Lumina-T2X

Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT from Alpha-VLLM, OpenGVLab, Shanghai AI Laboratory.

The abstract from the paper is:

Lumina-T2X is a nascent family of Flow-based Large Diffusion Transformers (Flag-DiT) that establishes a unified framework for transforming noise into various modalities, such as images and videos, conditioned on text instructions. Despite its promising capabilities, Lumina-T2X still encounters challenges including training instability, slow inference, and extrapolation artifacts. In this paper, we present Lumina-Next, an improved version of Lumina-T2X, showcasing stronger generation performance with increased training and inference efficiency. We begin with a comprehensive analysis of the Flag-DiT architecture and identify several suboptimal components, which we address by introducing the Next-DiT architecture with 3D RoPE and sandwich normalizations. To enable better resolution extrapolation, we thoroughly compare different context extrapolation methods applied to text-to-image generation with 3D RoPE, and propose Frequency- and Time-Aware Scaled RoPE tailored for diffusion transformers. Additionally, we introduce a sigmoid time discretization schedule to reduce sampling steps in solving the Flow ODE and the Context Drop method to merge redundant visual tokens for faster network evaluation, effectively boosting the overall sampling speed. Thanks to these improvements, Lumina-Next not only improves the quality and efficiency of basic text-to-image generation but also demonstrates superior resolution extrapolation capabilities and multilingual generation using decoder-based LLMs as the text encoder, all in a zero-shot manner. To further validate Lumina-Next as a versatile generative framework, we instantiate it on diverse tasks including visual recognition, multi-view, audio, music, and point cloud generation, showcasing strong performance across these domains. By releasing all codes and model weights at https://github.com/Alpha-VLLM/Lumina-T2X, we aim to advance the development of next-generation generative AI capable of universal modeling.

Highlights: Lumina-Next is a next-generation Diffusion Transformer that significantly enhances text-to-image generation, multilingual generation, and multitask performance by introducing the Next-DiT architecture, 3D RoPE, and frequency- and time-aware RoPE, among other improvements.

Lumina-Next has the following components: * It improves sampling efficiency with fewer and faster Steps. * It uses a Next-DiT as a transformer backbone with Sandwichnorm 3D RoPE, and Grouped-Query Attention. * It uses a Frequency- and Time-Aware Scaled RoPE.

---

Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers from Alpha-VLLM, OpenGVLab, Shanghai AI Laboratory.

The abstract from the paper is:

Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details. In this technical report, we introduce the Lumina-T2X family - a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a unified framework designed to transform noise into images, videos, multi-view 3D objects, and audio clips conditioned on text instructions. By tokenizing the latent spatial-temporal space and incorporating learnable placeholders such as [nextline] and [nextframe] tokens, Lumina-T2X seamlessly unifies the representations of different modalities across various spatial-temporal resolutions. This unified approach enables training within a single framework for different modalities and allows for flexible generation of multimodal data at any resolution, aspect ratio, and length during inference. Advanced techniques like RoPE, RMSNorm, and flow matching enhance the stability, flexibility, and scalability of Flag-DiT, enabling models of Lumina-T2X to scale up to 7 billion parameters and extend the context window to 128K tokens. This is particularly beneficial for creating ultra-high-definition images with our Lumina-T2I model and long 720p videos with our Lumina-T2V model. Remarkably, Lumina-T2I, powered by a 5-billion-parameter Flag-DiT, requires only 35% of the training computational costs of a 600-million-parameter naive DiT. Our further comprehensive analysis underscores Lumina-T2X's preliminary capability in resolution extrapolation, high-resolution editing, generating consistent 3D views, and synthesizing videos with seamless transitions. We expect that the open-sourcing of Lumina-T2X will further foster creativity, transparency, and diversity in the generative AI community.

You can find the original codebase at Alpha-VLLM and all the available checkpoints at Alpha-VLLM Lumina Family.

Highlights: Lumina-T2X supports Any Modality, Resolution, and Duration.

Lumina-T2X has the following components: * It uses a Flow-based Large Diffusion Transformer as the backbone * It supports different any modalities with one backbone and corresponding encoder, decoder.

This pipeline was contributed by PommesPeter. The original codebase can be found here. The original weights can be found under hf.co/Alpha-VLLM.

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 (Text-to-Image)

from mindone.diffusers import LuminaText2ImgPipeline
import mindspore as ms

pipeline = LuminaText2ImgPipeline.from_pretrained(
    "Alpha-VLLM/Lumina-Next-SFT-diffusers", mindspore_dtype=ms.bfloat16
)

image = pipeline(prompt="Upper body of a young woman in a Victorian-era outfit with brass goggles and leather straps. Background shows an industrial revolution cityscape with smoky skies and tall, metal structures")[0][0]

mindone.diffusers.LuminaText2ImgPipeline

Bases: DiffusionPipeline

Pipeline for text-to-image generation using Lumina-T2I.

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 images to and from latent representations. TYPE: [`AutoencoderKL`]
text_encoder	Frozen text-encoder. Lumina-T2I uses T5, specifically the t5-v1_1-xxl variant. TYPE: [`AutoModel`]
tokenizer	Tokenizer of class AutoModel. TYPE: `AutoModel`
transformer	A text conditioned Transformer2DModel to denoise the encoded image latents. TYPE: [`Transformer2DModel`]
scheduler	A scheduler to be used in combination with transformer to denoise the encoded image latents. TYPE: [`SchedulerMixin`]

Source code in mindone/diffusers/pipelines/lumina/pipeline_lumina.py

class LuminaText2ImgPipeline(DiffusionPipeline):
    r"""
    Pipeline for text-to-image generation using Lumina-T2I.

    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 images to and from latent representations.
        text_encoder ([`AutoModel`]):
            Frozen text-encoder. Lumina-T2I uses
            [T5](https://huggingface.co/docs/transformers/model_doc/t5#transformers.AutoModel), specifically the
            [t5-v1_1-xxl](https://huggingface.co/Alpha-VLLM/tree/main/t5-v1_1-xxl) variant.
        tokenizer (`AutoModel`):
            Tokenizer of class
            [AutoModel](https://huggingface.co/docs/transformers/model_doc/t5#transformers.AutoModel).
        transformer ([`Transformer2DModel`]):
            A text conditioned `Transformer2DModel` to denoise the encoded image latents.
        scheduler ([`SchedulerMixin`]):
            A scheduler to be used in combination with `transformer` to denoise the encoded image 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"

    def __init__(
        self,
        transformer: LuminaNextDiT2DModel,
        scheduler: FlowMatchEulerDiscreteScheduler,
        vae: AutoencoderKL,
        text_encoder: GemmaModel,
        tokenizer: AutoTokenizer,
    ):
        super().__init__()

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            transformer=transformer,
            scheduler=scheduler,
        )
        self.vae_scale_factor = 8
        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
        self.max_sequence_length = 256
        self.default_sample_size = (
            self.transformer.config.sample_size
            if hasattr(self, "transformer") and self.transformer is not None
            else 128
        )
        self.default_image_size = self.default_sample_size * self.vae_scale_factor

    def _get_gemma_prompt_embeds(
        self,
        prompt: Union[str, List[str]],
        num_images_per_prompt: int = 1,
        clean_caption: Optional[bool] = False,
        max_length: Optional[int] = None,
    ):
        prompt = [prompt] if isinstance(prompt, str) else prompt
        batch_size = len(prompt)

        prompt = self._text_preprocessing(prompt, clean_caption=clean_caption)
        text_inputs = self.tokenizer(
            prompt,
            pad_to_multiple_of=8,
            max_length=self.max_sequence_length,
            truncation=True,
            padding=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[:, self.max_sequence_length - 1 : -1])
            logger.warning(
                "The following part of your input was truncated because Gemma can only handle sequences up to"
                f" {self.max_sequence_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, output_hidden_states=True
        )
        prompt_embeds = prompt_embeds[1][-2]

        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)

        _, 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(batch_size * num_images_per_prompt, seq_len, -1)
        prompt_attention_mask = prompt_attention_mask.tile((num_images_per_prompt, 1))
        prompt_attention_mask = prompt_attention_mask.view(batch_size * num_images_per_prompt, -1)

        return prompt_embeds, prompt_attention_mask

    # 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: Union[str, List[str]] = None,
        num_images_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,
        **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
                Lumina-T2I, this should be "".
            do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
                whether to use classifier free guidance or not
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                number of images that should be generated per prompt
            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 Lumina-T2I, 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 256): Maximum sequence length to use for the prompt.
        """
        prompt = [prompt] if isinstance(prompt, str) else prompt
        if prompt is not None:
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if prompt_embeds is None:
            prompt_embeds, prompt_attention_mask = self._get_gemma_prompt_embeds(
                prompt=prompt,
                num_images_per_prompt=num_images_per_prompt,
                clean_caption=clean_caption,
            )

        # Get negative embeddings for classifier free guidance
        if do_classifier_free_guidance and negative_prompt_embeds is None:
            negative_prompt = negative_prompt if negative_prompt is not None else ""

            # Normalize str to list
            negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt

            if prompt is not None and type(prompt) is not type(negative_prompt):
                raise TypeError(
                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                    f" {type(prompt)}."
                )
            elif isinstance(negative_prompt, str):
                negative_prompt = [negative_prompt]
            elif batch_size != len(negative_prompt):
                raise ValueError(
                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                    " the batch size of `prompt`."
                )
            # Padding negative prompt to the same length with prompt
            prompt_max_length = prompt_embeds.shape[1]
            negative_text_inputs = self.tokenizer(
                negative_prompt,
                padding="max_length",
                max_length=prompt_max_length,
                truncation=True,
                return_tensors="np",
            )
            negative_text_input_ids = ms.tensor(negative_text_inputs.input_ids)
            negative_prompt_attention_mask = ms.tensor(negative_text_inputs.attention_mask)
            # Get the negative prompt embeddings
            negative_prompt_embeds = self.text_encoder(
                negative_text_input_ids,
                attention_mask=negative_prompt_attention_mask,
                output_hidden_states=True,
            )

            negative_dtype = self.text_encoder.dtype
            negative_prompt_embeds = negative_prompt_embeds[1][-2]
            _, seq_len, _ = negative_prompt_embeds.shape

            negative_prompt_embeds = negative_prompt_embeds.to(dtype=negative_dtype)
            # duplicate text embeddings and attention mask for each generation per prompt, using mps friendly method
            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)
            negative_prompt_attention_mask = negative_prompt_attention_mask.tile((num_images_per_prompt, 1))
            negative_prompt_attention_mask = negative_prompt_attention_mask.view(batch_size * num_images_per_prompt, -1)

        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,
        height,
        width,
        negative_prompt,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        prompt_attention_mask=None,
        negative_prompt_attention_mask=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 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, height, width, dtype, generator, latents=None):
        shape = (
            batch_size,
            num_channels_latents,
            int(height) // self.vae_scale_factor,
            int(width) // self.vae_scale_factor,
        )
        if isinstance(generator, list) and len(generator) != batch_size:
            raise ValueError(
                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
            )

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

    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        width: Optional[int] = None,
        height: Optional[int] = None,
        num_inference_steps: int = 30,
        timesteps: List[int] = None,
        guidance_scale: float = 4.0,
        negative_prompt: Union[str, List[str]] = None,
        sigmas: List[float] = None,
        num_images_per_prompt: Optional[int] = 1,
        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,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = False,
        clean_caption: bool = True,
        max_sequence_length: int = 256,
        scaling_watershed: Optional[float] = 1.0,
        proportional_attn: Optional[bool] = True,
    ) -> Union[ImagePipelineOutput, Tuple]:
        """
        Function invoked when calling the pipeline for generation.

        Args:
            prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
                instead.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
                less than `1`).
            num_inference_steps (`int`, *optional*, defaults to 30):
                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                expense of slower inference.
            timesteps (`List[int]`, *optional*):
                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
                passed will be used. Must be in descending order.
            sigmas (`List[float]`, *optional*):
                Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
                their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
                will be used.
            guidance_scale (`float`, *optional*, defaults to 4.0):
                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 images that are closely linked to the text `prompt`,
                usually at the expense of lower image quality.
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            height (`int`, *optional*, defaults to self.unet.config.sample_size):
                The height in pixels of the generated image.
            width (`int`, *optional*, defaults to self.unet.config.sample_size):
                The width in pixels of the generated image.
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
                [`schedulers.DDIMScheduler`], will be ignored for others.
            generator (`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 image
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor will ge generated by sampling using the supplied random `generator`.
            prompt_embeds (`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 Lumina-T2I 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 image. 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.
            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 120):
                Maximum sequence length to use with the `prompt`.
            callback_on_step_end (`Callable`, *optional*):
                A function that calls at the end of each denoising steps during the inference. The function is called
                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
                `callback_on_step_end_tensor_inputs`.
            callback_on_step_end_tensor_inputs (`List`, *optional*):
                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
                `._callback_tensor_inputs` attribute of your pipeline class.

        Examples:

        Returns:
            [`~pipelines.ImagePipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.ImagePipelineOutput`] is returned, otherwise a `tuple` is
                returned where the first element is a list with the generated images
        """
        height = height or self.default_sample_size * self.vae_scale_factor
        width = width or self.default_sample_size * self.vae_scale_factor

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            prompt,
            height,
            width,
            negative_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,
        )
        cross_attention_kwargs = {}

        # 2. Define call parameters
        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]

        if proportional_attn:
            cross_attention_kwargs["base_sequence_length"] = (self.default_image_size // 16) ** 2

        scaling_factor = math.sqrt(width * height / self.default_image_size**2)

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

        # 3. Encode input prompt
        (
            prompt_embeds,
            prompt_attention_mask,
            negative_prompt_embeds,
            negative_prompt_attention_mask,
        ) = self.encode_prompt(
            prompt,
            do_classifier_free_guidance,
            negative_prompt=negative_prompt,
            num_images_per_prompt=num_images_per_prompt,
            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([prompt_embeds, negative_prompt_embeds], axis=0)
            prompt_attention_mask = ops.cat([prompt_attention_mask, negative_prompt_attention_mask], axis=0)

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

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

        # 6. Denoising loop
        with self.progress_bar(total=num_inference_steps) as progress_bar:
            for i, t in enumerate(timesteps):
                # expand the latents if we are doing classifier free guidance
                latent_model_input = ops.cat([latents] * 2) if do_classifier_free_guidance else latents

                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],))

                # reverse the timestep since Lumina uses t=0 as the noise and t=1 as the image
                current_timestep = 1 - current_timestep / self.scheduler.config.num_train_timesteps

                # prepare image_rotary_emb for positional encoding
                # dynamic scaling_factor for different resolution.
                # NOTE: For `Time-aware` denosing mechanism from Lumina-Next
                # https://arxiv.org/abs/2406.18583, Sec 2.3
                # NOTE: We should compute different image_rotary_emb with different timestep.
                if current_timestep[0] < scaling_watershed:
                    linear_factor = scaling_factor
                    ntk_factor = 1.0
                else:
                    linear_factor = 1.0
                    ntk_factor = scaling_factor
                image_rotary_emb = get_2d_rotary_pos_embed_lumina(
                    self.transformer.head_dim,
                    384,
                    384,
                    linear_factor=linear_factor,
                    ntk_factor=ntk_factor,
                )

                noise_pred = self.transformer(
                    hidden_states=latent_model_input,
                    timestep=current_timestep,
                    encoder_hidden_states=prompt_embeds,
                    encoder_mask=prompt_attention_mask,
                    image_rotary_emb=image_rotary_emb,
                    cross_attention_kwargs=cross_attention_kwargs,
                    return_dict=False,
                )[0]
                noise_pred = noise_pred.chunk(2, axis=1)[0]

                # perform guidance scale
                # NOTE: For exact reproducibility reasons, we apply classifier-free guidance on only
                # three channels by default. The standard approach to cfg applies it to all channels.
                # This can be done by uncommenting the following line and commenting-out the line following that.
                # eps, rest = model_out[:, :self.in_channels], model_out[:, self.in_channels:]
                if do_classifier_free_guidance:
                    noise_pred_eps, noise_pred_rest = noise_pred[:, :3], noise_pred[:, 3:]
                    noise_pred_cond_eps, noise_pred_uncond_eps = ops.split(
                        noise_pred_eps, len(noise_pred_eps) // 2, axis=0
                    )
                    noise_pred_half = noise_pred_uncond_eps + guidance_scale * (
                        noise_pred_cond_eps - noise_pred_uncond_eps
                    )
                    noise_pred_eps = ops.cat([noise_pred_half, noise_pred_half], axis=0)

                    noise_pred = ops.cat([noise_pred_eps, noise_pred_rest], axis=1)
                    noise_pred, _ = noise_pred.chunk(2, axis=0)

                # compute the previous noisy sample x_t -> x_t-1
                noise_pred = -noise_pred
                latents = self.scheduler.step(noise_pred, t, latents, return_dict=False)[0]

                progress_bar.update()

        if not output_type == "latent":
            latents = latents / self.vae.config.scaling_factor
            image = self.vae.decode(latents, return_dict=False)[0]
            image = self.image_processor.postprocess(image, output_type=output_type)
        else:
            image = latents

        if not return_dict:
            return (image,)

        return ImagePipelineOutput(images=image)

mindone.diffusers.LuminaText2ImgPipeline.__call__(prompt=None, width=None, height=None, num_inference_steps=30, timesteps=None, guidance_scale=4.0, negative_prompt=None, sigmas=None, num_images_per_prompt=1, generator=None, latents=None, prompt_embeds=None, negative_prompt_embeds=None, prompt_attention_mask=None, negative_prompt_attention_mask=None, output_type='pil', return_dict=False, clean_caption=True, max_sequence_length=256, scaling_watershed=1.0, proportional_attn=True)

Function invoked when calling the pipeline for generation.

PARAMETER	DESCRIPTION
prompt	The prompt or prompts to guide the image 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 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). TYPE: `str` or `List[str]`, *optional* DEFAULT: None
num_inference_steps	The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. TYPE: `int`, *optional*, defaults to 30 DEFAULT: 30
timesteps	Custom timesteps to use for the denoising process with schedulers which support a timesteps argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used. Must be in descending order. TYPE: `List[int]`, *optional* DEFAULT: None
sigmas	Custom sigmas to use for the denoising process with schedulers which support a sigmas argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used. TYPE: `List[float]`, *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 images that are closely linked to the text prompt, usually at the expense of lower image quality. TYPE: `float`, *optional*, defaults to 4.0 DEFAULT: 4.0
num_images_per_prompt	The number of images to generate per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
height	The height in pixels of the generated image. TYPE: `int`, *optional*, defaults to self.unet.config.sample_size DEFAULT: None
width	The width in pixels of the generated image. 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
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 image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied random generator. 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 Lumina-T2I 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 image. 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
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 120 DEFAULT: 256
callback_on_step_end	A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs. TYPE: `Callable`, *optional*
callback_on_step_end_tensor_inputs	The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the ._callback_tensor_inputs attribute of your pipeline class. TYPE: `List`, *optional*

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

Source code in mindone/diffusers/pipelines/lumina/pipeline_lumina.py

def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    width: Optional[int] = None,
    height: Optional[int] = None,
    num_inference_steps: int = 30,
    timesteps: List[int] = None,
    guidance_scale: float = 4.0,
    negative_prompt: Union[str, List[str]] = None,
    sigmas: List[float] = None,
    num_images_per_prompt: Optional[int] = 1,
    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,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    output_type: Optional[str] = "pil",
    return_dict: bool = False,
    clean_caption: bool = True,
    max_sequence_length: int = 256,
    scaling_watershed: Optional[float] = 1.0,
    proportional_attn: Optional[bool] = True,
) -> Union[ImagePipelineOutput, Tuple]:
    """
    Function invoked when calling the pipeline for generation.

    Args:
        prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
            instead.
        negative_prompt (`str` or `List[str]`, *optional*):
            The prompt or prompts not to guide the image generation. If not defined, one has to pass
            `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
            less than `1`).
        num_inference_steps (`int`, *optional*, defaults to 30):
            The number of denoising steps. More denoising steps usually lead to a higher quality image at the
            expense of slower inference.
        timesteps (`List[int]`, *optional*):
            Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
            in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
            passed will be used. Must be in descending order.
        sigmas (`List[float]`, *optional*):
            Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
            their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
            will be used.
        guidance_scale (`float`, *optional*, defaults to 4.0):
            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 images that are closely linked to the text `prompt`,
            usually at the expense of lower image quality.
        num_images_per_prompt (`int`, *optional*, defaults to 1):
            The number of images to generate per prompt.
        height (`int`, *optional*, defaults to self.unet.config.sample_size):
            The height in pixels of the generated image.
        width (`int`, *optional*, defaults to self.unet.config.sample_size):
            The width in pixels of the generated image.
        eta (`float`, *optional*, defaults to 0.0):
            Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
            [`schedulers.DDIMScheduler`], will be ignored for others.
        generator (`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 image
            generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
            tensor will ge generated by sampling using the supplied random `generator`.
        prompt_embeds (`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 Lumina-T2I 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 image. 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.
        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 120):
            Maximum sequence length to use with the `prompt`.
        callback_on_step_end (`Callable`, *optional*):
            A function that calls at the end of each denoising steps during the inference. The function is called
            with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
            callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
            `callback_on_step_end_tensor_inputs`.
        callback_on_step_end_tensor_inputs (`List`, *optional*):
            The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
            will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
            `._callback_tensor_inputs` attribute of your pipeline class.

    Examples:

    Returns:
        [`~pipelines.ImagePipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`~pipelines.ImagePipelineOutput`] is returned, otherwise a `tuple` is
            returned where the first element is a list with the generated images
    """
    height = height or self.default_sample_size * self.vae_scale_factor
    width = width or self.default_sample_size * self.vae_scale_factor

    # 1. Check inputs. Raise error if not correct
    self.check_inputs(
        prompt,
        height,
        width,
        negative_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,
    )
    cross_attention_kwargs = {}

    # 2. Define call parameters
    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]

    if proportional_attn:
        cross_attention_kwargs["base_sequence_length"] = (self.default_image_size // 16) ** 2

    scaling_factor = math.sqrt(width * height / self.default_image_size**2)

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

    # 3. Encode input prompt
    (
        prompt_embeds,
        prompt_attention_mask,
        negative_prompt_embeds,
        negative_prompt_attention_mask,
    ) = self.encode_prompt(
        prompt,
        do_classifier_free_guidance,
        negative_prompt=negative_prompt,
        num_images_per_prompt=num_images_per_prompt,
        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([prompt_embeds, negative_prompt_embeds], axis=0)
        prompt_attention_mask = ops.cat([prompt_attention_mask, negative_prompt_attention_mask], axis=0)

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

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

    # 6. Denoising loop
    with self.progress_bar(total=num_inference_steps) as progress_bar:
        for i, t in enumerate(timesteps):
            # expand the latents if we are doing classifier free guidance
            latent_model_input = ops.cat([latents] * 2) if do_classifier_free_guidance else latents

            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],))

            # reverse the timestep since Lumina uses t=0 as the noise and t=1 as the image
            current_timestep = 1 - current_timestep / self.scheduler.config.num_train_timesteps

            # prepare image_rotary_emb for positional encoding
            # dynamic scaling_factor for different resolution.
            # NOTE: For `Time-aware` denosing mechanism from Lumina-Next
            # https://arxiv.org/abs/2406.18583, Sec 2.3
            # NOTE: We should compute different image_rotary_emb with different timestep.
            if current_timestep[0] < scaling_watershed:
                linear_factor = scaling_factor
                ntk_factor = 1.0
            else:
                linear_factor = 1.0
                ntk_factor = scaling_factor
            image_rotary_emb = get_2d_rotary_pos_embed_lumina(
                self.transformer.head_dim,
                384,
                384,
                linear_factor=linear_factor,
                ntk_factor=ntk_factor,
            )

            noise_pred = self.transformer(
                hidden_states=latent_model_input,
                timestep=current_timestep,
                encoder_hidden_states=prompt_embeds,
                encoder_mask=prompt_attention_mask,
                image_rotary_emb=image_rotary_emb,
                cross_attention_kwargs=cross_attention_kwargs,
                return_dict=False,
            )[0]
            noise_pred = noise_pred.chunk(2, axis=1)[0]

            # perform guidance scale
            # NOTE: For exact reproducibility reasons, we apply classifier-free guidance on only
            # three channels by default. The standard approach to cfg applies it to all channels.
            # This can be done by uncommenting the following line and commenting-out the line following that.
            # eps, rest = model_out[:, :self.in_channels], model_out[:, self.in_channels:]
            if do_classifier_free_guidance:
                noise_pred_eps, noise_pred_rest = noise_pred[:, :3], noise_pred[:, 3:]
                noise_pred_cond_eps, noise_pred_uncond_eps = ops.split(
                    noise_pred_eps, len(noise_pred_eps) // 2, axis=0
                )
                noise_pred_half = noise_pred_uncond_eps + guidance_scale * (
                    noise_pred_cond_eps - noise_pred_uncond_eps
                )
                noise_pred_eps = ops.cat([noise_pred_half, noise_pred_half], axis=0)

                noise_pred = ops.cat([noise_pred_eps, noise_pred_rest], axis=1)
                noise_pred, _ = noise_pred.chunk(2, axis=0)

            # compute the previous noisy sample x_t -> x_t-1
            noise_pred = -noise_pred
            latents = self.scheduler.step(noise_pred, t, latents, return_dict=False)[0]

            progress_bar.update()

    if not output_type == "latent":
        latents = latents / self.vae.config.scaling_factor
        image = self.vae.decode(latents, return_dict=False)[0]
        image = self.image_processor.postprocess(image, output_type=output_type)
    else:
        image = latents

    if not return_dict:
        return (image,)

    return ImagePipelineOutput(images=image)

mindone.diffusers.LuminaText2ImgPipeline.encode_prompt(prompt, do_classifier_free_guidance=True, negative_prompt=None, num_images_per_prompt=1, prompt_embeds=None, negative_prompt_embeds=None, prompt_attention_mask=None, negative_prompt_attention_mask=None, clean_caption=False, **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 Lumina-T2I, this should be "". TYPE: `str` or `List[str]`, *optional* DEFAULT: None
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 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 Lumina-T2I, 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 256

Source code in mindone/diffusers/pipelines/lumina/pipeline_lumina.py

def encode_prompt(
    self,
    prompt: Union[str, List[str]],
    do_classifier_free_guidance: bool = True,
    negative_prompt: Union[str, List[str]] = None,
    num_images_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,
    **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
            Lumina-T2I, this should be "".
        do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
            whether to use classifier free guidance or not
        num_images_per_prompt (`int`, *optional*, defaults to 1):
            number of images that should be generated per prompt
        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 Lumina-T2I, 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 256): Maximum sequence length to use for the prompt.
    """
    prompt = [prompt] if isinstance(prompt, str) else prompt
    if prompt is not None:
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    if prompt_embeds is None:
        prompt_embeds, prompt_attention_mask = self._get_gemma_prompt_embeds(
            prompt=prompt,
            num_images_per_prompt=num_images_per_prompt,
            clean_caption=clean_caption,
        )

    # Get negative embeddings for classifier free guidance
    if do_classifier_free_guidance and negative_prompt_embeds is None:
        negative_prompt = negative_prompt if negative_prompt is not None else ""

        # Normalize str to list
        negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt

        if prompt is not None and type(prompt) is not type(negative_prompt):
            raise TypeError(
                f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                f" {type(prompt)}."
            )
        elif isinstance(negative_prompt, str):
            negative_prompt = [negative_prompt]
        elif batch_size != len(negative_prompt):
            raise ValueError(
                f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                " the batch size of `prompt`."
            )
        # Padding negative prompt to the same length with prompt
        prompt_max_length = prompt_embeds.shape[1]
        negative_text_inputs = self.tokenizer(
            negative_prompt,
            padding="max_length",
            max_length=prompt_max_length,
            truncation=True,
            return_tensors="np",
        )
        negative_text_input_ids = ms.tensor(negative_text_inputs.input_ids)
        negative_prompt_attention_mask = ms.tensor(negative_text_inputs.attention_mask)
        # Get the negative prompt embeddings
        negative_prompt_embeds = self.text_encoder(
            negative_text_input_ids,
            attention_mask=negative_prompt_attention_mask,
            output_hidden_states=True,
        )

        negative_dtype = self.text_encoder.dtype
        negative_prompt_embeds = negative_prompt_embeds[1][-2]
        _, seq_len, _ = negative_prompt_embeds.shape

        negative_prompt_embeds = negative_prompt_embeds.to(dtype=negative_dtype)
        # duplicate text embeddings and attention mask for each generation per prompt, using mps friendly method
        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)
        negative_prompt_attention_mask = negative_prompt_attention_mask.tile((num_images_per_prompt, 1))
        negative_prompt_attention_mask = negative_prompt_attention_mask.view(batch_size * num_images_per_prompt, -1)

    return prompt_embeds, prompt_attention_mask, negative_prompt_embeds, negative_prompt_attention_mask