Latte

Latte: Latent Diffusion Transformer for Video Generation from Monash University, Shanghai AI Lab, Nanjing University, and Nanyang Technological University.

The abstract from the paper is:

We propose a novel Latent Diffusion Transformer, namely Latte, for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep-class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state-of-the-art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi-HD. In addition, we extend Latte to text-to-video generation (T2V) task, where Latte achieves comparable results compared to recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation.

Highlights: Latte is a latent diffusion transformer proposed as a backbone for modeling different modalities (trained for text-to-video generation here). It achieves state-of-the-art performance across four standard video benchmarks - FaceForensics, SkyTimelapse, UCF101 and Taichi-HD. To prepare and download the datasets for evaluation, please refer to this https URL.

This pipeline was contributed by maxin-cn. The original codebase can be found here. The original weights can be found under hf.co/maxin-cn.

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.

Inference

import mindspore as ms
from mindone.diffusers import LattePipeline

pipeline = LattePipeline.from_pretrained(
    "maxin-cn/Latte-1", mindspore_dtype=ms.float16
)

video = pipeline(prompt="A dog wearing sunglasses floating in space, surreal, nebulae in background")[0][0]

mindone.diffusers.LattePipeline

Bases: DiffusionPipeline

Pipeline for text-to-video generation using Latte.

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 videos to and from latent representations. TYPE: [`AutoencoderKL`]
text_encoder	Frozen text-encoder. Latte uses T5, specifically the t5-v1_1-xxl variant. TYPE: [`T5EncoderModel`]
tokenizer	Tokenizer of class T5Tokenizer. TYPE: `T5Tokenizer`
transformer	A text conditioned LatteTransformer3DModel to denoise the encoded video latents. TYPE: [`LatteTransformer3DModel`]
scheduler	A scheduler to be used in combination with transformer to denoise the encoded video latents. TYPE: [`SchedulerMixin`]

Source code in mindone/diffusers/pipelines/latte/pipeline_latte.py

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

    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 ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations.
        text_encoder ([`T5EncoderModel`]):
            Frozen text-encoder. Latte 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 ([`LatteTransformer3DModel`]):
            A text conditioned `LatteTransformer3DModel` 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¿¡§~\)\(\]\[\}\{\|\\/\\*]{1,}")

    _optional_components = ["tokenizer", "text_encoder"]
    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: AutoencoderKL,
        transformer: LatteTransformer3DModel,
        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.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor)

    # Adapted from https://github.com/PixArt-alpha/PixArt-alpha/blob/master/diffusion/model/utils.py
    def mask_text_embeddings(self, emb, mask):
        if emb.shape[0] == 1:
            keep_index = mask.sum().item()
            return emb[:, :, :keep_index, :], keep_index  # 1, 120, 4096 -> 1 7 4096
        else:
            masked_feature = emb * mask[:, None, :, None]  # 1 120 4096
            return masked_feature, emb.shape[2]

    # Adapted from diffusers.pipelines.deepfloyd_if.pipeline_if.encode_prompt
    def encode_prompt(
        self,
        prompt: Union[str, List[str]],
        do_classifier_free_guidance: bool = True,
        negative_prompt: str = "",
        num_images_per_prompt: int = 1,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        clean_caption: bool = False,
        mask_feature: bool = True,
        dtype=None,
    ):
        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 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`). For
                Latte, 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 video 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 Latte, 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.
            mask_feature: (bool, defaults to `True`):
                If `True`, the function will mask the text embeddings.
        """
        embeds_initially_provided = prompt_embeds is not None and negative_prompt_embeds is not None

        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]

        max_length = 120
        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,
                return_attention_mask=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 CLIP can only handle sequences up to"
                    f" {max_length} tokens: {removed_text}"
                )

            attention_mask = ms.tensor(text_inputs.attention_mask)
            prompt_embeds_attention_mask = attention_mask

            prompt_embeds = self.text_encoder(ms.tensor(text_input_ids), attention_mask=attention_mask)
            prompt_embeds = prompt_embeds[0]
        else:
            prompt_embeds_attention_mask = ops.ones_like(prompt_embeds)

        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_images_per_prompt, 1))
        prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)
        prompt_embeds_attention_mask = prompt_embeds_attention_mask.view(bs_embed, -1)
        prompt_embeds_attention_mask = prompt_embeds_attention_mask.tile((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="np",
            )
            attention_mask = ms.tensor(uncond_input.attention_mask)

            negative_prompt_embeds = self.text_encoder(
                ms.tensor(uncond_input.input_ids),
                attention_mask=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_images_per_prompt, 1))
            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)

            # For classifier free guidance, we need to do two forward passes.
            # Here we concatenate the unconditional and text embeddings into a single batch
            # to avoid doing two forward passes
        else:
            negative_prompt_embeds = None

        # Perform additional masking.
        if mask_feature and not embeds_initially_provided:
            prompt_embeds = prompt_embeds.unsqueeze(1)
            masked_prompt_embeds, keep_indices = self.mask_text_embeddings(prompt_embeds, prompt_embeds_attention_mask)
            masked_prompt_embeds = masked_prompt_embeds.squeeze(1)
            masked_negative_prompt_embeds = (
                negative_prompt_embeds[:, :keep_indices, :] if negative_prompt_embeds is not None else None
            )

            return masked_prompt_embeds, masked_negative_prompt_embeds

        return prompt_embeds, negative_prompt_embeds

    # 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,
        height,
        width,
        negative_prompt,
        callback_on_step_end_tensor_inputs,
        prompt_embeds=None,
        negative_prompt_embeds=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}.")

        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}, "
                f"but found {[k for k in callback_on_step_end_tensor_inputs if k not in self._callback_tensor_inputs]}"
            )
        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 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}."
                )

    # 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.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
    def prepare_latents(
        self, batch_size, num_channels_latents, num_frames, height, width, dtype, generator, latents=None
    ):
        shape = (
            batch_size,
            num_channels_latents,
            num_frames,
            height // self.vae_scale_factor,
            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 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

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

    # 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.
    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1

    @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 = 50,
        timesteps: Optional[List[int]] = None,
        guidance_scale: float = 7.5,
        num_images_per_prompt: int = 1,
        video_length: int = 16,
        height: int = 512,
        width: int = 512,
        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,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        output_type: 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,
        mask_feature: bool = True,
        enable_temporal_attentions: bool = True,
        decode_chunk_size: Optional[int] = None,
    ) -> Union[LattePipelineOutput, 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 7.0):
                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.
            video_length (`int`, *optional*, defaults to 16):
                The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                The number of videos to generate per prompt.
            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*):
                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for video
                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 (`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 Latte this negative prompt should be "". If not provided,
                negative_prompt_embeds will be generated from `negative_prompt` input argument.
            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_on_step_end (`Callable[[int, int, Dict], None]`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
                A callback function or a list of callback functions to be called at the end of each denoising step.
            callback_on_step_end_tensor_inputs (`List[str]`, *optional*):
                A list of tensor inputs that should be passed to the callback function. If not defined, all tensor
                inputs will be passed.
            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.
            mask_feature (`bool` defaults to `True`): If set to `True`, the text embeddings will be masked.
            enable_temporal_attentions (`bool`, *optional*, defaults to `True`): Whether to enable temporal attentions
            decode_chunk_size (`int`, *optional*):
                The number of frames to decode at a time. Higher chunk size leads to better temporal consistency at the
                expense of more memory usage. By default, the decoder decodes all frames at once for maximal quality.
                For lower memory usage, reduce `decode_chunk_size`.

        Examples:

        Returns:
            [`~pipelines.latte.pipeline_latte.LattePipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.latte.pipeline_latte.LattePipelineOutput`] is returned,
                otherwise a `tuple` is returned where the first element is a list with the generated images
        """
        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

        # 0. Default
        decode_chunk_size = decode_chunk_size if decode_chunk_size is not None else video_length

        # 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
        self.check_inputs(
            prompt,
            height,
            width,
            negative_prompt,
            callback_on_step_end_tensor_inputs,
            prompt_embeds,
            negative_prompt_embeds,
        )
        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, negative_prompt_embeds = self.encode_prompt(
            prompt,
            do_classifier_free_guidance,
            negative_prompt=negative_prompt,
            num_images_per_prompt=num_images_per_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            clean_caption=clean_caption,
            mask_feature=mask_feature,
        )
        if do_classifier_free_guidance:
            prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)

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

        # 5. Prepare latents.
        latent_channels = self.transformer.config.in_channels
        latents = self.prepare_latents(
            batch_size * num_images_per_prompt,
            latent_channels,
            video_length,
            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. Denoising loop
        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)

        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)

                current_timestep = t
                if not ops.is_tensor(current_timestep):
                    if isinstance(current_timestep, float):
                        dtype = ms.float32
                    else:
                        dtype = ms.int32
                    current_timestep = ms.tensor([current_timestep], dtype=dtype)
                elif len(current_timestep.shape) == 0:
                    current_timestep = current_timestep[None]
                # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
                current_timestep = current_timestep.broadcast_to((latent_model_input.shape[0],))

                # predict noise model_output
                noise_pred = self.transformer(
                    latent_model_input,
                    encoder_hidden_states=prompt_embeds,
                    timestep=current_timestep,
                    enable_temporal_attentions=enable_temporal_attentions,
                    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)

                # use learned sigma?
                if not (
                    hasattr(self.scheduler.config, "variance_type")
                    and self.scheduler.config.variance_type in ["learned", "learned_range"]
                ):
                    noise_pred = noise_pred.chunk(2, axis=1)[0]

                # compute previous video: 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 == "latents":
            video = self.decode_latents(latents, video_length, decode_chunk_size=14)
            video = self.video_processor.postprocess_video(video=video, output_type=output_type)
        else:
            video = latents

        if not return_dict:
            return (video,)

        return LattePipelineOutput(frames=video)

    # Similar to diffusers.pipelines.stable_video_diffusion.pipeline_stable_video_diffusion.decode_latents
    def decode_latents(self, latents: ms.Tensor, video_length: int, decode_chunk_size: int = 14):
        # [batch, channels, frames, height, width] -> [batch*frames, channels, height, width]
        latents = latents.permute(0, 2, 1, 3, 4).flatten(start_dim=0, end_dim=1)

        latents = 1 / self.vae.config.scaling_factor * latents

        forward_vae_fn = self.vae.construct
        accepts_num_frames = "num_frames" in set(inspect.signature(forward_vae_fn).parameters.keys())

        # decode decode_chunk_size frames at a time to avoid OOM
        frames = []
        for i in range(0, latents.shape[0], decode_chunk_size):
            num_frames_in = latents[i : i + decode_chunk_size].shape[0]
            decode_kwargs = {}
            if accepts_num_frames:
                # we only pass num_frames_in if it's expected
                decode_kwargs["num_frames"] = num_frames_in

            frame = self.vae.decode(latents[i : i + decode_chunk_size], **decode_kwargs)[0]
            frames.append(frame)
        frames = ops.cat(frames, axis=0)

        # [batch*frames, channels, height, width] -> [batch, channels, frames, height, width]
        frames = frames.reshape((-1, video_length) + frames.shape[1:]).permute(0, 2, 1, 3, 4)

        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloa16
        frames = frames.float()
        return frames

mindone.diffusers.LattePipeline.__call__(prompt=None, negative_prompt='', num_inference_steps=50, timesteps=None, guidance_scale=7.5, num_images_per_prompt=1, video_length=16, height=512, width=512, eta=0.0, generator=None, latents=None, prompt_embeds=None, negative_prompt_embeds=None, output_type='pil', return_dict=False, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], clean_caption=True, mask_feature=True, enable_temporal_attentions=True, decode_chunk_size=None)

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: 50
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 7.0 DEFAULT: 7.5
video_length	The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds TYPE: `int`, *optional*, defaults to 16 DEFAULT: 16
num_images_per_prompt	The number of videos to generate per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
height	The height in pixels of the generated video. TYPE: `int`, *optional*, defaults to self.unet.config.sample_size DEFAULT: 512
width	The width in pixels of the generated video. TYPE: `int`, *optional*, defaults to self.unet.config.sample_size DEFAULT: 512
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	Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for video 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. 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
negative_prompt_embeds	Pre-generated negative text embeddings. For Latte 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
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_on_step_end	A callback function or a list of callback functions to be called at the end of each denoising step. TYPE: `Callable[[int, int, Dict], None]`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional* DEFAULT: None
callback_on_step_end_tensor_inputs	A list of tensor inputs that should be passed to the callback function. If not defined, all tensor inputs will be passed. TYPE: `List[str]`, *optional* DEFAULT: ['latents']
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
mask_feature	If set to True, the text embeddings will be masked. TYPE: `bool` defaults to `True` DEFAULT: True
enable_temporal_attentions	Whether to enable temporal attentions TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
decode_chunk_size	The number of frames to decode at a time. Higher chunk size leads to better temporal consistency at the expense of more memory usage. By default, the decoder decodes all frames at once for maximal quality. For lower memory usage, reduce decode_chunk_size. TYPE: `int`, *optional* DEFAULT: None

RETURNS	DESCRIPTION
Union[LattePipelineOutput, Tuple]	[~pipelines.latte.pipeline_latte.LattePipelineOutput] or tuple: If return_dict is True, [~pipelines.latte.pipeline_latte.LattePipelineOutput] is returned, otherwise a tuple is returned where the first element is a list with the generated images

Source code in mindone/diffusers/pipelines/latte/pipeline_latte.py

def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    negative_prompt: str = "",
    num_inference_steps: int = 50,
    timesteps: Optional[List[int]] = None,
    guidance_scale: float = 7.5,
    num_images_per_prompt: int = 1,
    video_length: int = 16,
    height: int = 512,
    width: int = 512,
    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,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    output_type: 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,
    mask_feature: bool = True,
    enable_temporal_attentions: bool = True,
    decode_chunk_size: Optional[int] = None,
) -> Union[LattePipelineOutput, 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 7.0):
            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.
        video_length (`int`, *optional*, defaults to 16):
            The number of video frames that are generated. Defaults to 16 frames which at 8 frames per seconds
        num_images_per_prompt (`int`, *optional*, defaults to 1):
            The number of videos to generate per prompt.
        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*):
            Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for video
            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 (`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 Latte this negative prompt should be "". If not provided,
            negative_prompt_embeds will be generated from `negative_prompt` input argument.
        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_on_step_end (`Callable[[int, int, Dict], None]`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
            A callback function or a list of callback functions to be called at the end of each denoising step.
        callback_on_step_end_tensor_inputs (`List[str]`, *optional*):
            A list of tensor inputs that should be passed to the callback function. If not defined, all tensor
            inputs will be passed.
        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.
        mask_feature (`bool` defaults to `True`): If set to `True`, the text embeddings will be masked.
        enable_temporal_attentions (`bool`, *optional*, defaults to `True`): Whether to enable temporal attentions
        decode_chunk_size (`int`, *optional*):
            The number of frames to decode at a time. Higher chunk size leads to better temporal consistency at the
            expense of more memory usage. By default, the decoder decodes all frames at once for maximal quality.
            For lower memory usage, reduce `decode_chunk_size`.

    Examples:

    Returns:
        [`~pipelines.latte.pipeline_latte.LattePipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`~pipelines.latte.pipeline_latte.LattePipelineOutput`] is returned,
            otherwise a `tuple` is returned where the first element is a list with the generated images
    """
    if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
        callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs

    # 0. Default
    decode_chunk_size = decode_chunk_size if decode_chunk_size is not None else video_length

    # 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
    self.check_inputs(
        prompt,
        height,
        width,
        negative_prompt,
        callback_on_step_end_tensor_inputs,
        prompt_embeds,
        negative_prompt_embeds,
    )
    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, negative_prompt_embeds = self.encode_prompt(
        prompt,
        do_classifier_free_guidance,
        negative_prompt=negative_prompt,
        num_images_per_prompt=num_images_per_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        clean_caption=clean_caption,
        mask_feature=mask_feature,
    )
    if do_classifier_free_guidance:
        prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)

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

    # 5. Prepare latents.
    latent_channels = self.transformer.config.in_channels
    latents = self.prepare_latents(
        batch_size * num_images_per_prompt,
        latent_channels,
        video_length,
        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. Denoising loop
    num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)

    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)

            current_timestep = t
            if not ops.is_tensor(current_timestep):
                if isinstance(current_timestep, float):
                    dtype = ms.float32
                else:
                    dtype = ms.int32
                current_timestep = ms.tensor([current_timestep], dtype=dtype)
            elif len(current_timestep.shape) == 0:
                current_timestep = current_timestep[None]
            # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
            current_timestep = current_timestep.broadcast_to((latent_model_input.shape[0],))

            # predict noise model_output
            noise_pred = self.transformer(
                latent_model_input,
                encoder_hidden_states=prompt_embeds,
                timestep=current_timestep,
                enable_temporal_attentions=enable_temporal_attentions,
                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)

            # use learned sigma?
            if not (
                hasattr(self.scheduler.config, "variance_type")
                and self.scheduler.config.variance_type in ["learned", "learned_range"]
            ):
                noise_pred = noise_pred.chunk(2, axis=1)[0]

            # compute previous video: 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 == "latents":
        video = self.decode_latents(latents, video_length, decode_chunk_size=14)
        video = self.video_processor.postprocess_video(video=video, output_type=output_type)
    else:
        video = latents

    if not return_dict:
        return (video,)

    return LattePipelineOutput(frames=video)

mindone.diffusers.LattePipeline.encode_prompt(prompt, do_classifier_free_guidance=True, negative_prompt='', num_images_per_prompt=1, prompt_embeds=None, negative_prompt_embeds=None, clean_caption=False, mask_feature=True, dtype=None)

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 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). For Latte, 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_images_per_prompt	number of video 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 Latte, 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
mask_feature	(bool, defaults to True): If True, the function will mask the text embeddings. TYPE: bool DEFAULT: True

Source code in mindone/diffusers/pipelines/latte/pipeline_latte.py

def encode_prompt(
    self,
    prompt: Union[str, List[str]],
    do_classifier_free_guidance: bool = True,
    negative_prompt: str = "",
    num_images_per_prompt: int = 1,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    clean_caption: bool = False,
    mask_feature: bool = True,
    dtype=None,
):
    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 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`). For
            Latte, 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 video 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 Latte, 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.
        mask_feature: (bool, defaults to `True`):
            If `True`, the function will mask the text embeddings.
    """
    embeds_initially_provided = prompt_embeds is not None and negative_prompt_embeds is not None

    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]

    max_length = 120
    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,
            return_attention_mask=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 CLIP can only handle sequences up to"
                f" {max_length} tokens: {removed_text}"
            )

        attention_mask = ms.tensor(text_inputs.attention_mask)
        prompt_embeds_attention_mask = attention_mask

        prompt_embeds = self.text_encoder(ms.tensor(text_input_ids), attention_mask=attention_mask)
        prompt_embeds = prompt_embeds[0]
    else:
        prompt_embeds_attention_mask = ops.ones_like(prompt_embeds)

    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_images_per_prompt, 1))
    prompt_embeds = prompt_embeds.view(bs_embed * num_images_per_prompt, seq_len, -1)
    prompt_embeds_attention_mask = prompt_embeds_attention_mask.view(bs_embed, -1)
    prompt_embeds_attention_mask = prompt_embeds_attention_mask.tile((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="np",
        )
        attention_mask = ms.tensor(uncond_input.attention_mask)

        negative_prompt_embeds = self.text_encoder(
            ms.tensor(uncond_input.input_ids),
            attention_mask=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_images_per_prompt, 1))
        negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)

        # For classifier free guidance, we need to do two forward passes.
        # Here we concatenate the unconditional and text embeddings into a single batch
        # to avoid doing two forward passes
    else:
        negative_prompt_embeds = None

    # Perform additional masking.
    if mask_feature and not embeds_initially_provided:
        prompt_embeds = prompt_embeds.unsqueeze(1)
        masked_prompt_embeds, keep_indices = self.mask_text_embeddings(prompt_embeds, prompt_embeds_attention_mask)
        masked_prompt_embeds = masked_prompt_embeds.squeeze(1)
        masked_negative_prompt_embeds = (
            negative_prompt_embeds[:, :keep_indices, :] if negative_prompt_embeds is not None else None
        )

        return masked_prompt_embeds, masked_negative_prompt_embeds

    return prompt_embeds, negative_prompt_embeds