SanaPipeline

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers from NVIDIA and MIT HAN Lab, by Enze Xie, Junsong Chen, Junyu Chen, Han Cai, Haotian Tang, Yujun Lin, Zhekai Zhang, Muyang Li, Ligeng Zhu, Yao Lu, Song Han.

The abstract from the paper is:

We introduce Sana, a text-to-image framework that can efficiently generate images up to 4096×4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU. Core designs include: (1) Deep compression autoencoder: unlike traditional AEs, which compress images only 8×, we trained an AE that can compress images 32×, effectively reducing the number of latent tokens. (2) Linear DiT: we replace all vanilla attention in DiT with linear attention, which is more efficient at high resolutions without sacrificing quality. (3) Decoder-only text encoder: we replaced T5 with modern decoder-only small LLM as the text encoder and designed complex human instruction with in-context learning to enhance the image-text alignment. (4) Efficient training and sampling: we propose Flow-DPM-Solver to reduce sampling steps, with efficient caption labeling and selection to accelerate convergence. As a result, Sana-0.6B is very competitive with modern giant diffusion model (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput. Moreover, Sana-0.6B can be deployed on a 16GB laptop GPU, taking less than 1 second to generate a 1024×1024 resolution image. Sana enables content creation at low cost. Code and model will be publicly released.

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.

This pipeline was contributed by lawrence-cj and chenjy2003. The original codebase can be found here. The original weights can be found under hf.co/Efficient-Large-Model.

Available models:

Model	Recommended dtype
Efficient-Large-Model/Sana_1600M_1024px_BF16_diffusers	mindspore.bfloat16
Efficient-Large-Model/Sana_1600M_1024px_diffusers	mindspore.float16
Efficient-Large-Model/Sana_1600M_1024px_MultiLing_diffusers	mindspore.float16
Efficient-Large-Model/Sana_1600M_512px_diffusers	mindspore.float16
Efficient-Large-Model/Sana_1600M_512px_MultiLing_diffusers	mindspore.float16
Efficient-Large-Model/Sana_600M_1024px_diffusers	mindspore.float16
Efficient-Large-Model/Sana_600M_512px_diffusers	mindspore.float16

Refer to this collection for more information.

Note: The recommended dtype mentioned is for the transformer weights. The text encoder and VAE weights must stay in mindspore.bfloat16 or mindspore.float32 for the model to work correctly. Please refer to the inference example below to see how to load the model with the recommended dtype.

Tip

Make sure to pass the variant argument for downloaded checkpoints to use lower disk space. Set it to "fp16" for models with recommended dtype as mindspore.float16, and "bf16" for models with recommended dtype as mindspore.bfloat16. By default, mindspore.float32 weights are downloaded, which use twice the amount of disk storage. Additionally, mindspore.float32 weights can be downcasted on-the-fly by specifying the mindspore_dtype argument. Read about it in the docs.

mindone.diffusers.SanaPipeline

Bases: DiffusionPipeline, SanaLoraLoaderMixin

Pipeline for text-to-image generation using Sana.

Source code in mindone/diffusers/pipelines/sana/pipeline_sana.py

class SanaPipeline(DiffusionPipeline, SanaLoraLoaderMixin):
    r"""
    Pipeline for text-to-image generation using [Sana](https://huggingface.co/papers/2410.10629).
    """

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

    model_cpu_offload_seq = "text_encoder->transformer->vae"
    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]

    def __init__(
        self,
        tokenizer: AutoTokenizer,
        text_encoder: MSPreTrainedModel,
        vae: AutoencoderDC,
        transformer: SanaTransformer2DModel,
        scheduler: DPMSolverMultistepScheduler,
    ):
        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.encoder_block_out_channels) - 1)
            if hasattr(self, "vae") and self.vae is not None
            else 32
        )
        self.image_processor = PixArtImageProcessor(vae_scale_factor=self.vae_scale_factor)

    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,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        clean_caption: bool = False,
        max_sequence_length: int = 300,
        complex_human_instruction: Optional[List[str]] = None,
        lora_scale: Optional[float] = 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 image generation. If not defined, one has to pass `negative_prompt_embeds`
                instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`). For
                PixArt-Alpha, this should be "".
            do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
                whether to use classifier free guidance or not
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                number of images that should be generated per prompt
            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 Sana, it's should be the embeddings of the "" string.
            clean_caption (`bool`, defaults to `False`):
                If `True`, the function will preprocess and clean the provided caption before encoding.
            max_sequence_length (`int`, defaults to 300): Maximum sequence length to use for the prompt.
            complex_human_instruction (`list[str]`, defaults to `complex_human_instruction`):
                If `complex_human_instruction` is not empty, the function will use the complex Human instruction for
                the prompt.
        """
        # set lora scale so that monkey patched LoRA
        # function of text encoder can correctly access it
        if lora_scale is not None and isinstance(self, SanaLoraLoaderMixin):
            self._lora_scale = lora_scale

            # dynamically adjust the LoRA scale
            if self.text_encoder is not None:
                scale_lora_layers(self.text_encoder, lora_scale)

        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]

        self.tokenizer.padding_side = "right"

        # See Section 3.1. of the paper.
        max_length = max_sequence_length
        select_index = [0] + list(range(-max_length + 1, 0))

        if prompt_embeds is None:
            prompt = self._text_preprocessing(prompt, clean_caption=clean_caption)

            # prepare complex human instruction
            if not complex_human_instruction:
                max_length_all = max_length
            else:
                chi_prompt = "\n".join(complex_human_instruction)
                prompt = [chi_prompt + p for p in prompt]
                num_chi_prompt_tokens = len(self.tokenizer.encode(chi_prompt))
                max_length_all = num_chi_prompt_tokens + max_length - 2

            text_inputs = self.tokenizer(
                prompt,
                padding="max_length",
                max_length=max_length_all,
                truncation=True,
                add_special_tokens=True,
                return_tensors="np",
            )
            text_input_ids = ms.Tensor.from_numpy(text_inputs.input_ids)

            prompt_attention_mask = ms.Tensor.from_numpy(text_inputs.attention_mask)

            prompt_embeds = self.text_encoder(text_input_ids, attention_mask=prompt_attention_mask)
            prompt_embeds = prompt_embeds[0][:, select_index]
            prompt_attention_mask = prompt_attention_mask[:, select_index]

        if self.transformer is not None:
            dtype = self.transformer.dtype
        elif self.text_encoder is not None:
            dtype = self.text_encoder.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_attention_mask = prompt_attention_mask.view(bs_embed, -1)
        prompt_attention_mask = prompt_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",
            )
            negative_prompt_attention_mask = ms.Tensor.from_numpy(uncond_input.attention_mask)

            negative_prompt_embeds = self.text_encoder(
                ms.Tensor.from_numpy(uncond_input.input_ids),
                attention_mask=negative_prompt_attention_mask,
            )
            negative_prompt_embeds = negative_prompt_embeds[0]

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

            negative_prompt_embeds = negative_prompt_embeds.to(dtype=dtype)

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

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

        if self.text_encoder is not None:
            if isinstance(self, SanaLoraLoaderMixin):
                # Retrieve the original scale by scaling back the LoRA layers
                unscale_lora_layers(self.text_encoder, lora_scale)

        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,
        callback_on_step_end_tensor_inputs=None,
        negative_prompt=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        prompt_attention_mask=None,
        negative_prompt_attention_mask=None,
    ):
        if height % 32 != 0 or width % 32 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 32 but are {height} and {width}.")

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

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

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

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

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

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

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

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

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

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

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

        return [process(t) for t in text]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

        caption.strip()

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

        return caption.strip()

    def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, generator, latents=None):
        if latents is not None:
            return latents.to(dtype=dtype)

        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."
            )

        latents = randn_tensor(shape, generator=generator, dtype=dtype)
        return latents

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

    @property
    def attention_kwargs(self):
        return self._attention_kwargs

    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1.0

    @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 = 20,
        timesteps: List[int] = None,
        sigmas: List[float] = None,
        guidance_scale: float = 4.5,
        num_images_per_prompt: Optional[int] = 1,
        height: int = 1024,
        width: int = 1024,
        eta: float = 0.0,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = False,
        clean_caption: bool = True,
        use_resolution_binning: bool = True,
        attention_kwargs: Optional[Dict[str, Any]] = None,
        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
        max_sequence_length: int = 300,
        complex_human_instruction: List[str] = [
            "Given a user prompt, generate an 'Enhanced prompt' that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:",  # noqa: E501
            "- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.",  # noqa: E501
            "- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.",
            "Here are examples of how to transform or refine prompts:",
            "- User Prompt: A cat sleeping -> Enhanced: A small, fluffy white cat curled up in a round shape, sleeping peacefully on a warm sunny windowsill, surrounded by pots of blooming red flowers.",  # noqa: E501
            "- User Prompt: A busy city street -> Enhanced: A bustling city street scene at dusk, featuring glowing street lamps, a diverse crowd of people in colorful clothing, and a double-decker bus passing by towering glass skyscrapers.",  # noqa: E501
            "Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:",
            "User Prompt: ",
        ],
    ) -> Union[SanaPipelineOutput, 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 20):
                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 4.5):
                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
                `guidance_scale` is defined as `w` of equation 2. of [Imagen
                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
                usually at the expense of lower image quality.
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            height (`int`, *optional*, defaults to self.unet.config.sample_size):
                The height in pixels of the generated image.
            width (`int`, *optional*, defaults to self.unet.config.sample_size):
                The width in pixels of the generated image.
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
                [`schedulers.DDIMScheduler`], will be ignored for others.
            generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
                One or a list of [numpy generator(s)](https://pytorch.org/docs/stable/generated/torch.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 PixArt-Sigma this negative prompt should be "". If not
                provided, negative_prompt_embeds will be generated from `negative_prompt` input argument.
            negative_prompt_attention_mask (`ms.Tensor`, *optional*):
                Pre-generated attention mask for negative text embeddings.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generate 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.
            attention_kwargs:
                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
                `self.processor` in
                [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
            clean_caption (`bool`, *optional*, defaults to `True`):
                Whether or not to clean the caption before creating embeddings. Requires `beautifulsoup4` and `ftfy` to
                be installed. If the dependencies are not installed, the embeddings will be created from the raw
                prompt.
            use_resolution_binning (`bool` defaults to `True`):
                If set to `True`, the requested height and width are first mapped to the closest resolutions using
                `ASPECT_RATIO_1024_BIN`. After the produced latents are decoded into images, they are resized back to
                the requested resolution. Useful for generating non-square images.
            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.
            max_sequence_length (`int` defaults to `300`):
                Maximum sequence length to use with the `prompt`.
            complex_human_instruction (`List[str]`, *optional*):
                Instructions for complex human attention:
                https://github.com/NVlabs/Sana/blob/main/configs/sana_app_config/Sana_1600M_app.yaml#L55.

        Examples:

        Returns:
            [`~pipelines.sana.pipeline_output.SanaPipelineOutput`] or `tuple`:
                If `return_dict` is `True`, [`~pipelines.sana.pipeline_output.SanaPipelineOutput`] 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

        # 1. Check inputs. Raise error if not correct
        if use_resolution_binning:
            if self.transformer.config.sample_size == 64:
                aspect_ratio_bin = ASPECT_RATIO_2048_BIN
            elif self.transformer.config.sample_size == 32:
                aspect_ratio_bin = ASPECT_RATIO_1024_BIN
            elif self.transformer.config.sample_size == 16:
                aspect_ratio_bin = ASPECT_RATIO_512_BIN
            else:
                raise ValueError("Invalid sample size")
            orig_height, orig_width = height, width
            height, width = self.image_processor.classify_height_width_bin(height, width, ratios=aspect_ratio_bin)

        self.check_inputs(
            prompt,
            height,
            width,
            callback_on_step_end_tensor_inputs,
            negative_prompt,
            prompt_embeds,
            negative_prompt_embeds,
            prompt_attention_mask,
            negative_prompt_attention_mask,
        )

        self._guidance_scale = guidance_scale
        self._attention_kwargs = attention_kwargs
        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]

        lora_scale = self.attention_kwargs.get("scale", None) if self.attention_kwargs is not None else None

        # 3. Encode input prompt
        (
            prompt_embeds,
            prompt_attention_mask,
            negative_prompt_embeds,
            negative_prompt_attention_mask,
        ) = self.encode_prompt(
            prompt,
            self.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,
            complex_human_instruction=complex_human_instruction,
            lora_scale=lora_scale,
        )
        if self.do_classifier_free_guidance:
            prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)
            prompt_attention_mask = ops.cat([negative_prompt_attention_mask, prompt_attention_mask], axis=0)

        # 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,
            ms.float32,
            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)

        # 7.0 lora_scale outside transformer
        if lora_scale is not None:
            # weight the lora layers by setting `lora_scale` for each PEFT layer
            scale_lora_layers(self.transformer, lora_scale)

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

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

                latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
                latent_model_input = latent_model_input.to(prompt_embeds.dtype)

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

                # predict noise model_output
                noise_pred = self.transformer(
                    latent_model_input,
                    encoder_hidden_states=prompt_embeds,
                    encoder_attention_mask=prompt_attention_mask,
                    timestep=timestep,
                    return_dict=False,
                    attention_kwargs=self.attention_kwargs,
                )[0]
                noise_pred = noise_pred.float()

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

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

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

                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)

                # call the callback, if provided
                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                    progress_bar.update()

        if lora_scale is not None:
            # remove `lora_scale` from each PEFT layer
            unscale_lora_layers(self.transformer, lora_scale)

        if output_type == "latent":
            image = latents
        else:
            latents = latents.to(self.vae.dtype)
            image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
            if use_resolution_binning:
                image = self.image_processor.resize_and_crop_tensor(image, orig_width, orig_height)

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

        if not return_dict:
            return (image,)

        return SanaPipelineOutput(images=image)

mindone.diffusers.SanaPipeline.__call__(prompt=None, negative_prompt='', num_inference_steps=20, timesteps=None, sigmas=None, guidance_scale=4.5, num_images_per_prompt=1, height=1024, width=1024, eta=0.0, generator=None, latents=None, prompt_embeds=None, prompt_attention_mask=None, negative_prompt_embeds=None, negative_prompt_attention_mask=None, output_type='pil', return_dict=False, clean_caption=True, use_resolution_binning=True, attention_kwargs=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], max_sequence_length=300, complex_human_instruction=["Given a user prompt, generate an 'Enhanced prompt' that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:", '- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.', '- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.', 'Here are examples of how to transform or refine prompts:', '- User Prompt: A cat sleeping -> Enhanced: A small, fluffy white cat curled up in a round shape, sleeping peacefully on a warm sunny windowsill, surrounded by pots of blooming red flowers.', '- User Prompt: A busy city street -> Enhanced: A bustling city street scene at dusk, featuring glowing street lamps, a diverse crowd of people in colorful clothing, and a double-decker bus passing by towering glass skyscrapers.', 'Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:', 'User Prompt: '])

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: ''
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 20 DEFAULT: 20
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 4.5 DEFAULT: 4.5
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: 1024
width	The width in pixels of the generated image. TYPE: `int`, *optional*, defaults to self.unet.config.sample_size DEFAULT: 1024
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 numpy 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 PixArt-Sigma this negative prompt should be "". If not provided, negative_prompt_embeds will be generated from negative_prompt input argument. TYPE: `ms.Tensor`, *optional* DEFAULT: None
negative_prompt_attention_mask	Pre-generated attention mask for negative text embeddings. TYPE: `ms.Tensor`, *optional* DEFAULT: None
output_type	The output format of the generate 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
attention_kwargs	A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.models.attention_processor. TYPE: Optional[Dict[str, Any]] DEFAULT: None
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
use_resolution_binning	If set to True, the requested height and width are first mapped to the closest resolutions using ASPECT_RATIO_1024_BIN. After the produced latents are decoded into images, they are resized back to the requested resolution. Useful for generating non-square images. TYPE: `bool` defaults to `True` DEFAULT: True
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* DEFAULT: None
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* DEFAULT: ['latents']
max_sequence_length	Maximum sequence length to use with the prompt. TYPE: `int` defaults to `300` DEFAULT: 300
complex_human_instruction	Instructions for complex human attention: https://github.com/NVlabs/Sana/blob/main/configs/sana_app_config/Sana_1600M_app.yaml#L55. TYPE: `List[str]`, *optional* DEFAULT: ["Given a user prompt, generate an 'Enhanced prompt' that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:", '- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.', '- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.', 'Here are examples of how to transform or refine prompts:', '- User Prompt: A cat sleeping -> Enhanced: A small, fluffy white cat curled up in a round shape, sleeping peacefully on a warm sunny windowsill, surrounded by pots of blooming red flowers.', '- User Prompt: A busy city street -> Enhanced: A bustling city street scene at dusk, featuring glowing street lamps, a diverse crowd of people in colorful clothing, and a double-decker bus passing by towering glass skyscrapers.', 'Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:', 'User Prompt: ']

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

Source code in mindone/diffusers/pipelines/sana/pipeline_sana.py

def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    negative_prompt: str = "",
    num_inference_steps: int = 20,
    timesteps: List[int] = None,
    sigmas: List[float] = None,
    guidance_scale: float = 4.5,
    num_images_per_prompt: Optional[int] = 1,
    height: int = 1024,
    width: int = 1024,
    eta: float = 0.0,
    generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
    latents: Optional[ms.Tensor] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    output_type: Optional[str] = "pil",
    return_dict: bool = False,
    clean_caption: bool = True,
    use_resolution_binning: bool = True,
    attention_kwargs: Optional[Dict[str, Any]] = None,
    callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    max_sequence_length: int = 300,
    complex_human_instruction: List[str] = [
        "Given a user prompt, generate an 'Enhanced prompt' that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:",  # noqa: E501
        "- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.",  # noqa: E501
        "- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.",
        "Here are examples of how to transform or refine prompts:",
        "- User Prompt: A cat sleeping -> Enhanced: A small, fluffy white cat curled up in a round shape, sleeping peacefully on a warm sunny windowsill, surrounded by pots of blooming red flowers.",  # noqa: E501
        "- User Prompt: A busy city street -> Enhanced: A bustling city street scene at dusk, featuring glowing street lamps, a diverse crowd of people in colorful clothing, and a double-decker bus passing by towering glass skyscrapers.",  # noqa: E501
        "Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:",
        "User Prompt: ",
    ],
) -> Union[SanaPipelineOutput, 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 20):
            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 4.5):
            Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
            `guidance_scale` is defined as `w` of equation 2. of [Imagen
            Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
            1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
            usually at the expense of lower image quality.
        num_images_per_prompt (`int`, *optional*, defaults to 1):
            The number of images to generate per prompt.
        height (`int`, *optional*, defaults to self.unet.config.sample_size):
            The height in pixels of the generated image.
        width (`int`, *optional*, defaults to self.unet.config.sample_size):
            The width in pixels of the generated image.
        eta (`float`, *optional*, defaults to 0.0):
            Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
            [`schedulers.DDIMScheduler`], will be ignored for others.
        generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
            One or a list of [numpy generator(s)](https://pytorch.org/docs/stable/generated/torch.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 PixArt-Sigma this negative prompt should be "". If not
            provided, negative_prompt_embeds will be generated from `negative_prompt` input argument.
        negative_prompt_attention_mask (`ms.Tensor`, *optional*):
            Pre-generated attention mask for negative text embeddings.
        output_type (`str`, *optional*, defaults to `"pil"`):
            The output format of the generate 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.
        attention_kwargs:
            A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
            `self.processor` in
            [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
        clean_caption (`bool`, *optional*, defaults to `True`):
            Whether or not to clean the caption before creating embeddings. Requires `beautifulsoup4` and `ftfy` to
            be installed. If the dependencies are not installed, the embeddings will be created from the raw
            prompt.
        use_resolution_binning (`bool` defaults to `True`):
            If set to `True`, the requested height and width are first mapped to the closest resolutions using
            `ASPECT_RATIO_1024_BIN`. After the produced latents are decoded into images, they are resized back to
            the requested resolution. Useful for generating non-square images.
        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.
        max_sequence_length (`int` defaults to `300`):
            Maximum sequence length to use with the `prompt`.
        complex_human_instruction (`List[str]`, *optional*):
            Instructions for complex human attention:
            https://github.com/NVlabs/Sana/blob/main/configs/sana_app_config/Sana_1600M_app.yaml#L55.

    Examples:

    Returns:
        [`~pipelines.sana.pipeline_output.SanaPipelineOutput`] or `tuple`:
            If `return_dict` is `True`, [`~pipelines.sana.pipeline_output.SanaPipelineOutput`] 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

    # 1. Check inputs. Raise error if not correct
    if use_resolution_binning:
        if self.transformer.config.sample_size == 64:
            aspect_ratio_bin = ASPECT_RATIO_2048_BIN
        elif self.transformer.config.sample_size == 32:
            aspect_ratio_bin = ASPECT_RATIO_1024_BIN
        elif self.transformer.config.sample_size == 16:
            aspect_ratio_bin = ASPECT_RATIO_512_BIN
        else:
            raise ValueError("Invalid sample size")
        orig_height, orig_width = height, width
        height, width = self.image_processor.classify_height_width_bin(height, width, ratios=aspect_ratio_bin)

    self.check_inputs(
        prompt,
        height,
        width,
        callback_on_step_end_tensor_inputs,
        negative_prompt,
        prompt_embeds,
        negative_prompt_embeds,
        prompt_attention_mask,
        negative_prompt_attention_mask,
    )

    self._guidance_scale = guidance_scale
    self._attention_kwargs = attention_kwargs
    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]

    lora_scale = self.attention_kwargs.get("scale", None) if self.attention_kwargs is not None else None

    # 3. Encode input prompt
    (
        prompt_embeds,
        prompt_attention_mask,
        negative_prompt_embeds,
        negative_prompt_attention_mask,
    ) = self.encode_prompt(
        prompt,
        self.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,
        complex_human_instruction=complex_human_instruction,
        lora_scale=lora_scale,
    )
    if self.do_classifier_free_guidance:
        prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)
        prompt_attention_mask = ops.cat([negative_prompt_attention_mask, prompt_attention_mask], axis=0)

    # 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,
        ms.float32,
        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)

    # 7.0 lora_scale outside transformer
    if lora_scale is not None:
        # weight the lora layers by setting `lora_scale` for each PEFT layer
        scale_lora_layers(self.transformer, lora_scale)

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

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

            latent_model_input = ops.cat([latents] * 2) if self.do_classifier_free_guidance else latents
            latent_model_input = latent_model_input.to(prompt_embeds.dtype)

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

            # predict noise model_output
            noise_pred = self.transformer(
                latent_model_input,
                encoder_hidden_states=prompt_embeds,
                encoder_attention_mask=prompt_attention_mask,
                timestep=timestep,
                return_dict=False,
                attention_kwargs=self.attention_kwargs,
            )[0]
            noise_pred = noise_pred.float()

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

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

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

            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)

            # call the callback, if provided
            if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
                progress_bar.update()

    if lora_scale is not None:
        # remove `lora_scale` from each PEFT layer
        unscale_lora_layers(self.transformer, lora_scale)

    if output_type == "latent":
        image = latents
    else:
        latents = latents.to(self.vae.dtype)
        image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
        if use_resolution_binning:
            image = self.image_processor.resize_and_crop_tensor(image, orig_width, orig_height)

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

    if not return_dict:
        return (image,)

    return SanaPipelineOutput(images=image)

mindone.diffusers.SanaPipeline.encode_prompt(prompt, do_classifier_free_guidance=True, negative_prompt='', num_images_per_prompt=1, prompt_embeds=None, negative_prompt_embeds=None, prompt_attention_mask=None, negative_prompt_attention_mask=None, clean_caption=False, max_sequence_length=300, complex_human_instruction=None, lora_scale=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 image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1). For PixArt-Alpha, this should be "". TYPE: `str` or `List[str]`, *optional* DEFAULT: ''
do_classifier_free_guidance	whether to use classifier free guidance or not TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
num_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 Sana, 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 300 DEFAULT: 300
complex_human_instruction	If complex_human_instruction is not empty, the function will use the complex Human instruction for the prompt. TYPE: `list[str]`, defaults to `complex_human_instruction` DEFAULT: None

Source code in mindone/diffusers/pipelines/sana/pipeline_sana.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,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    clean_caption: bool = False,
    max_sequence_length: int = 300,
    complex_human_instruction: Optional[List[str]] = None,
    lora_scale: Optional[float] = 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 image generation. If not defined, one has to pass `negative_prompt_embeds`
            instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`). For
            PixArt-Alpha, this should be "".
        do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
            whether to use classifier free guidance or not
        num_images_per_prompt (`int`, *optional*, defaults to 1):
            number of images that should be generated per prompt
        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 Sana, it's should be the embeddings of the "" string.
        clean_caption (`bool`, defaults to `False`):
            If `True`, the function will preprocess and clean the provided caption before encoding.
        max_sequence_length (`int`, defaults to 300): Maximum sequence length to use for the prompt.
        complex_human_instruction (`list[str]`, defaults to `complex_human_instruction`):
            If `complex_human_instruction` is not empty, the function will use the complex Human instruction for
            the prompt.
    """
    # set lora scale so that monkey patched LoRA
    # function of text encoder can correctly access it
    if lora_scale is not None and isinstance(self, SanaLoraLoaderMixin):
        self._lora_scale = lora_scale

        # dynamically adjust the LoRA scale
        if self.text_encoder is not None:
            scale_lora_layers(self.text_encoder, lora_scale)

    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]

    self.tokenizer.padding_side = "right"

    # See Section 3.1. of the paper.
    max_length = max_sequence_length
    select_index = [0] + list(range(-max_length + 1, 0))

    if prompt_embeds is None:
        prompt = self._text_preprocessing(prompt, clean_caption=clean_caption)

        # prepare complex human instruction
        if not complex_human_instruction:
            max_length_all = max_length
        else:
            chi_prompt = "\n".join(complex_human_instruction)
            prompt = [chi_prompt + p for p in prompt]
            num_chi_prompt_tokens = len(self.tokenizer.encode(chi_prompt))
            max_length_all = num_chi_prompt_tokens + max_length - 2

        text_inputs = self.tokenizer(
            prompt,
            padding="max_length",
            max_length=max_length_all,
            truncation=True,
            add_special_tokens=True,
            return_tensors="np",
        )
        text_input_ids = ms.Tensor.from_numpy(text_inputs.input_ids)

        prompt_attention_mask = ms.Tensor.from_numpy(text_inputs.attention_mask)

        prompt_embeds = self.text_encoder(text_input_ids, attention_mask=prompt_attention_mask)
        prompt_embeds = prompt_embeds[0][:, select_index]
        prompt_attention_mask = prompt_attention_mask[:, select_index]

    if self.transformer is not None:
        dtype = self.transformer.dtype
    elif self.text_encoder is not None:
        dtype = self.text_encoder.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_attention_mask = prompt_attention_mask.view(bs_embed, -1)
    prompt_attention_mask = prompt_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",
        )
        negative_prompt_attention_mask = ms.Tensor.from_numpy(uncond_input.attention_mask)

        negative_prompt_embeds = self.text_encoder(
            ms.Tensor.from_numpy(uncond_input.input_ids),
            attention_mask=negative_prompt_attention_mask,
        )
        negative_prompt_embeds = negative_prompt_embeds[0]

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

        negative_prompt_embeds = negative_prompt_embeds.to(dtype=dtype)

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

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

    if self.text_encoder is not None:
        if isinstance(self, SanaLoraLoaderMixin):
            # Retrieve the original scale by scaling back the LoRA layers
            unscale_lora_layers(self.text_encoder, lora_scale)

    return prompt_embeds, prompt_attention_mask, negative_prompt_embeds, negative_prompt_attention_mask

mindone.diffusers.SanaPAGPipeline

Bases: DiffusionPipeline, PAGMixin

Pipeline for text-to-image generation using Sana. This pipeline supports the use of Perturbed Attention Guidance (PAG).

Source code in mindone/diffusers/pipelines/pag/pipeline_pag_sana.py

class SanaPAGPipeline(DiffusionPipeline, PAGMixin):
    r"""
    Pipeline for text-to-image generation using [Sana](https://huggingface.co/papers/2410.10629). This pipeline
    supports the use of [Perturbed Attention Guidance
    (PAG)](https://huggingface.co/docs/diffusers/main/en/using-diffusers/pag).
    """

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

    model_cpu_offload_seq = "text_encoder->transformer->vae"
    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]

    def __init__(
        self,
        tokenizer: AutoTokenizer,
        text_encoder: MSPreTrainedModel,
        vae: AutoencoderDC,
        transformer: SanaTransformer2DModel,
        scheduler: FlowMatchEulerDiscreteScheduler,
        pag_applied_layers: Union[str, List[str]] = "transformer_blocks.0",
    ):
        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.encoder_block_out_channels) - 1)
        self.image_processor = PixArtImageProcessor(vae_scale_factor=self.vae_scale_factor)

        self.set_pag_applied_layers(
            pag_applied_layers,
            pag_attn_processors=(PAGCFGSanaLinearAttnProcessor2_0(), PAGIdentitySanaLinearAttnProcessor2_0()),
        )

    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,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        clean_caption: bool = False,
        max_sequence_length: int = 300,
        complex_human_instruction: Optional[List[str]] = 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 image generation. If not defined, one has to pass `negative_prompt_embeds`
                instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`). For
                PixArt-Alpha, this should be "".
            do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
                whether to use classifier free guidance or not
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                number of images that should be generated per prompt
            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 Sana, it's should be the embeddings of the "" string.
            clean_caption (`bool`, defaults to `False`):
                If `True`, the function will preprocess and clean the provided caption before encoding.
            max_sequence_length (`int`, defaults to 300): Maximum sequence length to use for the prompt.
            complex_human_instruction (`list[str]`, defaults to `complex_human_instruction`):
                If `complex_human_instruction` is not empty, the function will use the complex Human instruction for
                the prompt.
        """
        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]

        self.tokenizer.padding_side = "right"

        # See Section 3.1. of the paper.
        max_length = max_sequence_length
        select_index = [0] + list(range(-max_length + 1, 0))

        if prompt_embeds is None:
            prompt = self._text_preprocessing(prompt, clean_caption=clean_caption)

            # prepare complex human instruction
            if not complex_human_instruction:
                max_length_all = max_length
            else:
                chi_prompt = "\n".join(complex_human_instruction)
                prompt = [chi_prompt + p for p in prompt]
                num_chi_prompt_tokens = len(self.tokenizer.encode(chi_prompt))
                max_length_all = num_chi_prompt_tokens + max_length - 2

            text_inputs = self.tokenizer(
                prompt,
                padding="max_length",
                max_length=max_length_all,
                truncation=True,
                add_special_tokens=True,
                return_tensors="np",
            )
            text_input_ids = ms.Tensor.from_numpy(text_inputs.input_ids)

            prompt_attention_mask = ms.Tensor.from_numpy(text_inputs.attention_mask)

            prompt_embeds = self.text_encoder(text_input_ids, attention_mask=prompt_attention_mask)
            prompt_embeds = prompt_embeds[0][:, select_index]
            prompt_attention_mask = prompt_attention_mask[:, select_index]

        if self.transformer is not None:
            dtype = self.transformer.dtype
        elif self.text_encoder is not None:
            dtype = self.text_encoder.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_attention_mask = prompt_attention_mask.view(bs_embed, -1)
        prompt_attention_mask = prompt_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",
            )
            negative_prompt_attention_mask = ms.Tensor.from_numpy(uncond_input.attention_mask)

            negative_prompt_embeds = self.text_encoder(
                ms.Tensor.from_numpy(uncond_input.input_ids), attention_mask=negative_prompt_attention_mask
            )
            negative_prompt_embeds = negative_prompt_embeds[0]

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

            negative_prompt_embeds = negative_prompt_embeds.to(dtype=dtype)

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

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

        return prompt_embeds, prompt_attention_mask, negative_prompt_embeds, negative_prompt_attention_mask

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

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

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

    # Copied from diffusers.pipelines.sana.pipeline_sana.SanaPipeline.check_inputs
    def check_inputs(
        self,
        prompt,
        height,
        width,
        callback_on_step_end_tensor_inputs=None,
        negative_prompt=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        prompt_attention_mask=None,
        negative_prompt_attention_mask=None,
    ):
        if height % 32 != 0 or width % 32 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 32 but are {height} and {width}.")

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

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

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

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

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

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

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

    # Copied from diffusers.pipelines.sana.pipeline_sana.SanaPipeline._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.sana.pipeline_sana.SanaPipeline._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.sana.pipeline_sana.SanaPipeline.prepare_latents
    def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, generator, latents=None):
        if latents is not None:
            return latents.to(dtype=dtype)

        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."
            )

        latents = randn_tensor(shape, generator=generator, dtype=dtype)
        return latents

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

    @property
    def do_classifier_free_guidance(self):
        return self._guidance_scale > 1.0

    @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 = 20,
        timesteps: List[int] = None,
        sigmas: List[float] = None,
        guidance_scale: float = 4.5,
        num_images_per_prompt: Optional[int] = 1,
        height: int = 1024,
        width: int = 1024,
        eta: float = 0.0,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = False,
        clean_caption: bool = True,
        use_resolution_binning: bool = True,
        callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
        max_sequence_length: int = 300,
        complex_human_instruction: List[str] = [
            "Given a user prompt, generate an 'Enhanced prompt' that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:",  # noqa: E501
            "- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.",  # noqa: E501
            "- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.",
            "Here are examples of how to transform or refine prompts:",
            "- User Prompt: A cat sleeping -> Enhanced: A small, fluffy white cat curled up in a round shape, sleeping peacefully on a warm sunny windowsill, surrounded by pots of blooming red flowers.",  # noqa: E501
            "- User Prompt: A busy city street -> Enhanced: A bustling city street scene at dusk, featuring glowing street lamps, a diverse crowd of people in colorful clothing, and a double-decker bus passing by towering glass skyscrapers.",  # noqa: E501
            "Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:",
            "User Prompt: ",
        ],
        pag_scale: float = 3.0,
        pag_adaptive_scale: float = 0.0,
    ) -> 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 20):
                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 4.5):
                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
                `guidance_scale` is defined as `w` of equation 2. of [Imagen
                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
                usually at the expense of lower image quality.
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            height (`int`, *optional*, defaults to self.unet.config.sample_size):
                The height in pixels of the generated image.
            width (`int`, *optional*, defaults to self.unet.config.sample_size):
                The width in pixels of the generated image.
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
                [`schedulers.DDIMScheduler`], will be ignored for others.
            generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
                One or a list of [numpy generator(s)](https://pytorch.org/docs/stable/generated/torch.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 PixArt-Sigma this negative prompt should be "". If not
                provided, negative_prompt_embeds will be generated from `negative_prompt` input argument.
            negative_prompt_attention_mask (`ms.Tensor`, *optional*):
                Pre-generated attention mask for negative text embeddings.
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generate 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.
            use_resolution_binning (`bool` defaults to `True`):
                If set to `True`, the requested height and width are first mapped to the closest resolutions using
                `ASPECT_RATIO_1024_BIN`. After the produced latents are decoded into images, they are resized back to
                the requested resolution. Useful for generating non-square images.
            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.
            max_sequence_length (`int` defaults to 300): Maximum sequence length to use with the `prompt`.
            complex_human_instruction (`List[str]`, *optional*):
                Instructions for complex human attention:
                https://github.com/NVlabs/Sana/blob/main/configs/sana_app_config/Sana_1600M_app.yaml#L55.
            pag_scale (`float`, *optional*, defaults to 3.0):
                The scale factor for the perturbed attention guidance. If it is set to 0.0, the perturbed attention
                guidance will not be used.
            pag_adaptive_scale (`float`, *optional*, defaults to 0.0):
                The adaptive scale factor for the perturbed attention guidance. If it is set to 0.0, `pag_scale` is
                used.

        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
        """

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

        if use_resolution_binning:
            if self.transformer.config.sample_size == 64:
                aspect_ratio_bin = ASPECT_RATIO_2048_BIN
            elif self.transformer.config.sample_size == 32:
                aspect_ratio_bin = ASPECT_RATIO_1024_BIN
            elif self.transformer.config.sample_size == 16:
                aspect_ratio_bin = ASPECT_RATIO_512_BIN
            else:
                raise ValueError("Invalid sample size")
            orig_height, orig_width = height, width
            height, width = self.image_processor.classify_height_width_bin(height, width, ratios=aspect_ratio_bin)

        self.check_inputs(
            prompt,
            height,
            width,
            callback_on_step_end_tensor_inputs,
            negative_prompt,
            prompt_embeds,
            negative_prompt_embeds,
            prompt_attention_mask,
            negative_prompt_attention_mask,
        )

        self._pag_scale = pag_scale
        self._pag_adaptive_scale = pag_adaptive_scale
        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]

        # 3. Encode input prompt
        (
            prompt_embeds,
            prompt_attention_mask,
            negative_prompt_embeds,
            negative_prompt_attention_mask,
        ) = self.encode_prompt(
            prompt,
            self.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,
            complex_human_instruction=complex_human_instruction,
        )

        if self.do_perturbed_attention_guidance:
            prompt_embeds = self._prepare_perturbed_attention_guidance(
                prompt_embeds, negative_prompt_embeds, self.do_classifier_free_guidance
            )
            prompt_attention_mask = self._prepare_perturbed_attention_guidance(
                prompt_attention_mask, negative_prompt_attention_mask, self.do_classifier_free_guidance
            )
        elif self.do_classifier_free_guidance:
            prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)
            prompt_attention_mask = ops.cat([negative_prompt_attention_mask, prompt_attention_mask], axis=0)

        # 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,
            ms.float32,
            generator,
            latents,
        )
        if self.do_perturbed_attention_guidance:
            original_attn_proc = self.transformer.attn_processors
            self._set_pag_attn_processor(
                pag_applied_layers=self.pag_applied_layers,
                do_classifier_free_guidance=self.do_classifier_free_guidance,
            )

        # 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)
        self._num_timesteps = len(timesteps)

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

                # expand the latents if we are doing classifier free guidance, perturbed-attention guidance, or both
                latent_model_input = ops.cat([latents] * (prompt_embeds.shape[0] // latents.shape[0]))
                latent_model_input = latent_model_input.to(prompt_embeds.dtype)

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

                # predict noise model_output
                noise_pred = self.transformer(
                    latent_model_input,
                    encoder_hidden_states=prompt_embeds,
                    encoder_attention_mask=prompt_attention_mask,
                    timestep=timestep,
                    return_dict=False,
                )[0]
                noise_pred = noise_pred.float()

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

                # compute previous image: x_t -> x_t-1
                latents_dtype = latents.dtype
                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 output_type == "latent":
            image = latents
        else:
            latents = latents.to(self.vae.dtype)
            image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
            if use_resolution_binning:
                image = self.image_processor.resize_and_crop_tensor(image, orig_width, orig_height)

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

        if self.do_perturbed_attention_guidance:
            self.transformer.set_attn_processor(original_attn_proc)

        if not return_dict:
            return (image,)

        return ImagePipelineOutput(images=image)

mindone.diffusers.SanaPAGPipeline.__call__(prompt=None, negative_prompt='', num_inference_steps=20, timesteps=None, sigmas=None, guidance_scale=4.5, num_images_per_prompt=1, height=1024, width=1024, eta=0.0, generator=None, latents=None, prompt_embeds=None, prompt_attention_mask=None, negative_prompt_embeds=None, negative_prompt_attention_mask=None, output_type='pil', return_dict=False, clean_caption=True, use_resolution_binning=True, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], max_sequence_length=300, complex_human_instruction=["Given a user prompt, generate an 'Enhanced prompt' that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:", '- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.', '- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.', 'Here are examples of how to transform or refine prompts:', '- User Prompt: A cat sleeping -> Enhanced: A small, fluffy white cat curled up in a round shape, sleeping peacefully on a warm sunny windowsill, surrounded by pots of blooming red flowers.', '- User Prompt: A busy city street -> Enhanced: A bustling city street scene at dusk, featuring glowing street lamps, a diverse crowd of people in colorful clothing, and a double-decker bus passing by towering glass skyscrapers.', 'Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:', 'User Prompt: '], pag_scale=3.0, pag_adaptive_scale=0.0)

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: ''
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 20 DEFAULT: 20
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 4.5 DEFAULT: 4.5
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: 1024
width	The width in pixels of the generated image. TYPE: `int`, *optional*, defaults to self.unet.config.sample_size DEFAULT: 1024
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 numpy 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 PixArt-Sigma this negative prompt should be "". If not provided, negative_prompt_embeds will be generated from negative_prompt input argument. TYPE: `ms.Tensor`, *optional* DEFAULT: None
negative_prompt_attention_mask	Pre-generated attention mask for negative text embeddings. TYPE: `ms.Tensor`, *optional* DEFAULT: None
output_type	The output format of the generate 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
use_resolution_binning	If set to True, the requested height and width are first mapped to the closest resolutions using ASPECT_RATIO_1024_BIN. After the produced latents are decoded into images, they are resized back to the requested resolution. Useful for generating non-square images. TYPE: `bool` defaults to `True` DEFAULT: True
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* DEFAULT: None
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* DEFAULT: ['latents']
max_sequence_length	Maximum sequence length to use with the prompt. TYPE: `int` defaults to 300 DEFAULT: 300
complex_human_instruction	Instructions for complex human attention: https://github.com/NVlabs/Sana/blob/main/configs/sana_app_config/Sana_1600M_app.yaml#L55. TYPE: `List[str]`, *optional* DEFAULT: ["Given a user prompt, generate an 'Enhanced prompt' that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:", '- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.', '- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.', 'Here are examples of how to transform or refine prompts:', '- User Prompt: A cat sleeping -> Enhanced: A small, fluffy white cat curled up in a round shape, sleeping peacefully on a warm sunny windowsill, surrounded by pots of blooming red flowers.', '- User Prompt: A busy city street -> Enhanced: A bustling city street scene at dusk, featuring glowing street lamps, a diverse crowd of people in colorful clothing, and a double-decker bus passing by towering glass skyscrapers.', 'Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:', 'User Prompt: ']
pag_scale	The scale factor for the perturbed attention guidance. If it is set to 0.0, the perturbed attention guidance will not be used. TYPE: `float`, *optional*, defaults to 3.0 DEFAULT: 3.0
pag_adaptive_scale	The adaptive scale factor for the perturbed attention guidance. If it is set to 0.0, pag_scale is used. TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

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/pag/pipeline_pag_sana.py

def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    negative_prompt: str = "",
    num_inference_steps: int = 20,
    timesteps: List[int] = None,
    sigmas: List[float] = None,
    guidance_scale: float = 4.5,
    num_images_per_prompt: Optional[int] = 1,
    height: int = 1024,
    width: int = 1024,
    eta: float = 0.0,
    generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
    latents: Optional[ms.Tensor] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    output_type: Optional[str] = "pil",
    return_dict: bool = False,
    clean_caption: bool = True,
    use_resolution_binning: bool = True,
    callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
    callback_on_step_end_tensor_inputs: List[str] = ["latents"],
    max_sequence_length: int = 300,
    complex_human_instruction: List[str] = [
        "Given a user prompt, generate an 'Enhanced prompt' that provides detailed visual descriptions suitable for image generation. Evaluate the level of detail in the user prompt:",  # noqa: E501
        "- If the prompt is simple, focus on adding specifics about colors, shapes, sizes, textures, and spatial relationships to create vivid and concrete scenes.",  # noqa: E501
        "- If the prompt is already detailed, refine and enhance the existing details slightly without overcomplicating.",
        "Here are examples of how to transform or refine prompts:",
        "- User Prompt: A cat sleeping -> Enhanced: A small, fluffy white cat curled up in a round shape, sleeping peacefully on a warm sunny windowsill, surrounded by pots of blooming red flowers.",  # noqa: E501
        "- User Prompt: A busy city street -> Enhanced: A bustling city street scene at dusk, featuring glowing street lamps, a diverse crowd of people in colorful clothing, and a double-decker bus passing by towering glass skyscrapers.",  # noqa: E501
        "Please generate only the enhanced description for the prompt below and avoid including any additional commentary or evaluations:",
        "User Prompt: ",
    ],
    pag_scale: float = 3.0,
    pag_adaptive_scale: float = 0.0,
) -> 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 20):
            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 4.5):
            Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
            `guidance_scale` is defined as `w` of equation 2. of [Imagen
            Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
            1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
            usually at the expense of lower image quality.
        num_images_per_prompt (`int`, *optional*, defaults to 1):
            The number of images to generate per prompt.
        height (`int`, *optional*, defaults to self.unet.config.sample_size):
            The height in pixels of the generated image.
        width (`int`, *optional*, defaults to self.unet.config.sample_size):
            The width in pixels of the generated image.
        eta (`float`, *optional*, defaults to 0.0):
            Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
            [`schedulers.DDIMScheduler`], will be ignored for others.
        generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
            One or a list of [numpy generator(s)](https://pytorch.org/docs/stable/generated/torch.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 PixArt-Sigma this negative prompt should be "". If not
            provided, negative_prompt_embeds will be generated from `negative_prompt` input argument.
        negative_prompt_attention_mask (`ms.Tensor`, *optional*):
            Pre-generated attention mask for negative text embeddings.
        output_type (`str`, *optional*, defaults to `"pil"`):
            The output format of the generate 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.
        use_resolution_binning (`bool` defaults to `True`):
            If set to `True`, the requested height and width are first mapped to the closest resolutions using
            `ASPECT_RATIO_1024_BIN`. After the produced latents are decoded into images, they are resized back to
            the requested resolution. Useful for generating non-square images.
        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.
        max_sequence_length (`int` defaults to 300): Maximum sequence length to use with the `prompt`.
        complex_human_instruction (`List[str]`, *optional*):
            Instructions for complex human attention:
            https://github.com/NVlabs/Sana/blob/main/configs/sana_app_config/Sana_1600M_app.yaml#L55.
        pag_scale (`float`, *optional*, defaults to 3.0):
            The scale factor for the perturbed attention guidance. If it is set to 0.0, the perturbed attention
            guidance will not be used.
        pag_adaptive_scale (`float`, *optional*, defaults to 0.0):
            The adaptive scale factor for the perturbed attention guidance. If it is set to 0.0, `pag_scale` is
            used.

    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
    """

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

    if use_resolution_binning:
        if self.transformer.config.sample_size == 64:
            aspect_ratio_bin = ASPECT_RATIO_2048_BIN
        elif self.transformer.config.sample_size == 32:
            aspect_ratio_bin = ASPECT_RATIO_1024_BIN
        elif self.transformer.config.sample_size == 16:
            aspect_ratio_bin = ASPECT_RATIO_512_BIN
        else:
            raise ValueError("Invalid sample size")
        orig_height, orig_width = height, width
        height, width = self.image_processor.classify_height_width_bin(height, width, ratios=aspect_ratio_bin)

    self.check_inputs(
        prompt,
        height,
        width,
        callback_on_step_end_tensor_inputs,
        negative_prompt,
        prompt_embeds,
        negative_prompt_embeds,
        prompt_attention_mask,
        negative_prompt_attention_mask,
    )

    self._pag_scale = pag_scale
    self._pag_adaptive_scale = pag_adaptive_scale
    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]

    # 3. Encode input prompt
    (
        prompt_embeds,
        prompt_attention_mask,
        negative_prompt_embeds,
        negative_prompt_attention_mask,
    ) = self.encode_prompt(
        prompt,
        self.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,
        complex_human_instruction=complex_human_instruction,
    )

    if self.do_perturbed_attention_guidance:
        prompt_embeds = self._prepare_perturbed_attention_guidance(
            prompt_embeds, negative_prompt_embeds, self.do_classifier_free_guidance
        )
        prompt_attention_mask = self._prepare_perturbed_attention_guidance(
            prompt_attention_mask, negative_prompt_attention_mask, self.do_classifier_free_guidance
        )
    elif self.do_classifier_free_guidance:
        prompt_embeds = ops.cat([negative_prompt_embeds, prompt_embeds], axis=0)
        prompt_attention_mask = ops.cat([negative_prompt_attention_mask, prompt_attention_mask], axis=0)

    # 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,
        ms.float32,
        generator,
        latents,
    )
    if self.do_perturbed_attention_guidance:
        original_attn_proc = self.transformer.attn_processors
        self._set_pag_attn_processor(
            pag_applied_layers=self.pag_applied_layers,
            do_classifier_free_guidance=self.do_classifier_free_guidance,
        )

    # 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)
    self._num_timesteps = len(timesteps)

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

            # expand the latents if we are doing classifier free guidance, perturbed-attention guidance, or both
            latent_model_input = ops.cat([latents] * (prompt_embeds.shape[0] // latents.shape[0]))
            latent_model_input = latent_model_input.to(prompt_embeds.dtype)

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

            # predict noise model_output
            noise_pred = self.transformer(
                latent_model_input,
                encoder_hidden_states=prompt_embeds,
                encoder_attention_mask=prompt_attention_mask,
                timestep=timestep,
                return_dict=False,
            )[0]
            noise_pred = noise_pred.float()

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

            # compute previous image: x_t -> x_t-1
            latents_dtype = latents.dtype
            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 output_type == "latent":
        image = latents
    else:
        latents = latents.to(self.vae.dtype)
        image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
        if use_resolution_binning:
            image = self.image_processor.resize_and_crop_tensor(image, orig_width, orig_height)

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

    if self.do_perturbed_attention_guidance:
        self.transformer.set_attn_processor(original_attn_proc)

    if not return_dict:
        return (image,)

    return ImagePipelineOutput(images=image)

mindone.diffusers.SanaPAGPipeline.encode_prompt(prompt, do_classifier_free_guidance=True, negative_prompt='', num_images_per_prompt=1, prompt_embeds=None, negative_prompt_embeds=None, prompt_attention_mask=None, negative_prompt_attention_mask=None, clean_caption=False, max_sequence_length=300, complex_human_instruction=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 image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1). For PixArt-Alpha, this should be "". TYPE: `str` or `List[str]`, *optional* DEFAULT: ''
do_classifier_free_guidance	whether to use classifier free guidance or not TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
num_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 Sana, 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 300 DEFAULT: 300
complex_human_instruction	If complex_human_instruction is not empty, the function will use the complex Human instruction for the prompt. TYPE: `list[str]`, defaults to `complex_human_instruction` DEFAULT: None

Source code in mindone/diffusers/pipelines/pag/pipeline_pag_sana.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,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    clean_caption: bool = False,
    max_sequence_length: int = 300,
    complex_human_instruction: Optional[List[str]] = 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 image generation. If not defined, one has to pass `negative_prompt_embeds`
            instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`). For
            PixArt-Alpha, this should be "".
        do_classifier_free_guidance (`bool`, *optional*, defaults to `True`):
            whether to use classifier free guidance or not
        num_images_per_prompt (`int`, *optional*, defaults to 1):
            number of images that should be generated per prompt
        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 Sana, it's should be the embeddings of the "" string.
        clean_caption (`bool`, defaults to `False`):
            If `True`, the function will preprocess and clean the provided caption before encoding.
        max_sequence_length (`int`, defaults to 300): Maximum sequence length to use for the prompt.
        complex_human_instruction (`list[str]`, defaults to `complex_human_instruction`):
            If `complex_human_instruction` is not empty, the function will use the complex Human instruction for
            the prompt.
    """
    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]

    self.tokenizer.padding_side = "right"

    # See Section 3.1. of the paper.
    max_length = max_sequence_length
    select_index = [0] + list(range(-max_length + 1, 0))

    if prompt_embeds is None:
        prompt = self._text_preprocessing(prompt, clean_caption=clean_caption)

        # prepare complex human instruction
        if not complex_human_instruction:
            max_length_all = max_length
        else:
            chi_prompt = "\n".join(complex_human_instruction)
            prompt = [chi_prompt + p for p in prompt]
            num_chi_prompt_tokens = len(self.tokenizer.encode(chi_prompt))
            max_length_all = num_chi_prompt_tokens + max_length - 2

        text_inputs = self.tokenizer(
            prompt,
            padding="max_length",
            max_length=max_length_all,
            truncation=True,
            add_special_tokens=True,
            return_tensors="np",
        )
        text_input_ids = ms.Tensor.from_numpy(text_inputs.input_ids)

        prompt_attention_mask = ms.Tensor.from_numpy(text_inputs.attention_mask)

        prompt_embeds = self.text_encoder(text_input_ids, attention_mask=prompt_attention_mask)
        prompt_embeds = prompt_embeds[0][:, select_index]
        prompt_attention_mask = prompt_attention_mask[:, select_index]

    if self.transformer is not None:
        dtype = self.transformer.dtype
    elif self.text_encoder is not None:
        dtype = self.text_encoder.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_attention_mask = prompt_attention_mask.view(bs_embed, -1)
    prompt_attention_mask = prompt_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",
        )
        negative_prompt_attention_mask = ms.Tensor.from_numpy(uncond_input.attention_mask)

        negative_prompt_embeds = self.text_encoder(
            ms.Tensor.from_numpy(uncond_input.input_ids), attention_mask=negative_prompt_attention_mask
        )
        negative_prompt_embeds = negative_prompt_embeds[0]

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

        negative_prompt_embeds = negative_prompt_embeds.to(dtype=dtype)

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

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

    return prompt_embeds, prompt_attention_mask, negative_prompt_embeds, negative_prompt_attention_mask

mindone.diffusers.pipelines.sana.pipeline_output.SanaPipelineOutput dataclass

Bases: BaseOutput

Output class for Sana pipelines.

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

@dataclass
class SanaPipelineOutput(BaseOutput):
    """
    Output class for Sana pipelines.

    Args:
        images (`List[PIL.Image.Image]` or `np.ndarray`)
            List of denoised PIL images of length `batch_size` or numpy array of shape `(batch_size, height, width,
            num_channels)`. PIL images or numpy array present the denoised images of the diffusion pipeline.
    """

    images: Union[List[PIL.Image.Image], np.ndarray]