Allegro

Allegro: Open the Black Box of Commercial-Level Video Generation Model from RhymesAI, by Yuan Zhou, Qiuyue Wang, Yuxuan Cai, Huan Yang.

The abstract from the paper is:

Significant advancements have been made in the field of video generation, with the open-source community contributing a wealth of research papers and tools for training high-quality models. However, despite these efforts, the available information and resources remain insufficient for achieving commercial-level performance. In this report, we open the black box and introduce Allegro, an advanced video generation model that excels in both quality and temporal consistency. We also highlight the current limitations in the field and present a comprehensive methodology for training high-performance, commercial-level video generation models, addressing key aspects such as data, model architecture, training pipeline, and evaluation. Our user study shows that Allegro surpasses existing open-source models and most commercial models, ranking just behind Hailuo and Kling. Code: https://github.com/rhymes-ai/Allegro , Model: https://huggingface.co/rhymes-ai/Allegro , Gallery: https://rhymes.ai/allegro_gallery .

Tip

Make sure to check out the Schedulers guide to learn how to explore the tradeoff between scheduler speed and quality, and see the reuse components across pipelines section to learn how to efficiently load the same components into multiple pipelines.

mindone.diffusers.AllegroPipeline

Bases: DiffusionPipeline

Pipeline for text-to-video generation using Allegro.

This model inherits from [DiffusionPipeline]. Check the superclass documentation for the generic methods the library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)

PARAMETER	DESCRIPTION
vae	Variational Auto-Encoder (VAE) Model to encode and decode video to and from latent representations. TYPE: [`AllegroAutoEncoderKL3D`]
text_encoder	Frozen text-encoder. PixArt-Alpha uses T5, specifically the t5-v1_1-xxl variant. TYPE: [`T5EncoderModel`]
tokenizer	Tokenizer of class T5Tokenizer. TYPE: `T5Tokenizer`
transformer	A text conditioned AllegroTransformer3DModel to denoise the encoded video latents. TYPE: [`AllegroTransformer3DModel`]
scheduler	A scheduler to be used in combination with transformer to denoise the encoded video latents. TYPE: [`SchedulerMixin`]

Source code in mindone/diffusers/pipelines/allegro/pipeline_allegro.py

class AllegroPipeline(DiffusionPipeline):
    r"""
    Pipeline for text-to-video generation using Allegro.

    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
    library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)

    Args:
        vae ([`AllegroAutoEncoderKL3D`]):
            Variational Auto-Encoder (VAE) Model to encode and decode video to and from latent representations.
        text_encoder ([`T5EncoderModel`]):
            Frozen text-encoder. PixArt-Alpha uses
            [T5](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5EncoderModel), specifically the
            [t5-v1_1-xxl](https://huggingface.co/PixArt-alpha/PixArt-alpha/tree/main/t5-v1_1-xxl) variant.
        tokenizer (`T5Tokenizer`):
            Tokenizer of class
            [T5Tokenizer](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5Tokenizer).
        transformer ([`AllegroTransformer3DModel`]):
            A text conditioned `AllegroTransformer3DModel` to denoise the encoded video latents.
        scheduler ([`SchedulerMixin`]):
            A scheduler to be used in combination with `transformer` to denoise the encoded video latents.
    """

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

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

    _callback_tensor_inputs = [
        "latents",
        "prompt_embeds",
        "negative_prompt_embeds",
    ]

    def __init__(
        self,
        tokenizer: T5Tokenizer,
        text_encoder: T5EncoderModel,
        vae: AutoencoderKLAllegro,
        transformer: AllegroTransformer3DModel,
        scheduler: KarrasDiffusionSchedulers,
    ):
        super().__init__()

        self.register_modules(
            tokenizer=tokenizer, text_encoder=text_encoder, vae=vae, transformer=transformer, scheduler=scheduler
        )
        self.vae_scale_factor_spatial = (
            2 ** (len(self.vae.config.block_out_channels) - 1) if hasattr(self, "vae") and self.vae is not None else 8
        )
        self.vae_scale_factor_temporal = (
            self.vae.config.temporal_compression_ratio if hasattr(self, "vae") and self.vae is not None else 4
        )

        self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor_spatial)

    # Copied from diffusers.pipelines.pixart_alpha.pipeline_pixart_alpha.PixArtAlphaPipeline.encode_prompt with 120->512, num_images_per_prompt->num_videos_per_prompt # noqa: E501
    def encode_prompt(
        self,
        prompt: Union[str, List[str]],
        do_classifier_free_guidance: bool = True,
        negative_prompt: str = "",
        num_videos_per_prompt: int = 1,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        clean_caption: bool = False,
        max_sequence_length: int = 512,
        **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_videos_per_prompt (`int`, *optional*, defaults to 1):
                number of images that should be generated per prompt
            prompt_embeds (`ms.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 (`ms.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 512): 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."  # noqa: E501
            deprecate("mask_feature", "1.0.0", deprecation_message, standard_warn=False)

        # 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="np",
            )
            text_input_ids = text_inputs.input_ids
            untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids

            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_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 = ms.tensor(text_inputs.attention_mask)

            prompt_embeds = self.text_encoder(ms.tensor(text_input_ids), 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)

        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.tile((1, num_videos_per_prompt, 1))
        prompt_embeds = prompt_embeds.view(bs_embed * num_videos_per_prompt, seq_len, -1)
        prompt_attention_mask = prompt_attention_mask.tile((1, num_videos_per_prompt))
        prompt_attention_mask = prompt_attention_mask.view(bs_embed * num_videos_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] * bs_embed 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="np",
            )
            negative_prompt_attention_mask = ms.tensor(uncond_input.attention_mask)

            negative_prompt_embeds = self.text_encoder(
                ms.tensor(uncond_input.input_ids), 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)

            negative_prompt_embeds = negative_prompt_embeds.tile((1, num_videos_per_prompt, 1))
            negative_prompt_embeds = negative_prompt_embeds.view(bs_embed * num_videos_per_prompt, seq_len, -1)

            negative_prompt_attention_mask = negative_prompt_attention_mask.tile((1, num_videos_per_prompt))
            negative_prompt_attention_mask = negative_prompt_attention_mask.view(bs_embed * num_videos_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

    def check_inputs(
        self,
        prompt,
        num_frames,
        height,
        width,
        callback_on_step_end_tensor_inputs,
        negative_prompt=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        prompt_attention_mask=None,
        negative_prompt_attention_mask=None,
    ):
        if num_frames <= 0:
            raise ValueError(f"`num_frames` have to be positive but is {num_frames}.")
        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}.")

        if callback_on_step_end_tensor_inputs is not None and not all(
            k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
        ):
            raise ValueError(
                f"`callback_on_step_end_tensor_inputs` has to be in {self._callback_tensor_inputs}, but found {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"  # noqa: E501
            )

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

        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()

    def prepare_latents(
        self, batch_size, num_channels_latents, num_frames, height, width, dtype, generator, latents=None
    ):
        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 num_frames % 2 == 0:
            num_frames = math.ceil(num_frames / self.vae_scale_factor_temporal)
        else:
            num_frames = math.ceil((num_frames - 1) / self.vae_scale_factor_temporal) + 1

        shape = (
            batch_size,
            num_channels_latents,
            num_frames,
            height // self.vae_scale_factor_spatial,
            width // self.vae_scale_factor_spatial,
        )

        if latents is None:
            latents = randn_tensor(shape, generator=generator, dtype=dtype)

        # scale the initial noise by the standard deviation required by the scheduler
        latents = (latents * self.scheduler.init_noise_sigma).to(dtype)
        return latents

    def decode_latents(self, latents: ms.Tensor) -> ms.Tensor:
        latents = 1 / self.vae.config.scaling_factor * latents
        frames = self.vae.decode(latents)[0]
        frames = frames.permute(0, 2, 1, 3, 4)  # [batch_size, channels, num_frames, height, width]
        return frames

    def _prepare_rotary_positional_embeddings(
        self,
        batch_size: int,
        height: int,
        width: int,
        num_frames: int,
    ):
        grid_height = height // (self.vae_scale_factor_spatial * self.transformer.config.patch_size)
        grid_width = width // (self.vae_scale_factor_spatial * self.transformer.config.patch_size)

        start, stop = (0, 0), (grid_height, grid_width)
        freqs_t, freqs_h, freqs_w, grid_t, grid_h, grid_w = get_3d_rotary_pos_embed_allegro(
            embed_dim=self.transformer.config.attention_head_dim,
            crops_coords=(start, stop),
            grid_size=(grid_height, grid_width),
            temporal_size=num_frames,
            interpolation_scale=(
                self.transformer.config.interpolation_scale_t,
                self.transformer.config.interpolation_scale_h,
                self.transformer.config.interpolation_scale_w,
            ),
        )

        grid_t = grid_t.to(dtype=ms.int64)
        grid_h = grid_h.to(dtype=ms.int64)
        grid_w = grid_w.to(dtype=ms.int64)

        pos = ops.cartesian_prod(grid_t, grid_h, grid_w)
        pos = pos.reshape(-1, 3).swapaxes(0, 1).reshape(3, 1, -1).contiguous()
        grid_t, grid_h, grid_w = pos

        return (freqs_t, freqs_h, freqs_w), (grid_t, grid_h, grid_w)

    def enable_vae_slicing(self):
        r"""
        Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
        compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
        """
        self.vae.enable_slicing()

    def disable_vae_slicing(self):
        r"""
        Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
        computing decoding in one step.
        """
        self.vae.disable_slicing()

    def enable_vae_tiling(self):
        r"""
        Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to
        compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow
        processing larger images.
        """
        self.vae.enable_tiling()

    def disable_vae_tiling(self):
        r"""
        Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to
        computing decoding in one step.
        """
        self.vae.disable_tiling()

    @property
    def guidance_scale(self):
        return self._guidance_scale

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

    @property
    def interrupt(self):
        return self._interrupt

    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        negative_prompt: str = "",
        num_inference_steps: int = 100,
        timesteps: List[int] = None,
        guidance_scale: float = 7.5,
        num_frames: Optional[int] = None,
        height: Optional[int] = None,
        width: Optional[int] = None,
        num_videos_per_prompt: int = 1,
        eta: float = 0.0,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = False,
        callback_on_step_end: Optional[
            Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
        ] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
        clean_caption: bool = True,
        max_sequence_length: int = 512,
    ) -> Union[AllegroPipelineOutput, Tuple]:
        """
        Function invoked when calling the pipeline for generation.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide the video 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 video 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`).
            num_inference_steps (`int`, *optional*, defaults to 100):
                The number of denoising steps. More denoising steps usually lead to a higher quality video at the
                expense of slower inference.
            timesteps (`List[int]`, *optional*):
                Custom timesteps to use for the denoising process. If not defined, equal spaced `num_inference_steps`
                timesteps are used. Must be in descending order.
            guidance_scale (`float`, *optional*, defaults to 7.5):
                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 videos that are closely linked to the text `prompt`,
                usually at the expense of lower video quality.
            num_videos_per_prompt (`int`, *optional*, defaults to 1):
                The number of videos to generate per prompt.
            num_frames: (`int`, *optional*, defaults to 88):
                The number controls the generated video frames.
            height (`int`, *optional*, defaults to self.unet.config.sample_size):
                The height in pixels of the generated video.
            width (`int`, *optional*, defaults to self.unet.config.sample_size):
                The width in pixels of the generated video.
            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 (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
                One or a list of [np.random.Generator(s)](https://numpy.org/doc/stable/reference/random/generator.html)
                to make generation deterministic.
            latents (`ms.Tensor`, *optional*):
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for video
                tensor will ge generated by sampling using the supplied random `generator`.
            prompt_embeds (`ms.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 (`ms.Tensor`, *optional*): Pre-generated attention mask for text embeddings.
            negative_prompt_embeds (`ms.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 (`ms.Tensor`, *optional*):
                Pre-generated attention mask for negative text embeddings.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generate video. Choose between
                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `False`):
                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: ms.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.
            max_sequence_length (`int` defaults to `512`):
                Maximum sequence length to use with the `prompt`.

        Examples:

        Returns:
            [`~pipelines.allegro.pipeline_output.AllegroPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.allegro.pipeline_output.AllegroPipelineOutput`] is returned,
                otherwise a `tuple` is returned where the first element is a list with the generated videos.
        """

        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

        num_videos_per_prompt = 1

        # 1. Check inputs. Raise error if not correct
        num_frames = num_frames or self.transformer.config.sample_frames * self.vae_scale_factor_temporal
        height = height or self.transformer.config.sample_height * self.vae_scale_factor_spatial
        width = width or self.transformer.config.sample_width * self.vae_scale_factor_spatial

        self.check_inputs(
            prompt,
            num_frames,
            height,
            width,
            callback_on_step_end_tensor_inputs,
            negative_prompt,
            prompt_embeds,
            negative_prompt_embeds,
            prompt_attention_mask,
            negative_prompt_attention_mask,
        )
        self._guidance_scale = guidance_scale
        self._interrupt = False

        # 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]

        # 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_videos_per_prompt=num_videos_per_prompt,
            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 = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)
            prompt_attention_mask = ops.cat([negative_prompt_attention_mask, prompt_attention_mask], axis=0)
        if prompt_embeds.ndim == 3:
            prompt_embeds = prompt_embeds.unsqueeze(1)  # b l d -> b 1 l d

        # 4. Prepare timesteps
        timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, timesteps)
        self.scheduler.set_timesteps(num_inference_steps)

        # 5. Prepare latents.
        latent_channels = self.transformer.config.in_channels
        latents = self.prepare_latents(
            batch_size * num_videos_per_prompt,
            latent_channels,
            num_frames,
            height,
            width,
            prompt_embeds.dtype,
            generator,
            latents,
        )

        # 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)

        # 7. Prepare rotary embeddings
        image_rotary_emb = self._prepare_rotary_positional_embeddings(
            batch_size,
            height,
            width,
            latents.shape[2],
        )

        # 8. Denoising loop
        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
        self._num_timesteps = len(timesteps)

        with self.progress_bar(total=num_inference_steps) as progress_bar:
            for i, t in enumerate(timesteps):
                if self.interrupt:
                    continue

                latent_model_input = ops.cat([latents] * 2) if do_classifier_free_guidance else latents
                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

                # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
                timestep = t.broadcast_to((latent_model_input.shape[0],))

                # predict noise model_output
                noise_pred = self.transformer(
                    hidden_states=latent_model_input,
                    encoder_hidden_states=prompt_embeds,
                    encoder_attention_mask=prompt_attention_mask,
                    timestep=timestep,
                    image_rotary_emb=image_rotary_emb,
                    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)

                # 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 callback_on_step_end is not None:
                    callback_kwargs = {}
                    for k in callback_on_step_end_tensor_inputs:
                        callback_kwargs[k] = locals()[k]
                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                    latents = callback_outputs.pop("latents", latents)
                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)

                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                    progress_bar.update()

        if not output_type == "latent":
            latents = latents.to(self.vae.dtype)
            video = self.decode_latents(latents)
            video = video[:, :, :num_frames, :height, :width]
            video = self.video_processor.postprocess_video(video=video, output_type=output_type)
        else:
            video = latents

        if not return_dict:
            return (video,)

        return AllegroPipelineOutput(frames=video)

mindone.diffusers.AllegroPipeline.__call__(prompt=None, negative_prompt='', num_inference_steps=100, timesteps=None, guidance_scale=7.5, num_frames=None, height=None, width=None, num_videos_per_prompt=1, eta=0.0, generator=None, latents=None, prompt_embeds=None, prompt_attention_mask=None, negative_prompt_embeds=None, negative_prompt_attention_mask=None, output_type='pil', return_dict=False, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], clean_caption=True, max_sequence_length=512)

Function invoked when calling the pipeline for generation.

PARAMETER	DESCRIPTION
prompt	The prompt or prompts to guide the video generation. If not defined, one has to pass prompt_embeds. instead. TYPE: `str` or `List[str]`, *optional* DEFAULT: None
negative_prompt	The prompt or prompts not to guide the video 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). TYPE: `str` or `List[str]`, *optional* DEFAULT: ''
num_inference_steps	The number of denoising steps. More denoising steps usually lead to a higher quality video at the expense of slower inference. TYPE: `int`, *optional*, defaults to 100 DEFAULT: 100
timesteps	Custom timesteps to use for the denoising process. If not defined, equal spaced num_inference_steps timesteps are used. Must be in descending order. TYPE: `List[int]`, *optional* DEFAULT: None
guidance_scale	Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. Guidance scale is enabled by setting guidance_scale > 1. Higher guidance scale encourages to generate videos that are closely linked to the text prompt, usually at the expense of lower video quality. TYPE: `float`, *optional*, defaults to 7.5 DEFAULT: 7.5
num_videos_per_prompt	The number of videos to generate per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
num_frames	(int, optional, defaults to 88): The number controls the generated video frames. TYPE: Optional[int] DEFAULT: None
height	The height in pixels of the generated video. TYPE: `int`, *optional*, defaults to self.unet.config.sample_size DEFAULT: None
width	The width in pixels of the generated video. TYPE: `int`, *optional*, defaults to self.unet.config.sample_size DEFAULT: None
eta	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. TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0
generator	One or a list of np.random.Generator(s) to make generation deterministic. TYPE: `np.random.Generator` or `List[np.random.Generator]`, *optional* DEFAULT: None
latents	generation. Can be used to tweak the same generation with different prompts. If not provided, a latents Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for video tensor will ge generated by sampling using the supplied random generator. TYPE: `ms.Tensor`, *optional* DEFAULT: None
prompt_embeds	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. TYPE: `ms.Tensor`, *optional* DEFAULT: None
prompt_attention_mask	Pre-generated attention mask for text embeddings. TYPE: `ms.Tensor`, *optional* DEFAULT: None
negative_prompt_embeds	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. TYPE: `ms.Tensor`, *optional* DEFAULT: None
negative_prompt_attention_mask	Pre-generated attention mask for negative text embeddings. TYPE: `ms.Tensor`, *optional* DEFAULT: None
output_type	The output format of the generate video. Choose between PIL: PIL.Image.Image or np.array. TYPE: `str`, *optional*, defaults to `"pil"` DEFAULT: 'pil'
return_dict	Whether or not to return a [~pipelines.stable_diffusion.IFPipelineOutput] instead of a plain tuple. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
callback	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: ms.Tensor). TYPE: `Callable`, *optional*
callback_steps	The frequency at which the callback function will be called. If not specified, the callback will be called at every step. TYPE: `int`, *optional*, defaults to 1
clean_caption	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. TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
max_sequence_length	Maximum sequence length to use with the prompt. TYPE: `int` defaults to `512` DEFAULT: 512

RETURNS	DESCRIPTION
Union[AllegroPipelineOutput, Tuple]	[~pipelines.allegro.pipeline_output.AllegroPipelineOutput] or tuple: If return_dict is True, [~pipelines.allegro.pipeline_output.AllegroPipelineOutput] is returned, otherwise a tuple is returned where the first element is a list with the generated videos.

Source code in mindone/diffusers/pipelines/allegro/pipeline_allegro.py

def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    negative_prompt: str = "",
    num_inference_steps: int = 100,
    timesteps: List[int] = None,
    guidance_scale: float = 7.5,
    num_frames: Optional[int] = None,
    height: Optional[int] = None,
    width: Optional[int] = None,
    num_videos_per_prompt: int = 1,
    eta: float = 0.0,
    generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
    latents: Optional[ms.Tensor] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    output_type: Optional[str] = "pil",
    return_dict: bool = False,
    callback_on_step_end: Optional[
        Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
    ] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    clean_caption: bool = True,
    max_sequence_length: int = 512,
) -> Union[AllegroPipelineOutput, Tuple]:
    """
    Function invoked when calling the pipeline for generation.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide the video 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 video 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`).
        num_inference_steps (`int`, *optional*, defaults to 100):
            The number of denoising steps. More denoising steps usually lead to a higher quality video at the
            expense of slower inference.
        timesteps (`List[int]`, *optional*):
            Custom timesteps to use for the denoising process. If not defined, equal spaced `num_inference_steps`
            timesteps are used. Must be in descending order.
        guidance_scale (`float`, *optional*, defaults to 7.5):
            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 videos that are closely linked to the text `prompt`,
            usually at the expense of lower video quality.
        num_videos_per_prompt (`int`, *optional*, defaults to 1):
            The number of videos to generate per prompt.
        num_frames: (`int`, *optional*, defaults to 88):
            The number controls the generated video frames.
        height (`int`, *optional*, defaults to self.unet.config.sample_size):
            The height in pixels of the generated video.
        width (`int`, *optional*, defaults to self.unet.config.sample_size):
            The width in pixels of the generated video.
        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 (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
            One or a list of [np.random.Generator(s)](https://numpy.org/doc/stable/reference/random/generator.html)
            to make generation deterministic.
        latents (`ms.Tensor`, *optional*):
            generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
            Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for video
            tensor will ge generated by sampling using the supplied random `generator`.
        prompt_embeds (`ms.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 (`ms.Tensor`, *optional*): Pre-generated attention mask for text embeddings.
        negative_prompt_embeds (`ms.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 (`ms.Tensor`, *optional*):
            Pre-generated attention mask for negative text embeddings.
        output_type (`str`, *optional*, defaults to `"pil"`):
            The output format of the generate video. Choose between
            [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
        return_dict (`bool`, *optional*, defaults to `False`):
            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: ms.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.
        max_sequence_length (`int` defaults to `512`):
            Maximum sequence length to use with the `prompt`.

    Examples:

    Returns:
        [`~pipelines.allegro.pipeline_output.AllegroPipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`~pipelines.allegro.pipeline_output.AllegroPipelineOutput`] is returned,
            otherwise a `tuple` is returned where the first element is a list with the generated videos.
    """

    if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
        callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

    num_videos_per_prompt = 1

    # 1. Check inputs. Raise error if not correct
    num_frames = num_frames or self.transformer.config.sample_frames * self.vae_scale_factor_temporal
    height = height or self.transformer.config.sample_height * self.vae_scale_factor_spatial
    width = width or self.transformer.config.sample_width * self.vae_scale_factor_spatial

    self.check_inputs(
        prompt,
        num_frames,
        height,
        width,
        callback_on_step_end_tensor_inputs,
        negative_prompt,
        prompt_embeds,
        negative_prompt_embeds,
        prompt_attention_mask,
        negative_prompt_attention_mask,
    )
    self._guidance_scale = guidance_scale
    self._interrupt = False

    # 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]

    # 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_videos_per_prompt=num_videos_per_prompt,
        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 = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)
        prompt_attention_mask = ops.cat([negative_prompt_attention_mask, prompt_attention_mask], axis=0)
    if prompt_embeds.ndim == 3:
        prompt_embeds = prompt_embeds.unsqueeze(1)  # b l d -> b 1 l d

    # 4. Prepare timesteps
    timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, timesteps)
    self.scheduler.set_timesteps(num_inference_steps)

    # 5. Prepare latents.
    latent_channels = self.transformer.config.in_channels
    latents = self.prepare_latents(
        batch_size * num_videos_per_prompt,
        latent_channels,
        num_frames,
        height,
        width,
        prompt_embeds.dtype,
        generator,
        latents,
    )

    # 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)

    # 7. Prepare rotary embeddings
    image_rotary_emb = self._prepare_rotary_positional_embeddings(
        batch_size,
        height,
        width,
        latents.shape[2],
    )

    # 8. Denoising loop
    num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
    self._num_timesteps = len(timesteps)

    with self.progress_bar(total=num_inference_steps) as progress_bar:
        for i, t in enumerate(timesteps):
            if self.interrupt:
                continue

            latent_model_input = ops.cat([latents] * 2) if do_classifier_free_guidance else latents
            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

            # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
            timestep = t.broadcast_to((latent_model_input.shape[0],))

            # predict noise model_output
            noise_pred = self.transformer(
                hidden_states=latent_model_input,
                encoder_hidden_states=prompt_embeds,
                encoder_attention_mask=prompt_attention_mask,
                timestep=timestep,
                image_rotary_emb=image_rotary_emb,
                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)

            # 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 callback_on_step_end is not None:
                callback_kwargs = {}
                for k in callback_on_step_end_tensor_inputs:
                    callback_kwargs[k] = locals()[k]
                callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)

                latents = callback_outputs.pop("latents", latents)
                prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
                negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)

            if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                progress_bar.update()

    if not output_type == "latent":
        latents = latents.to(self.vae.dtype)
        video = self.decode_latents(latents)
        video = video[:, :, :num_frames, :height, :width]
        video = self.video_processor.postprocess_video(video=video, output_type=output_type)
    else:
        video = latents

    if not return_dict:
        return (video,)

    return AllegroPipelineOutput(frames=video)

mindone.diffusers.AllegroPipeline.disable_vae_slicing()

Disable sliced VAE decoding. If enable_vae_slicing was previously enabled, this method will go back to computing decoding in one step.

Source code in mindone/diffusers/pipelines/allegro/pipeline_allegro.py

def disable_vae_slicing(self):
    r"""
    Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
    computing decoding in one step.
    """
    self.vae.disable_slicing()

mindone.diffusers.AllegroPipeline.disable_vae_tiling()

Disable tiled VAE decoding. If enable_vae_tiling was previously enabled, this method will go back to computing decoding in one step.

Source code in mindone/diffusers/pipelines/allegro/pipeline_allegro.py

def disable_vae_tiling(self):
    r"""
    Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to
    computing decoding in one step.
    """
    self.vae.disable_tiling()

mindone.diffusers.AllegroPipeline.enable_vae_slicing()

Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.

Source code in mindone/diffusers/pipelines/allegro/pipeline_allegro.py

def enable_vae_slicing(self):
    r"""
    Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
    compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
    """
    self.vae.enable_slicing()

mindone.diffusers.AllegroPipeline.enable_vae_tiling()

Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow processing larger images.

Source code in mindone/diffusers/pipelines/allegro/pipeline_allegro.py

def enable_vae_tiling(self):
    r"""
    Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to
    compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow
    processing larger images.
    """
    self.vae.enable_tiling()

mindone.diffusers.AllegroPipeline.encode_prompt(prompt, do_classifier_free_guidance=True, negative_prompt='', num_videos_per_prompt=1, prompt_embeds=None, negative_prompt_embeds=None, prompt_attention_mask=None, negative_prompt_attention_mask=None, clean_caption=False, max_sequence_length=512, **kwargs)

Encodes the prompt into text encoder hidden states.

PARAMETER	DESCRIPTION
prompt	prompt to be encoded TYPE: `str` or `List[str]`, *optional*
negative_prompt	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 "". TYPE: `str` or `List[str]`, *optional* DEFAULT: ''
do_classifier_free_guidance	whether to use classifier free guidance or not TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
num_videos_per_prompt	number of images that should be generated per prompt TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
prompt_embeds	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. TYPE: `ms.Tensor`, *optional* DEFAULT: None
negative_prompt_embeds	Pre-generated negative text embeddings. For PixArt-Alpha, it's should be the embeddings of the "" string. TYPE: `ms.Tensor`, *optional* DEFAULT: None
clean_caption	If True, the function will preprocess and clean the provided caption before encoding. TYPE: `bool`, defaults to `False` DEFAULT: False
max_sequence_length	Maximum sequence length to use for the prompt. TYPE: `int`, defaults to 512 DEFAULT: 512

Source code in mindone/diffusers/pipelines/allegro/pipeline_allegro.py

def encode_prompt(
    self,
    prompt: Union[str, List[str]],
    do_classifier_free_guidance: bool = True,
    negative_prompt: str = "",
    num_videos_per_prompt: int = 1,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    clean_caption: bool = False,
    max_sequence_length: int = 512,
    **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_videos_per_prompt (`int`, *optional*, defaults to 1):
            number of images that should be generated per prompt
        prompt_embeds (`ms.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 (`ms.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 512): 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."  # noqa: E501
        deprecate("mask_feature", "1.0.0", deprecation_message, standard_warn=False)

    # 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="np",
        )
        text_input_ids = text_inputs.input_ids
        untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids

        if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_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 = ms.tensor(text_inputs.attention_mask)

        prompt_embeds = self.text_encoder(ms.tensor(text_input_ids), 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)

    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.tile((1, num_videos_per_prompt, 1))
    prompt_embeds = prompt_embeds.view(bs_embed * num_videos_per_prompt, seq_len, -1)
    prompt_attention_mask = prompt_attention_mask.tile((1, num_videos_per_prompt))
    prompt_attention_mask = prompt_attention_mask.view(bs_embed * num_videos_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] * bs_embed 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="np",
        )
        negative_prompt_attention_mask = ms.tensor(uncond_input.attention_mask)

        negative_prompt_embeds = self.text_encoder(
            ms.tensor(uncond_input.input_ids), 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)

        negative_prompt_embeds = negative_prompt_embeds.tile((1, num_videos_per_prompt, 1))
        negative_prompt_embeds = negative_prompt_embeds.view(bs_embed * num_videos_per_prompt, seq_len, -1)

        negative_prompt_attention_mask = negative_prompt_attention_mask.tile((1, num_videos_per_prompt))
        negative_prompt_attention_mask = negative_prompt_attention_mask.view(bs_embed * num_videos_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

mindone.diffusers.pipelines.allegro.pipeline_output.AllegroPipelineOutput dataclass

Bases: BaseOutput

Output class for Allegro pipelines.

PARAMETER	DESCRIPTION
frames	List of video outputs - It can be a nested list of length batch_size, with each sub-list containing denoised PIL image sequences of length num_frames. It can also be a NumPy array or Torch tensor of shape (batch_size, num_frames, channels, height, width). TYPE: `ms.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]

Source code in mindone/diffusers/pipelines/allegro/pipeline_output.py

@dataclass
class AllegroPipelineOutput(BaseOutput):
    r"""
    Output class for Allegro pipelines.

    Args:
        frames (`ms.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]):
            List of video outputs - It can be a nested list of length `batch_size,` with each sub-list containing
            denoised PIL image sequences of length `num_frames.` It can also be a NumPy array or Torch tensor of shape
            `(batch_size, num_frames, channels, height, width)`.
    """

    frames: Union[ms.Tensor, np.ndarray, List[List[PIL.Image.Image]]]