        self.scheduler.config.num_train_timesteps
                        - (denoising_start * self.scheduler.config.num_train_timesteps)
                    )
                )

                num_inference_steps = (
                    (timesteps < discrete_timestep_cutoff).sum().item()
                )
                debug_print(
                    f"Beginning inference for stage2 with {num_inference_steps} steps."
                )

            else:
                raise ValueError(
                    f"`denoising_start` must be a float between 0 and 1: {denoising_start}"
                )
        if self.denoising_end is not None:
            if denoising_value_valid(self.denoising_end):
                discrete_timestep_cutoff = int(
                    round(
                        self.scheduler.config.num_train_timesteps
                        - (
                            self.denoising_end
                            * self.scheduler.config.num_train_timesteps
                        )
                    )
                )
                num_inference_steps = len(
                    list(filter(lambda ts: ts >= discrete_timestep_cutoff, timesteps))
                )
                debug_print(
                    f"Beginning inference for stage1 with {num_inference_steps} steps."
                )
                timesteps = timesteps[:num_inference_steps]
            else:
                raise ValueError(
                    f"`denoising_end` must be a float between 0 and 1: {denoising_end}"
                )
        with self.progress_bar(total=num_inference_steps) as progress_bar:
            for i, t in enumerate(timesteps):
                latent_model_input = (
                    torch.cat([latents] * 2) if do_classifier_free_guidance else latents
                )
                latent_model_input = self.scheduler.scale_model_input(
                    latent_model_input, t
                )

                current_timestep = t
                if not torch.is_tensor(current_timestep):
                    # 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 = latent_model_input.device.type == "mps"
                    if isinstance(current_timestep, float):
                        dtype = torch.float32 if is_mps else torch.float64
                    else:
                        dtype = torch.int32 if is_mps else torch.int64
                    current_timestep = torch.tensor(
                        [current_timestep],
                        dtype=dtype,
                        device=latent_model_input.device,
                    )
                elif len(current_timestep.shape) == 0:
                    current_timestep = current_timestep[None].to(
                        latent_model_input.device
                    )
                # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
                current_timestep = current_timestep.expand(latent_model_input.shape[0])

                # predict noise model_output
                noise_pred = self.transformer(
                    latent_model_input.to(
                        device=self.transformer.device, dtype=self.transformer.dtype
                    ),
                    encoder_hidden_states=prompt_embeds,
                    encoder_attention_mask=prompt_attention_mask,
                    timestep=current_timestep,
                    added_cond_kwargs=added_cond_kwargs,
                    return_dict=False,
                )[0]

                # perform guidance
                if do_classifier_free_guidance:
                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
                    noise_pred = noise_pred_uncond + guidance_scale * (
                        noise_pred_text - noise_pred_uncond
                    )

                # learned sigma
                if self.transformer.config.out_channels // 2 == latent_channels:
                    noise_pred = noise_pred.chunk(2, dim=1)[0]
                else:
                    noise_pred = noise_pred

                # compute previous image: x_t -> x_t-1
                latents = self.scheduler.step(
                    noise_pred, t, latents, **extra_step_kwargs, return_dict=False
                )[0]

                # call the callback, if provided
                if i == len(timesteps) - 1 or (
                    (i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0
                ):
                    progress_bar.update()
                    if callback is not None and i % callback_steps == 0:
                        step_idx = i // getattr(self.scheduler, "order", 1)
                        callback(step_idx, t, latents)

        if not output_type == "latent":
            image = self.vae.decode(
                latents.to(device=self.vae.device, dtype=self.vae.dtype)
                / self.vae.config.scaling_factor,
                return_dict=False,
            )[0]
            if use_resolution_binning:
                image = self.image_processor.resize_and_crop_tensor(
                    image, orig_width, orig_height
                )
        else:
            image = latents

        if not output_type == "latent":
            image = self.image_processor.postprocess(image, output_type=output_type)

        # Offload all models
        self.maybe_free_model_hooks()

        if not return_dict:
            return (image,)

        return ImagePipelineOutput(images=image)