Chroma

Chroma is a text to image generation model based on Flux.

Original model checkpoints for Chroma can be found here.

Tip

Chroma can use all the same optimizations as Flux.

Inference

The Diffusers version of Chroma is based on the unlocked-v37 version of the original model, which is available in the Chroma repository.

import mindspore
import numpy as np
from mindone.diffusers import ChromaPipeline

pipe = ChromaPipeline.from_pretrained("lodestones/Chroma", mindspore_dtype=mindspore.bfloat16)

prompt = [
    "A high-fashion close-up portrait of a blonde woman in clear sunglasses. The image uses a bold teal and red color split for dramatic lighting. The background is a simple teal-green. The photo is sharp and well-composed, and is designed for viewing with anaglyph 3D glasses for optimal effect. It looks professionally done."
]
negative_prompt =  ["low quality, ugly, unfinished, out of focus, deformed, disfigure, blurry, smudged, restricted palette, flat colors"]

image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    generator=np.random.Generator(np.random.PCG64(seed=42)),
    num_inference_steps=40,
    guidance_scale=3.0,
    num_images_per_prompt=1,
)[0][0]
image.save("chroma.png")

Loading from a single file

To use updated model checkpoints that are not in the Diffusers format, you can use the ChromaTransformer2DModel class to load the model from a single file in the original format. This is also useful when trying to load finetunes or quantized versions of the models that have been published by the community.

The following example demonstrates how to run Chroma from a single file.

Then run the following example

import mindspore
import numpy as np
from mindone.diffusers import ChromaTransformer2DModel, ChromaPipeline

model_id = "lodestones/Chroma"
dtype = mindspore.bfloat16

transformer = ChromaTransformer2DModel.from_single_file("https://huggingface.co/lodestones/Chroma/blob/main/chroma-unlocked-v37.safetensors", mindspore_dtype=dtype)

pipe = ChromaPipeline.from_pretrained(model_id, transformer=transformer, mindspore_dtype=dtype)

prompt = [
    "A high-fashion close-up portrait of a blonde woman in clear sunglasses. The image uses a bold teal and red color split for dramatic lighting. The background is a simple teal-green. The photo is sharp and well-composed, and is designed for viewing with anaglyph 3D glasses for optimal effect. It looks professionally done."
]
negative_prompt =  ["low quality, ugly, unfinished, out of focus, deformed, disfigure, blurry, smudged, restricted palette, flat colors"]

image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    generator=np.random.Generator(np.random.PCG64(seed=42)),
    num_inference_steps=40,
    guidance_scale=3.0,
)[0][0]

image.save("chroma-single-file.png")

mindone.diffusers.ChromaPipeline

Bases: DiffusionPipeline, FluxLoraLoaderMixin, FromSingleFileMixin, TextualInversionLoaderMixin, FluxIPAdapterMixin

The Chroma pipeline for text-to-image generation.

Reference: https://huggingface.co/lodestones/Chroma/

PARAMETER	DESCRIPTION
transformer	Conditional Transformer (MMDiT) architecture to denoise the encoded image latents. TYPE: [`ChromaTransformer2DModel`]
scheduler	A scheduler to be used in combination with transformer to denoise the encoded image latents. TYPE: [`FlowMatchEulerDiscreteScheduler`]
vae	Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representation TYPE: [`AutoencoderKL`]
text_encoder	T5, specifically the google/t5-v1_1-xxl variant. TYPE: [`T5EncoderModel`]
tokenizer	Second Tokenizer of class T5TokenizerFast. TYPE: `T5TokenizerFast`

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma.py

class ChromaPipeline(
    DiffusionPipeline,
    FluxLoraLoaderMixin,
    FromSingleFileMixin,
    TextualInversionLoaderMixin,
    FluxIPAdapterMixin,
):
    r"""
    The Chroma pipeline for text-to-image generation.

    Reference: https://huggingface.co/lodestones/Chroma/

    Args:
        transformer ([`ChromaTransformer2DModel`]):
            Conditional Transformer (MMDiT) architecture to denoise the encoded image latents.
        scheduler ([`FlowMatchEulerDiscreteScheduler`]):
            A scheduler to be used in combination with `transformer` to denoise the encoded image latents.
        vae ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representation
        text_encoder ([`T5EncoderModel`]):
            [T5](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5EncoderModel), specifically
            the [google/t5-v1_1-xxl](https://huggingface.co/google/t5-v1_1-xxl) variant.
        tokenizer (`T5TokenizerFast`):
            Second Tokenizer of class
            [T5TokenizerFast](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5TokenizerFast).
    """

    model_cpu_offload_seq = "text_encoder->image_encoder->transformer->vae"
    _optional_components = ["image_encoder", "feature_extractor"]
    _callback_tensor_inputs = ["latents", "prompt_embeds"]

    def __init__(
        self,
        scheduler: FlowMatchEulerDiscreteScheduler,
        vae: AutoencoderKL,
        text_encoder: T5EncoderModel,
        tokenizer: T5TokenizerFast,
        transformer: ChromaTransformer2DModel,
        image_encoder: CLIPVisionModelWithProjection = None,
        feature_extractor: CLIPImageProcessor = None,
    ):
        super().__init__()

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            transformer=transformer,
            scheduler=scheduler,
            image_encoder=image_encoder,
            feature_extractor=feature_extractor,
        )
        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
        # Flux latents are turned into 2x2 patches and packed. This means the latent width and height has to be divisible
        # by the patch size. So the vae scale factor is multiplied by the patch size to account for this
        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor * 2)
        self.default_sample_size = 128

    def _get_t5_prompt_embeds(
        self,
        prompt: Union[str, List[str]] = None,
        num_images_per_prompt: int = 1,
        max_sequence_length: int = 512,
        dtype: Optional[ms.Type] = None,
    ):
        dtype = dtype or self.text_encoder.dtype

        prompt = [prompt] if isinstance(prompt, str) else prompt
        batch_size = len(prompt)

        if isinstance(self, TextualInversionLoaderMixin):
            prompt = self.maybe_convert_prompt(prompt, self.tokenizer)

        text_inputs = self.tokenizer(
            prompt,
            padding="max_length",
            max_length=max_sequence_length,
            truncation=True,
            return_length=False,
            return_overflowing_tokens=False,
            return_tensors="np",
        )
        text_input_ids = ms.tensor(text_inputs.input_ids)
        attention_mask = ms.tensor(text_inputs.attention_mask).clone()

        # Chroma requires the attention mask to include one padding token
        seq_lengths = attention_mask.sum(dim=1)
        mask_indices = mint.arange(attention_mask.shape[1]).unsqueeze(0).broadcast_to((batch_size, -1))
        attention_mask = (mask_indices <= seq_lengths.unsqueeze(1)).long()

        with pynative_context():
            prompt_embeds = self.text_encoder(
                text_input_ids, output_hidden_states=False, attention_mask=attention_mask
            )[0]

        dtype = self.text_encoder.dtype
        prompt_embeds = prompt_embeds.to(dtype=dtype)
        attention_mask = attention_mask.to(dtype=dtype)

        _, seq_len, _ = prompt_embeds.shape

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

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

        return prompt_embeds, attention_mask

    def encode_prompt(
        self,
        prompt: Union[str, List[str]],
        negative_prompt: Union[str, List[str]] = None,
        num_images_per_prompt: int = 1,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        do_classifier_free_guidance: bool = True,
        max_sequence_length: int = 512,
        lora_scale: Optional[float] = None,
    ):
        r"""

        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`).
            num_images_per_prompt (`int`):
                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.
            lora_scale (`float`, *optional*):
                A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
        """
        # 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, FluxLoraLoaderMixin):
            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)

        prompt = [prompt] if isinstance(prompt, str) else prompt

        if prompt is not None:
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if prompt_embeds is None:
            prompt_embeds, prompt_attention_mask = self._get_t5_prompt_embeds(
                prompt=prompt,
                num_images_per_prompt=num_images_per_prompt,
                max_sequence_length=max_sequence_length,
            )

        dtype = self.text_encoder.dtype if self.text_encoder is not None else self.transformer.dtype
        text_ids = mint.zeros((prompt_embeds.shape[1], 3)).to(dtype=dtype)
        negative_text_ids = None

        if do_classifier_free_guidance:
            if negative_prompt_embeds is None:
                negative_prompt = negative_prompt or ""
                negative_prompt = (
                    batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt
                )

                if prompt is not None and type(prompt) is not type(negative_prompt):
                    raise TypeError(
                        f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                        f" {type(prompt)}."
                    )
                elif batch_size != len(negative_prompt):
                    raise ValueError(
                        f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                        f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                        " the batch size of `prompt`."
                    )

                negative_prompt_embeds, negative_prompt_attention_mask = self._get_t5_prompt_embeds(
                    prompt=negative_prompt,
                    num_images_per_prompt=num_images_per_prompt,
                    max_sequence_length=max_sequence_length,
                )

            negative_text_ids = mint.zeros((negative_prompt_embeds.shape[1], 3)).to(dtype=dtype)

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

        return (
            prompt_embeds,
            text_ids,
            prompt_attention_mask,
            negative_prompt_embeds,
            negative_text_ids,
            negative_prompt_attention_mask,
        )

    # Copied from mindone.diffusers.pipelines.flux.pipeline_flux.FluxPipeline.encode_image
    def encode_image(self, image, num_images_per_prompt):
        dtype = next(self.image_encoder.parameters()).dtype

        if not isinstance(image, ms.Tensor):
            image = ms.tensor(self.feature_extractor(image, return_tensors="np").pixel_values)

        image = image.to(dtype=dtype)
        image_embeds = self.image_encoder(image).image_embeds
        image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
        return image_embeds

    # Copied from mindone.diffusers.pipelines.flux.pipeline_flux.FluxPipeline.prepare_ip_adapter_image_embeds
    def prepare_ip_adapter_image_embeds(self, ip_adapter_image, ip_adapter_image_embeds, num_images_per_prompt):
        image_embeds = []
        if ip_adapter_image_embeds is None:
            if not isinstance(ip_adapter_image, list):
                ip_adapter_image = [ip_adapter_image]

            if len(ip_adapter_image) != self.transformer.encoder_hid_proj.num_ip_adapters:
                raise ValueError(
                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {self.transformer.encoder_hid_proj.num_ip_adapters} IP Adapters."  # noqa
                )

            for single_ip_adapter_image in ip_adapter_image:
                single_image_embeds = self.encode_image(single_ip_adapter_image, 1)
                image_embeds.append(single_image_embeds[None, :])
        else:
            if not isinstance(ip_adapter_image_embeds, list):
                ip_adapter_image_embeds = [ip_adapter_image_embeds]

            if len(ip_adapter_image_embeds) != self.transformer.encoder_hid_proj.num_ip_adapters:
                raise ValueError(
                    f"`ip_adapter_image_embeds` must have same length as the number of IP Adapters. Got {len(ip_adapter_image_embeds)} image embeds and {self.transformer.encoder_hid_proj.num_ip_adapters} IP Adapters."  # noqa
                )

            for single_image_embeds in ip_adapter_image_embeds:
                image_embeds.append(single_image_embeds)

        ip_adapter_image_embeds = []
        for single_image_embeds in image_embeds:
            single_image_embeds = mint.cat([single_image_embeds] * num_images_per_prompt, dim=0)
            ip_adapter_image_embeds.append(single_image_embeds)

        return ip_adapter_image_embeds

    def check_inputs(
        self,
        prompt,
        height,
        width,
        negative_prompt=None,
        prompt_embeds=None,
        prompt_attention_mask=None,
        negative_prompt_embeds=None,
        negative_prompt_attention_mask=None,
        callback_on_step_end_tensor_inputs=None,
        max_sequence_length=None,
    ):
        if height % (self.vae_scale_factor * 2) != 0 or width % (self.vae_scale_factor * 2) != 0:
            logger.warning(
                f"`height` and `width` have to be divisible by {self.vae_scale_factor * 2} but are {height} and {width}. Dimensions will be resized accordingly"
            )

        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
            )

        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 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("Cannot provide `prompt_embeds` without also providing `prompt_attention_mask")

        if negative_prompt_embeds is not None and negative_prompt_attention_mask is None:
            raise ValueError(
                "Cannot provide `negative_prompt_embeds` without also providing `negative_prompt_attention_mask"
            )

        if max_sequence_length is not None and max_sequence_length > 512:
            raise ValueError(f"`max_sequence_length` cannot be greater than 512 but is {max_sequence_length}")

    @staticmethod
    def _prepare_latent_image_ids(batch_size, height, width, dtype):
        latent_image_ids = mint.zeros((height, width, 3))
        latent_image_ids[..., 1] = latent_image_ids[..., 1] + mint.arange(height)[:, None]
        latent_image_ids[..., 2] = latent_image_ids[..., 2] + mint.arange(width)[None, :]

        latent_image_id_height, latent_image_id_width, latent_image_id_channels = latent_image_ids.shape

        latent_image_ids = latent_image_ids.reshape(
            latent_image_id_height * latent_image_id_width, latent_image_id_channels
        )

        return latent_image_ids.to(dtype=dtype)

    @staticmethod
    def _pack_latents(latents, batch_size, num_channels_latents, height, width):
        latents = latents.view(batch_size, num_channels_latents, height // 2, 2, width // 2, 2)
        latents = latents.permute(0, 2, 4, 1, 3, 5)
        latents = latents.reshape(batch_size, (height // 2) * (width // 2), num_channels_latents * 4)

        return latents

    @staticmethod
    def _unpack_latents(latents, height, width, vae_scale_factor):
        batch_size, num_patches, channels = latents.shape

        # VAE applies 8x compression on images but we must also account for packing which requires
        # latent height and width to be divisible by 2.
        height = 2 * (int(height) // (vae_scale_factor * 2))
        width = 2 * (int(width) // (vae_scale_factor * 2))

        latents = latents.view(batch_size, height // 2, width // 2, channels // 4, 2, 2)
        latents = latents.permute(0, 3, 1, 4, 2, 5)

        latents = latents.reshape(batch_size, channels // (2 * 2), height, width)

        return latents

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

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

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

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

    # Copied from mindone.diffusers.pipelines.flux.pipeline_flux.FluxPipeline.prepare_latents
    def prepare_latents(
        self,
        batch_size,
        num_channels_latents,
        height,
        width,
        dtype,
        generator,
        latents=None,
    ):
        # VAE applies 8x compression on images but we must also account for packing which requires
        # latent height and width to be divisible by 2.
        height = 2 * (int(height) // (self.vae_scale_factor * 2))
        width = 2 * (int(width) // (self.vae_scale_factor * 2))

        shape = (batch_size, num_channels_latents, height, width)

        if latents is not None:
            latent_image_ids = self._prepare_latent_image_ids(batch_size, height // 2, width // 2, dtype)
            return latents.to(dtype=dtype), latent_image_ids

        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)
        latents = self._pack_latents(latents, batch_size, num_channels_latents, height, width)

        latent_image_ids = self._prepare_latent_image_ids(batch_size, height // 2, width // 2, dtype)

        return latents, latent_image_ids

    def _prepare_attention_mask(
        self,
        batch_size,
        sequence_length,
        dtype,
        attention_mask=None,
    ):
        if attention_mask is None:
            return attention_mask

        # Extend the prompt attention mask to account for image tokens in the final sequence
        attention_mask = mint.cat(
            [attention_mask, mint.ones((batch_size, sequence_length), dtype=attention_mask.dtype)],
            dim=1,
        )
        attention_mask = attention_mask.to(dtype)

        return attention_mask

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

    @property
    def joint_attention_kwargs(self):
        return self._joint_attention_kwargs

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

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

    @property
    def current_timestep(self):
        return self._current_timestep

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

    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        negative_prompt: Union[str, List[str]] = None,
        height: Optional[int] = None,
        width: Optional[int] = None,
        num_inference_steps: int = 35,
        sigmas: Optional[List[float]] = None,
        guidance_scale: float = 5.0,
        num_images_per_prompt: Optional[int] = 1,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        ip_adapter_image: Optional[PipelineImageInput] = None,
        ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
        negative_ip_adapter_image: Optional[PipelineImageInput] = None,
        negative_ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = False,
        joint_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 = 512,
    ):
        r"""
        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
                not greater than `1`).
            height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                The height in pixels of the generated image. This is set to 1024 by default for the best results.
            width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                The width in pixels of the generated image. This is set to 1024 by default for the best results.
            num_inference_steps (`int`, *optional*, defaults to 50):
                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                expense of slower inference.
            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 3.5):
                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.
            generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
                One or a list of [np.random.Generator(s)](https://numpy.org/doc/stable/reference/random/generator.html)
                to make generation deterministic.
            latents (`ms.Tensor`, *optional*):
                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor will ge generated by sampling using the supplied random `generator`.
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
            ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. If not
                provided, embeddings are computed from the `ip_adapter_image` input argument.
            negative_ip_adapter_image:
                (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
            negative_ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. If not
                provided, embeddings are computed from the `ip_adapter_image` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                argument.
            prompt_attention_mask (ms.Tensor, *optional*):
                Attention mask for the prompt embeddings. Used to mask out padding tokens in the prompt sequence.
                Chroma requires a single padding token remain unmasked. Please refer to
                https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training
            negative_prompt_attention_mask (ms.Tensor, *optional*):
                Attention mask for the negative prompt embeddings. Used to mask out padding tokens in the negative
                prompt sequence. Chroma requires a single padding token remain unmasked. PLease refer to
                https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training
            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.flux.ChromaPipelineOutput`] instead of a plain tuple.
            joint_attention_kwargs (`dict`, *optional*):
                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).
            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 512): Maximum sequence length to use with the `prompt`.

        Examples:

        Returns:
            [`~pipelines.chroma.ChromaPipelineOutput`] or `tuple`: [`~pipelines.chroma.ChromaPipelineOutput`] if
            `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is a list with the
            generated images.
        """

        height = height or self.default_sample_size * self.vae_scale_factor
        width = width or self.default_sample_size * self.vae_scale_factor

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            prompt,
            height,
            width,
            negative_prompt=negative_prompt,
            prompt_embeds=prompt_embeds,
            prompt_attention_mask=prompt_attention_mask,
            negative_prompt_embeds=negative_prompt_embeds,
            negative_prompt_attention_mask=negative_prompt_attention_mask,
            callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
            max_sequence_length=max_sequence_length,
        )

        self._guidance_scale = guidance_scale
        self._joint_attention_kwargs = joint_attention_kwargs
        self._current_timestep = None
        self._interrupt = False

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

        lora_scale = self.joint_attention_kwargs.get("scale", None) if self.joint_attention_kwargs is not None else None
        (
            prompt_embeds,
            text_ids,
            prompt_attention_mask,
            negative_prompt_embeds,
            negative_text_ids,
            negative_prompt_attention_mask,
        ) = self.encode_prompt(
            prompt=prompt,
            negative_prompt=negative_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            prompt_attention_mask=prompt_attention_mask,
            negative_prompt_attention_mask=negative_prompt_attention_mask,
            do_classifier_free_guidance=self.do_classifier_free_guidance,
            num_images_per_prompt=num_images_per_prompt,
            max_sequence_length=max_sequence_length,
            lora_scale=lora_scale,
        )

        # 4. Prepare latent variables
        num_channels_latents = self.transformer.config.in_channels // 4
        latents, latent_image_ids = self.prepare_latents(
            batch_size * num_images_per_prompt,
            num_channels_latents,
            height,
            width,
            prompt_embeds.dtype,
            generator,
            latents,
        )

        # 5. Prepare timesteps
        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
        image_seq_len = latents.shape[1]
        mu = calculate_shift(
            image_seq_len,
            self.scheduler.config.get("base_image_seq_len", 256),
            self.scheduler.config.get("max_image_seq_len", 4096),
            self.scheduler.config.get("base_shift", 0.5),
            self.scheduler.config.get("max_shift", 1.15),
        )

        attention_mask = self._prepare_attention_mask(
            batch_size=latents.shape[0],
            sequence_length=image_seq_len,
            dtype=latents.dtype,
            attention_mask=prompt_attention_mask,
        )
        negative_attention_mask = self._prepare_attention_mask(
            batch_size=latents.shape[0],
            sequence_length=image_seq_len,
            dtype=latents.dtype,
            attention_mask=negative_prompt_attention_mask,
        )

        timesteps, num_inference_steps = retrieve_timesteps(
            self.scheduler,
            num_inference_steps,
            sigmas=sigmas,
            mu=mu,
        )
        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
        self._num_timesteps = len(timesteps)

        if (ip_adapter_image is not None or ip_adapter_image_embeds is not None) and (
            negative_ip_adapter_image is None and negative_ip_adapter_image_embeds is None
        ):
            negative_ip_adapter_image = np.zeros((width, height, 3), dtype=np.uint8)
            negative_ip_adapter_image = [negative_ip_adapter_image] * self.transformer.encoder_hid_proj.num_ip_adapters

        elif (ip_adapter_image is None and ip_adapter_image_embeds is None) and (
            negative_ip_adapter_image is not None or negative_ip_adapter_image_embeds is not None
        ):
            ip_adapter_image = np.zeros((width, height, 3), dtype=np.uint8)
            ip_adapter_image = [ip_adapter_image] * self.transformer.encoder_hid_proj.num_ip_adapters

        if self.joint_attention_kwargs is None:
            self._joint_attention_kwargs = {}

        image_embeds = None
        negative_image_embeds = None
        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
            image_embeds = self.prepare_ip_adapter_image_embeds(
                ip_adapter_image,
                ip_adapter_image_embeds,
                batch_size * num_images_per_prompt,
            )
        if negative_ip_adapter_image is not None or negative_ip_adapter_image_embeds is not None:
            negative_image_embeds = self.prepare_ip_adapter_image_embeds(
                negative_ip_adapter_image,
                negative_ip_adapter_image_embeds,
                batch_size * num_images_per_prompt,
            )

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

                self._current_timestep = t
                if image_embeds is not None:
                    self._joint_attention_kwargs["ip_adapter_image_embeds"] = image_embeds

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

                noise_pred = self.transformer(
                    hidden_states=latents,
                    timestep=timestep / 1000,
                    encoder_hidden_states=prompt_embeds,
                    txt_ids=text_ids,
                    img_ids=latent_image_ids,
                    attention_mask=attention_mask,
                    joint_attention_kwargs=self.joint_attention_kwargs,
                    return_dict=False,
                )[0]

                if self.do_classifier_free_guidance:
                    if negative_image_embeds is not None:
                        self._joint_attention_kwargs["ip_adapter_image_embeds"] = negative_image_embeds
                    neg_noise_pred = self.transformer(
                        hidden_states=latents,
                        timestep=timestep / 1000,
                        encoder_hidden_states=negative_prompt_embeds,
                        txt_ids=negative_text_ids,
                        img_ids=latent_image_ids,
                        attention_mask=negative_attention_mask,
                        joint_attention_kwargs=self.joint_attention_kwargs,
                        return_dict=False,
                    )[0]
                    noise_pred = neg_noise_pred + guidance_scale * (noise_pred - neg_noise_pred)

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

                # 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()

        self._current_timestep = None

        if output_type == "latent":
            image = latents
        else:
            latents = self._unpack_latents(latents, height, width, self.vae_scale_factor)
            latents = (latents / self.vae.config.scaling_factor) + self.vae.config.shift_factor
            image = self.vae.decode(latents, return_dict=False)[0]
            image = self.image_processor.postprocess(image, output_type=output_type)

        if not return_dict:
            return (image,)

        return ChromaPipelineOutput(images=image)

mindone.diffusers.ChromaPipeline.__call__(prompt=None, negative_prompt=None, height=None, width=None, num_inference_steps=35, sigmas=None, guidance_scale=5.0, num_images_per_prompt=1, generator=None, latents=None, prompt_embeds=None, ip_adapter_image=None, ip_adapter_image_embeds=None, negative_ip_adapter_image=None, negative_ip_adapter_image_embeds=None, negative_prompt_embeds=None, prompt_attention_mask=None, negative_prompt_attention_mask=None, output_type='pil', return_dict=False, joint_attention_kwargs=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], max_sequence_length=512)

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 not greater than 1). TYPE: `str` or `List[str]`, *optional* DEFAULT: None
height	The height in pixels of the generated image. This is set to 1024 by default for the best results. TYPE: `int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor DEFAULT: None
width	The width in pixels of the generated image. This is set to 1024 by default for the best results. TYPE: `int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor DEFAULT: None
num_inference_steps	The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. TYPE: `int`, *optional*, defaults to 50 DEFAULT: 35
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 3.5 DEFAULT: 5.0
num_images_per_prompt	The number of images to generate per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
generator	One or a list of np.random.Generator(s) to make generation deterministic. TYPE: `np.random.Generator` or `List[np.random.Generator]`, *optional* DEFAULT: None
latents	Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied random generator. TYPE: `ms.Tensor`, *optional* DEFAULT: None
prompt_embeds	Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument. TYPE: `ms.Tensor`, *optional* DEFAULT: None
ip_adapter_image	(PipelineImageInput, optional): Optional image input to work with IP Adapters. TYPE: Optional[PipelineImageInput] DEFAULT: None
ip_adapter_image_embeds	Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters. Each element should be a tensor of shape (batch_size, num_images, emb_dim). If not provided, embeddings are computed from the ip_adapter_image input argument. TYPE: `List[ms.Tensor]`, *optional* DEFAULT: None
negative_ip_adapter_image	(PipelineImageInput, optional): Optional image input to work with IP Adapters. TYPE: Optional[PipelineImageInput] DEFAULT: None
negative_ip_adapter_image_embeds	Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters. Each element should be a tensor of shape (batch_size, num_images, emb_dim). If not provided, embeddings are computed from the ip_adapter_image input argument. TYPE: `List[ms.Tensor]`, *optional* DEFAULT: None
negative_prompt_embeds	Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument. TYPE: `ms.Tensor`, *optional* DEFAULT: None
prompt_attention_mask	Attention mask for the prompt embeddings. Used to mask out padding tokens in the prompt sequence. Chroma requires a single padding token remain unmasked. Please refer to https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training TYPE: ms.Tensor, *optional* DEFAULT: None
negative_prompt_attention_mask	Attention mask for the negative prompt embeddings. Used to mask out padding tokens in the negative prompt sequence. Chroma requires a single padding token remain unmasked. PLease refer to https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training 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.flux.ChromaPipelineOutput] instead of a plain tuple. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
joint_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: `dict`, *optional* DEFAULT: None
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 512 DEFAULT: 512

RETURNS	DESCRIPTION
	[~pipelines.chroma.ChromaPipelineOutput] or tuple: [~pipelines.chroma.ChromaPipelineOutput] if
	return_dict is True, otherwise a tuple. When returning a tuple, the first element is a list with the
	generated images.

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma.py

def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    negative_prompt: Union[str, List[str]] = None,
    height: Optional[int] = None,
    width: Optional[int] = None,
    num_inference_steps: int = 35,
    sigmas: Optional[List[float]] = None,
    guidance_scale: float = 5.0,
    num_images_per_prompt: Optional[int] = 1,
    generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
    latents: Optional[ms.Tensor] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    ip_adapter_image: Optional[PipelineImageInput] = None,
    ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
    negative_ip_adapter_image: Optional[PipelineImageInput] = None,
    negative_ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    output_type: Optional[str] = "pil",
    return_dict: bool = False,
    joint_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 = 512,
):
    r"""
    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
            not greater than `1`).
        height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
            The height in pixels of the generated image. This is set to 1024 by default for the best results.
        width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
            The width in pixels of the generated image. This is set to 1024 by default for the best results.
        num_inference_steps (`int`, *optional*, defaults to 50):
            The number of denoising steps. More denoising steps usually lead to a higher quality image at the
            expense of slower inference.
        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 3.5):
            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.
        generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
            One or a list of [np.random.Generator(s)](https://numpy.org/doc/stable/reference/random/generator.html)
            to make generation deterministic.
        latents (`ms.Tensor`, *optional*):
            Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
            generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
            tensor will ge generated by sampling using the supplied random `generator`.
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
            provided, text embeddings will be generated from `prompt` input argument.
        ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
        ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
            Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
            IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. If not
            provided, embeddings are computed from the `ip_adapter_image` input argument.
        negative_ip_adapter_image:
            (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
        negative_ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
            Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
            IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. If not
            provided, embeddings are computed from the `ip_adapter_image` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
            weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
            argument.
        prompt_attention_mask (ms.Tensor, *optional*):
            Attention mask for the prompt embeddings. Used to mask out padding tokens in the prompt sequence.
            Chroma requires a single padding token remain unmasked. Please refer to
            https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training
        negative_prompt_attention_mask (ms.Tensor, *optional*):
            Attention mask for the negative prompt embeddings. Used to mask out padding tokens in the negative
            prompt sequence. Chroma requires a single padding token remain unmasked. PLease refer to
            https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training
        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.flux.ChromaPipelineOutput`] instead of a plain tuple.
        joint_attention_kwargs (`dict`, *optional*):
            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).
        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 512): Maximum sequence length to use with the `prompt`.

    Examples:

    Returns:
        [`~pipelines.chroma.ChromaPipelineOutput`] or `tuple`: [`~pipelines.chroma.ChromaPipelineOutput`] if
        `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is a list with the
        generated images.
    """

    height = height or self.default_sample_size * self.vae_scale_factor
    width = width or self.default_sample_size * self.vae_scale_factor

    # 1. Check inputs. Raise error if not correct
    self.check_inputs(
        prompt,
        height,
        width,
        negative_prompt=negative_prompt,
        prompt_embeds=prompt_embeds,
        prompt_attention_mask=prompt_attention_mask,
        negative_prompt_embeds=negative_prompt_embeds,
        negative_prompt_attention_mask=negative_prompt_attention_mask,
        callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
        max_sequence_length=max_sequence_length,
    )

    self._guidance_scale = guidance_scale
    self._joint_attention_kwargs = joint_attention_kwargs
    self._current_timestep = None
    self._interrupt = False

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

    lora_scale = self.joint_attention_kwargs.get("scale", None) if self.joint_attention_kwargs is not None else None
    (
        prompt_embeds,
        text_ids,
        prompt_attention_mask,
        negative_prompt_embeds,
        negative_text_ids,
        negative_prompt_attention_mask,
    ) = self.encode_prompt(
        prompt=prompt,
        negative_prompt=negative_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        prompt_attention_mask=prompt_attention_mask,
        negative_prompt_attention_mask=negative_prompt_attention_mask,
        do_classifier_free_guidance=self.do_classifier_free_guidance,
        num_images_per_prompt=num_images_per_prompt,
        max_sequence_length=max_sequence_length,
        lora_scale=lora_scale,
    )

    # 4. Prepare latent variables
    num_channels_latents = self.transformer.config.in_channels // 4
    latents, latent_image_ids = self.prepare_latents(
        batch_size * num_images_per_prompt,
        num_channels_latents,
        height,
        width,
        prompt_embeds.dtype,
        generator,
        latents,
    )

    # 5. Prepare timesteps
    sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
    image_seq_len = latents.shape[1]
    mu = calculate_shift(
        image_seq_len,
        self.scheduler.config.get("base_image_seq_len", 256),
        self.scheduler.config.get("max_image_seq_len", 4096),
        self.scheduler.config.get("base_shift", 0.5),
        self.scheduler.config.get("max_shift", 1.15),
    )

    attention_mask = self._prepare_attention_mask(
        batch_size=latents.shape[0],
        sequence_length=image_seq_len,
        dtype=latents.dtype,
        attention_mask=prompt_attention_mask,
    )
    negative_attention_mask = self._prepare_attention_mask(
        batch_size=latents.shape[0],
        sequence_length=image_seq_len,
        dtype=latents.dtype,
        attention_mask=negative_prompt_attention_mask,
    )

    timesteps, num_inference_steps = retrieve_timesteps(
        self.scheduler,
        num_inference_steps,
        sigmas=sigmas,
        mu=mu,
    )
    num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
    self._num_timesteps = len(timesteps)

    if (ip_adapter_image is not None or ip_adapter_image_embeds is not None) and (
        negative_ip_adapter_image is None and negative_ip_adapter_image_embeds is None
    ):
        negative_ip_adapter_image = np.zeros((width, height, 3), dtype=np.uint8)
        negative_ip_adapter_image = [negative_ip_adapter_image] * self.transformer.encoder_hid_proj.num_ip_adapters

    elif (ip_adapter_image is None and ip_adapter_image_embeds is None) and (
        negative_ip_adapter_image is not None or negative_ip_adapter_image_embeds is not None
    ):
        ip_adapter_image = np.zeros((width, height, 3), dtype=np.uint8)
        ip_adapter_image = [ip_adapter_image] * self.transformer.encoder_hid_proj.num_ip_adapters

    if self.joint_attention_kwargs is None:
        self._joint_attention_kwargs = {}

    image_embeds = None
    negative_image_embeds = None
    if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
        image_embeds = self.prepare_ip_adapter_image_embeds(
            ip_adapter_image,
            ip_adapter_image_embeds,
            batch_size * num_images_per_prompt,
        )
    if negative_ip_adapter_image is not None or negative_ip_adapter_image_embeds is not None:
        negative_image_embeds = self.prepare_ip_adapter_image_embeds(
            negative_ip_adapter_image,
            negative_ip_adapter_image_embeds,
            batch_size * num_images_per_prompt,
        )

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

            self._current_timestep = t
            if image_embeds is not None:
                self._joint_attention_kwargs["ip_adapter_image_embeds"] = image_embeds

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

            noise_pred = self.transformer(
                hidden_states=latents,
                timestep=timestep / 1000,
                encoder_hidden_states=prompt_embeds,
                txt_ids=text_ids,
                img_ids=latent_image_ids,
                attention_mask=attention_mask,
                joint_attention_kwargs=self.joint_attention_kwargs,
                return_dict=False,
            )[0]

            if self.do_classifier_free_guidance:
                if negative_image_embeds is not None:
                    self._joint_attention_kwargs["ip_adapter_image_embeds"] = negative_image_embeds
                neg_noise_pred = self.transformer(
                    hidden_states=latents,
                    timestep=timestep / 1000,
                    encoder_hidden_states=negative_prompt_embeds,
                    txt_ids=negative_text_ids,
                    img_ids=latent_image_ids,
                    attention_mask=negative_attention_mask,
                    joint_attention_kwargs=self.joint_attention_kwargs,
                    return_dict=False,
                )[0]
                noise_pred = neg_noise_pred + guidance_scale * (noise_pred - neg_noise_pred)

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

            # 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()

    self._current_timestep = None

    if output_type == "latent":
        image = latents
    else:
        latents = self._unpack_latents(latents, height, width, self.vae_scale_factor)
        latents = (latents / self.vae.config.scaling_factor) + self.vae.config.shift_factor
        image = self.vae.decode(latents, return_dict=False)[0]
        image = self.image_processor.postprocess(image, output_type=output_type)

    if not return_dict:
        return (image,)

    return ChromaPipelineOutput(images=image)

mindone.diffusers.ChromaPipeline.disable_vae_slicing()

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

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma.py

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

mindone.diffusers.ChromaPipeline.disable_vae_tiling()

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

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma.py

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

mindone.diffusers.ChromaPipeline.enable_vae_slicing()

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

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma.py

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

mindone.diffusers.ChromaPipeline.enable_vae_tiling()

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

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma.py

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

mindone.diffusers.ChromaPipeline.encode_prompt(prompt, negative_prompt=None, num_images_per_prompt=1, prompt_embeds=None, negative_prompt_embeds=None, prompt_attention_mask=None, negative_prompt_attention_mask=None, do_classifier_free_guidance=True, max_sequence_length=512, lora_scale=None)

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). TYPE: `str` or `List[str]`, *optional* DEFAULT: None
num_images_per_prompt	number of images that should be generated per prompt TYPE: `int` 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
lora_scale	A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded. TYPE: `float`, *optional* DEFAULT: None

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma.py

def encode_prompt(
    self,
    prompt: Union[str, List[str]],
    negative_prompt: Union[str, List[str]] = None,
    num_images_per_prompt: int = 1,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    do_classifier_free_guidance: bool = True,
    max_sequence_length: int = 512,
    lora_scale: Optional[float] = None,
):
    r"""

    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`).
        num_images_per_prompt (`int`):
            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.
        lora_scale (`float`, *optional*):
            A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
    """
    # 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, FluxLoraLoaderMixin):
        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)

    prompt = [prompt] if isinstance(prompt, str) else prompt

    if prompt is not None:
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    if prompt_embeds is None:
        prompt_embeds, prompt_attention_mask = self._get_t5_prompt_embeds(
            prompt=prompt,
            num_images_per_prompt=num_images_per_prompt,
            max_sequence_length=max_sequence_length,
        )

    dtype = self.text_encoder.dtype if self.text_encoder is not None else self.transformer.dtype
    text_ids = mint.zeros((prompt_embeds.shape[1], 3)).to(dtype=dtype)
    negative_text_ids = None

    if do_classifier_free_guidance:
        if negative_prompt_embeds is None:
            negative_prompt = negative_prompt or ""
            negative_prompt = (
                batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt
            )

            if prompt is not None and type(prompt) is not type(negative_prompt):
                raise TypeError(
                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                    f" {type(prompt)}."
                )
            elif batch_size != len(negative_prompt):
                raise ValueError(
                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                    " the batch size of `prompt`."
                )

            negative_prompt_embeds, negative_prompt_attention_mask = self._get_t5_prompt_embeds(
                prompt=negative_prompt,
                num_images_per_prompt=num_images_per_prompt,
                max_sequence_length=max_sequence_length,
            )

        negative_text_ids = mint.zeros((negative_prompt_embeds.shape[1], 3)).to(dtype=dtype)

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

    return (
        prompt_embeds,
        text_ids,
        prompt_attention_mask,
        negative_prompt_embeds,
        negative_text_ids,
        negative_prompt_attention_mask,
    )

mindone.diffusers.ChromaImg2ImgPipeline

Bases: DiffusionPipeline, FluxLoraLoaderMixin, FromSingleFileMixin, TextualInversionLoaderMixin, FluxIPAdapterMixin

The Chroma pipeline for image-to-image generation.

Reference: https://huggingface.co/lodestones/Chroma/

PARAMETER	DESCRIPTION
transformer	Conditional Transformer (MMDiT) architecture to denoise the encoded image latents. TYPE: [`ChromaTransformer2DModel`]
scheduler	A scheduler to be used in combination with transformer to denoise the encoded image latents. TYPE: [`FlowMatchEulerDiscreteScheduler`]
vae	Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representation TYPE: [`AutoencoderKL`]
text_encoder	T5, specifically the google/t5-v1_1-xxl variant. TYPE: [`T5EncoderModel`]
tokenizer	Second Tokenizer of class T5TokenizerFast. TYPE: `T5TokenizerFast`

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma_img2img.py

class ChromaImg2ImgPipeline(
    DiffusionPipeline,
    FluxLoraLoaderMixin,
    FromSingleFileMixin,
    TextualInversionLoaderMixin,
    FluxIPAdapterMixin,
):
    r"""
    The Chroma pipeline for image-to-image generation.

    Reference: https://huggingface.co/lodestones/Chroma/

    Args:
        transformer ([`ChromaTransformer2DModel`]):
            Conditional Transformer (MMDiT) architecture to denoise the encoded image latents.
        scheduler ([`FlowMatchEulerDiscreteScheduler`]):
            A scheduler to be used in combination with `transformer` to denoise the encoded image latents.
        vae ([`AutoencoderKL`]):
            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representation
        text_encoder ([`T5EncoderModel`]):
            [T5](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5EncoderModel), specifically
            the [google/t5-v1_1-xxl](https://huggingface.co/google/t5-v1_1-xxl) variant.
        tokenizer (`T5TokenizerFast`):
            Second Tokenizer of class
            [T5TokenizerFast](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5TokenizerFast).
    """

    model_cpu_offload_seq = "text_encoder->image_encoder->transformer->vae"
    _optional_components = ["image_encoder", "feature_extractor"]
    _callback_tensor_inputs = ["latents", "prompt_embeds"]

    def __init__(
        self,
        scheduler: FlowMatchEulerDiscreteScheduler,
        vae: AutoencoderKL,
        text_encoder: T5EncoderModel,
        tokenizer: T5TokenizerFast,
        transformer: ChromaTransformer2DModel,
        image_encoder: CLIPVisionModelWithProjection = None,
        feature_extractor: CLIPImageProcessor = None,
    ):
        super().__init__()

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            transformer=transformer,
            scheduler=scheduler,
            image_encoder=image_encoder,
            feature_extractor=feature_extractor,
        )
        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
        self.latent_channels = self.vae.config.latent_channels if getattr(self, "vae", None) else 16

        # Flux latents are turned into 2x2 patches and packed. This means the latent width and height has to be divisible
        # by the patch size. So the vae scale factor is multiplied by the patch size to account for this
        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor * 2)
        self.default_sample_size = 128

    def _get_t5_prompt_embeds(
        self,
        prompt: Union[str, List[str]] = None,
        num_images_per_prompt: int = 1,
        max_sequence_length: int = 512,
        dtype: Optional[ms.Type] = None,
    ):
        dtype = dtype or self.text_encoder.dtype

        prompt = [prompt] if isinstance(prompt, str) else prompt
        batch_size = len(prompt)

        if isinstance(self, TextualInversionLoaderMixin):
            prompt = self.maybe_convert_prompt(prompt, self.tokenizer)

        text_inputs = self.tokenizer(
            prompt,
            padding="max_length",
            max_length=max_sequence_length,
            truncation=True,
            return_length=False,
            return_overflowing_tokens=False,
            return_tensors="np",
        )
        text_input_ids = ms.tensor(text_inputs.input_ids)
        attention_mask = ms.tensor(text_inputs.attention_mask).clone()

        # Chroma requires the attention mask to include one padding token
        seq_lengths = attention_mask.sum(dim=1)
        mask_indices = mint.arange(attention_mask.shape[1]).unsqueeze(0).broadcast_to((batch_size, -1))
        attention_mask = (mask_indices <= seq_lengths.unsqueeze(1)).long()

        with pynative_context():
            prompt_embeds = self.text_encoder(
                text_input_ids, output_hidden_states=False, attention_mask=attention_mask
            )[0]

        dtype = self.text_encoder.dtype
        prompt_embeds = prompt_embeds.to(dtype=dtype)
        attention_mask = attention_mask.to(dtype=dtype)

        _, seq_len, _ = prompt_embeds.shape

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

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

        return prompt_embeds, attention_mask

    # Copied from mindone.diffusers.pipelines.stable_diffusion_3.pipeline_stable_diffusion_3_inpaint.StableDiffusion3InpaintPipeline._encode_vae_image
    def _encode_vae_image(self, image: ms.Tensor, generator: np.random.Generator):
        if isinstance(generator, list):
            image_latents = [
                retrieve_latents(self.vae, self.vae.encode(image[i : i + 1])[0], generator=generator[i])
                for i in range(image.shape[0])
            ]
            image_latents = mint.cat(image_latents, dim=0)
        else:
            image_latents = retrieve_latents(self.vae, self.vae.encode(image)[0], generator=generator)

        image_latents = (image_latents - self.vae.config.shift_factor) * self.vae.config.scaling_factor

        return image_latents

    def encode_prompt(
        self,
        prompt: Union[str, List[str]],
        negative_prompt: Union[str, List[str]] = None,
        num_images_per_prompt: int = 1,
        prompt_embeds: Optional[ms.Tensor] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        do_classifier_free_guidance: bool = True,
        max_sequence_length: int = 512,
        lora_scale: Optional[float] = None,
    ):
        r"""

        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`).
            num_images_per_prompt (`int`):
                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.
            lora_scale (`float`, *optional*):
                A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
        """
        # 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, FluxLoraLoaderMixin):
            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)

        prompt = [prompt] if isinstance(prompt, str) else prompt

        if prompt is not None:
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if prompt_embeds is None:
            prompt_embeds, prompt_attention_mask = self._get_t5_prompt_embeds(
                prompt=prompt,
                num_images_per_prompt=num_images_per_prompt,
                max_sequence_length=max_sequence_length,
            )

        dtype = self.text_encoder.dtype if self.text_encoder is not None else self.transformer.dtype
        text_ids = mint.zeros((prompt_embeds.shape[1], 3)).to(dtype=dtype)
        negative_text_ids = None

        if do_classifier_free_guidance:
            if negative_prompt_embeds is None:
                negative_prompt = negative_prompt or ""
                negative_prompt = (
                    batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt
                )

                if prompt is not None and type(prompt) is not type(negative_prompt):
                    raise TypeError(
                        f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                        f" {type(prompt)}."
                    )
                elif batch_size != len(negative_prompt):
                    raise ValueError(
                        f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                        f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                        " the batch size of `prompt`."
                    )

                negative_prompt_embeds, negative_prompt_attention_mask = self._get_t5_prompt_embeds(
                    prompt=negative_prompt,
                    num_images_per_prompt=num_images_per_prompt,
                    max_sequence_length=max_sequence_length,
                )

            negative_text_ids = mint.zeros((negative_prompt_embeds.shape[1], 3)).to(dtype=dtype)

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

        return (
            prompt_embeds,
            text_ids,
            prompt_attention_mask,
            negative_prompt_embeds,
            negative_text_ids,
            negative_prompt_attention_mask,
        )

    # Copied from mindone.diffusers.pipelines.flux.pipeline_flux.FluxPipeline.encode_image
    def encode_image(self, image, num_images_per_prompt):
        dtype = next(self.image_encoder.parameters()).dtype

        if not isinstance(image, ms.Tensor):
            image = self.feature_extractor(image, return_tensors="np").pixel_values
            image = ms.tensor(image)

        image = image.to(dtype=dtype)
        image_embeds = self.image_encoder(image).image_embeds
        image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
        return image_embeds

    def prepare_ip_adapter_image_embeds(self, ip_adapter_image, ip_adapter_image_embeds, num_images_per_prompt):
        image_embeds = []
        if ip_adapter_image_embeds is None:
            if not isinstance(ip_adapter_image, list):
                ip_adapter_image = [ip_adapter_image]

            if len(ip_adapter_image) != self.transformer.encoder_hid_proj.num_ip_adapters:
                raise ValueError(
                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {self.transformer.encoder_hid_proj.num_ip_adapters} IP Adapters."  # noqa
                )

            for single_ip_adapter_image in ip_adapter_image:
                single_image_embeds = self.encode_image(single_ip_adapter_image, 1)
                image_embeds.append(single_image_embeds[None, :])
        else:
            if not isinstance(ip_adapter_image_embeds, list):
                ip_adapter_image_embeds = [ip_adapter_image_embeds]

            if len(ip_adapter_image_embeds) != self.transformer.encoder_hid_proj.num_ip_adapters:
                raise ValueError(
                    f"`ip_adapter_image_embeds` must have same length as the number of IP Adapters. Got {len(ip_adapter_image_embeds)} image embeds and {self.transformer.encoder_hid_proj.num_ip_adapters} IP Adapters."  # noqa
                )

            for single_image_embeds in ip_adapter_image_embeds:
                image_embeds.append(single_image_embeds)

        ip_adapter_image_embeds = []
        for single_image_embeds in image_embeds:
            single_image_embeds = mint.cat([single_image_embeds] * num_images_per_prompt, dim=0)
            ip_adapter_image_embeds.append(single_image_embeds)

        return ip_adapter_image_embeds

    def check_inputs(
        self,
        prompt,
        height,
        width,
        strength,
        negative_prompt=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        prompt_attention_mask=None,
        negative_prompt_attention_mask=None,
        callback_on_step_end_tensor_inputs=None,
        max_sequence_length=None,
    ):
        if strength < 0 or strength > 1:
            raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")

        if height % (self.vae_scale_factor * 2) != 0 or width % (self.vae_scale_factor * 2) != 0:
            logger.warning(
                f"`height` and `width` have to be divisible by {self.vae_scale_factor * 2} but are {height} and {width}. Dimensions will be resized accordingly"
            )

        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
            )

        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 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("Cannot provide `prompt_embeds` without also providing `prompt_attention_mask")

        if negative_prompt_embeds is not None and negative_prompt_attention_mask is None:
            raise ValueError(
                "Cannot provide `negative_prompt_embeds` without also providing `negative_prompt_attention_mask"
            )

        if max_sequence_length is not None and max_sequence_length > 512:
            raise ValueError(f"`max_sequence_length` cannot be greater than 512 but is {max_sequence_length}")

    @staticmethod
    def _prepare_latent_image_ids(height, width, dtype):
        latent_image_ids = mint.zeros((height, width, 3))
        latent_image_ids[..., 1] = latent_image_ids[..., 1] + mint.arange(height)[:, None]
        latent_image_ids[..., 2] = latent_image_ids[..., 2] + mint.arange(width)[None, :]

        latent_image_id_height, latent_image_id_width, latent_image_id_channels = latent_image_ids.shape

        latent_image_ids = latent_image_ids.reshape(
            latent_image_id_height * latent_image_id_width, latent_image_id_channels
        )

        return latent_image_ids.to(dtype=dtype)

    @staticmethod
    def _pack_latents(latents, batch_size, num_channels_latents, height, width):
        latents = latents.view(batch_size, num_channels_latents, height // 2, 2, width // 2, 2)
        latents = latents.permute(0, 2, 4, 1, 3, 5)
        latents = latents.reshape(batch_size, (height // 2) * (width // 2), num_channels_latents * 4)

        return latents

    @staticmethod
    def _unpack_latents(latents, height, width, vae_scale_factor):
        batch_size, num_patches, channels = latents.shape

        # VAE applies 8x compression on images but we must also account for packing which requires
        # latent height and width to be divisible by 2.
        height = 2 * (int(height) // (vae_scale_factor * 2))
        width = 2 * (int(width) // (vae_scale_factor * 2))

        latents = latents.view(batch_size, height // 2, width // 2, channels // 4, 2, 2)
        latents = latents.permute(0, 3, 1, 4, 2, 5)

        latents = latents.reshape(batch_size, channels // (2 * 2), height, width)

        return latents

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

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

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

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

    # Copied from mindone.diffusers.pipelines.stable_diffusion_3.pipeline_stable_diffusion_3_img2img.StableDiffusion3Img2ImgPipeline.get_timesteps
    def get_timesteps(self, num_inference_steps, strength):
        # get the original timestep using init_timestep
        init_timestep = min(num_inference_steps * strength, num_inference_steps)

        t_start = int(max(num_inference_steps - init_timestep, 0))
        timesteps = self.scheduler.timesteps[t_start * self.scheduler.order :]
        if hasattr(self.scheduler, "set_begin_index"):
            self.scheduler.set_begin_index(t_start * self.scheduler.order)

        return timesteps, num_inference_steps - t_start

    def prepare_latents(
        self,
        image,
        timestep,
        batch_size,
        num_channels_latents,
        height,
        width,
        dtype,
        generator,
        latents=None,
    ):
        if isinstance(generator, list) and len(generator) != batch_size:
            raise ValueError(
                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
            )

        # VAE applies 8x compression on images but we must also account for packing which requires
        # latent height and width to be divisible by 2.
        height = 2 * (int(height) // (self.vae_scale_factor * 2))
        width = 2 * (int(width) // (self.vae_scale_factor * 2))
        shape = (batch_size, num_channels_latents, height, width)
        latent_image_ids = self._prepare_latent_image_ids(height // 2, width // 2, dtype)

        if latents is not None:
            return latents.to(dtype=dtype), latent_image_ids

        image = image.to(dtype=dtype)
        if image.shape[1] != self.latent_channels:
            image_latents = self._encode_vae_image(image=image, generator=generator)
        else:
            image_latents = image
        if batch_size > image_latents.shape[0] and batch_size % image_latents.shape[0] == 0:
            # expand init_latents for batch_size
            additional_image_per_prompt = batch_size // image_latents.shape[0]
            image_latents = mint.cat([image_latents] * additional_image_per_prompt, dim=0)
        elif batch_size > image_latents.shape[0] and batch_size % image_latents.shape[0] != 0:
            raise ValueError(
                f"Cannot duplicate `image` of batch size {image_latents.shape[0]} to {batch_size} text prompts."
            )
        else:
            image_latents = mint.cat([image_latents], dim=0)

        noise = randn_tensor(shape, generator=generator, dtype=dtype)
        latents = self.scheduler.scale_noise(image_latents, timestep, noise)
        latents = self._pack_latents(latents, batch_size, num_channels_latents, height, width)
        return latents, latent_image_ids

    def _prepare_attention_mask(
        self,
        batch_size,
        sequence_length,
        dtype,
        attention_mask=None,
    ):
        if attention_mask is None:
            return attention_mask

        # Extend the prompt attention mask to account for image tokens in the final sequence
        attention_mask = mint.cat(
            [attention_mask, mint.ones((batch_size, sequence_length), dtype=attention_mask.dtype)],
            dim=1,
        )
        attention_mask = attention_mask.to(dtype)

        return attention_mask

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

    @property
    def joint_attention_kwargs(self):
        return self._joint_attention_kwargs

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

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

    @property
    def current_timestep(self):
        return self._current_timestep

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

    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        negative_prompt: Union[str, List[str]] = None,
        image: PipelineImageInput = None,
        height: Optional[int] = None,
        width: Optional[int] = None,
        num_inference_steps: int = 35,
        sigmas: Optional[List[float]] = None,
        guidance_scale: float = 5.0,
        strength: float = 0.9,
        num_images_per_prompt: Optional[int] = 1,
        generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
        latents: Optional[ms.Tensor] = None,
        prompt_embeds: Optional[ms.Tensor] = None,
        ip_adapter_image: Optional[PipelineImageInput] = None,
        ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
        negative_ip_adapter_image: Optional[PipelineImageInput] = None,
        negative_ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
        negative_prompt_embeds: Optional[ms.Tensor] = None,
        prompt_attention_mask: Optional[ms.Tensor] = None,
        negative_prompt_attention_mask: Optional[ms.Tensor] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = False,
        joint_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 = 512,
    ):
        r"""
        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
                not greater than `1`).
            height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                The height in pixels of the generated image. This is set to 1024 by default for the best results.
            width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                The width in pixels of the generated image. This is set to 1024 by default for the best results.
            num_inference_steps (`int`, *optional*, defaults to 35):
                The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                expense of slower inference.
            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 5.0):
                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
                `guidance_scale` is defined as `w` of equation 2. of [Imagen
                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
                usually at the expense of lower image quality.
            strength (`float, *optional*, defaults to 0.9):
                Conceptually, indicates how much to transform the reference image. Must be between 0 and 1. image will
                be used as a starting point, adding more noise to it the larger the strength. The number of denoising
                steps depends on the amount of noise initially added. When strength is 1, added noise will be maximum
                and the denoising process will run for the full number of iterations specified in num_inference_steps.
                A value of 1, therefore, essentially ignores image.
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
                One or a list of [np.random.Generator(s)](https://numpy.org/doc/stable/reference/random/generator.html)
                to make generation deterministic.
            latents (`ms.Tensor`, *optional*):
                Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
                tensor will ge generated by sampling using the supplied random `generator`.
            prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
            ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. If not
                provided, embeddings are computed from the `ip_adapter_image` input argument.
            negative_ip_adapter_image:
                (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
            negative_ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. If not
                provided, embeddings are computed from the `ip_adapter_image` input argument.
            negative_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                argument.
            prompt_attention_mask (ms.Tensor, *optional*):
                Attention mask for the prompt embeddings. Used to mask out padding tokens in the prompt sequence.
                Chroma requires a single padding token remain unmasked. Please refer to
                https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training
            negative_prompt_attention_mask (ms.Tensor, *optional*):
                Attention mask for the negative prompt embeddings. Used to mask out padding tokens in the negative
                prompt sequence. Chroma requires a single padding token remain unmasked. PLease refer to
                https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training
            output_type (`str`, *optional*, defaults to `"pil"`):
                The output format of the generate image. Choose between
                [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
            return_dict (`bool`, *optional*, defaults to `True`):
                Whether or not to return a [`~pipelines.flux.ChromaPipelineOutput`] instead of a plain tuple.
            joint_attention_kwargs (`dict`, *optional*):
                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).
            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 512): Maximum sequence length to use with the `prompt`.

        Examples:

        Returns:
            [`~pipelines.chroma.ChromaPipelineOutput`] or `tuple`: [`~pipelines.chroma.ChromaPipelineOutput`] if
            `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is a list with the
            generated images.
        """

        height = height or self.default_sample_size * self.vae_scale_factor
        width = width or self.default_sample_size * self.vae_scale_factor

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            prompt,
            height,
            width,
            strength,
            negative_prompt=negative_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            prompt_attention_mask=prompt_attention_mask,
            negative_prompt_attention_mask=negative_prompt_attention_mask,
            callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
            max_sequence_length=max_sequence_length,
        )

        self._guidance_scale = guidance_scale
        self._joint_attention_kwargs = joint_attention_kwargs
        self._current_timestep = None
        self._interrupt = False

        # 2. Preprocess image
        init_image = self.image_processor.preprocess(image, height=height, width=width)
        init_image = init_image.to(dtype=ms.float32)

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

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

        (
            prompt_embeds,
            text_ids,
            prompt_attention_mask,
            negative_prompt_embeds,
            negative_text_ids,
            negative_prompt_attention_mask,
        ) = self.encode_prompt(
            prompt=prompt,
            negative_prompt=negative_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
            prompt_attention_mask=prompt_attention_mask,
            negative_prompt_attention_mask=negative_prompt_attention_mask,
            do_classifier_free_guidance=self.do_classifier_free_guidance,
            num_images_per_prompt=num_images_per_prompt,
            max_sequence_length=max_sequence_length,
            lora_scale=lora_scale,
        )

        # 4. Prepare timesteps
        sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
        image_seq_len = (int(height) // self.vae_scale_factor // 2) * (int(width) // self.vae_scale_factor // 2)
        mu = calculate_shift(
            image_seq_len,
            self.scheduler.config.get("base_image_seq_len", 256),
            self.scheduler.config.get("max_image_seq_len", 4096),
            self.scheduler.config.get("base_shift", 0.5),
            self.scheduler.config.get("max_shift", 1.15),
        )
        timesteps, num_inference_steps = retrieve_timesteps(
            self.scheduler,
            num_inference_steps,
            sigmas=sigmas,
            mu=mu,
        )
        timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, strength)

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

        if num_inference_steps < 1:
            raise ValueError(
                f"After adjusting the num_inference_steps by strength parameter: {strength}, the number of pipeline"
                f"steps is {num_inference_steps} which is < 1 and not appropriate for this pipeline."
            )
        latent_timestep = timesteps[:1].repeat(batch_size * num_images_per_prompt)

        # 5. Prepare latent variables
        num_channels_latents = self.transformer.config.in_channels // 4
        latents, latent_image_ids = self.prepare_latents(
            init_image,
            latent_timestep,
            batch_size * num_images_per_prompt,
            num_channels_latents,
            height,
            width,
            prompt_embeds.dtype,
            generator,
            latents,
        )

        attention_mask = self._prepare_attention_mask(
            batch_size=latents.shape[0],
            sequence_length=image_seq_len,
            dtype=latents.dtype,
            attention_mask=prompt_attention_mask,
        )
        negative_attention_mask = self._prepare_attention_mask(
            batch_size=latents.shape[0],
            sequence_length=image_seq_len,
            dtype=latents.dtype,
            attention_mask=negative_prompt_attention_mask,
        )

        # 6. Prepare image embeddings
        if (ip_adapter_image is not None or ip_adapter_image_embeds is not None) and (
            negative_ip_adapter_image is None and negative_ip_adapter_image_embeds is None
        ):
            negative_ip_adapter_image = np.zeros((width, height, 3), dtype=np.uint8)
            negative_ip_adapter_image = [negative_ip_adapter_image] * self.transformer.encoder_hid_proj.num_ip_adapters

        elif (ip_adapter_image is None and ip_adapter_image_embeds is None) and (
            negative_ip_adapter_image is not None or negative_ip_adapter_image_embeds is not None
        ):
            ip_adapter_image = np.zeros((width, height, 3), dtype=np.uint8)
            ip_adapter_image = [ip_adapter_image] * self.transformer.encoder_hid_proj.num_ip_adapters

        if self.joint_attention_kwargs is None:
            self._joint_attention_kwargs = {}

        image_embeds = None
        negative_image_embeds = None
        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
            image_embeds = self.prepare_ip_adapter_image_embeds(
                ip_adapter_image,
                ip_adapter_image_embeds,
                batch_size * num_images_per_prompt,
            )
        if negative_ip_adapter_image is not None or negative_ip_adapter_image_embeds is not None:
            negative_image_embeds = self.prepare_ip_adapter_image_embeds(
                negative_ip_adapter_image,
                negative_ip_adapter_image_embeds,
                batch_size * num_images_per_prompt,
            )

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

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

                if image_embeds is not None:
                    self._joint_attention_kwargs["ip_adapter_image_embeds"] = image_embeds

                noise_pred = self.transformer(
                    hidden_states=latents,
                    timestep=timestep / 1000,
                    encoder_hidden_states=prompt_embeds,
                    txt_ids=text_ids,
                    img_ids=latent_image_ids,
                    attention_mask=attention_mask,
                    joint_attention_kwargs=self.joint_attention_kwargs,
                    return_dict=False,
                )[0]

                if self.do_classifier_free_guidance:
                    if negative_image_embeds is not None:
                        self._joint_attention_kwargs["ip_adapter_image_embeds"] = negative_image_embeds

                    noise_pred_uncond = self.transformer(
                        hidden_states=latents,
                        timestep=timestep / 1000,
                        encoder_hidden_states=negative_prompt_embeds,
                        txt_ids=negative_text_ids,
                        img_ids=latent_image_ids,
                        attention_mask=negative_attention_mask,
                        joint_attention_kwargs=self.joint_attention_kwargs,
                        return_dict=False,
                    )[0]
                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred - noise_pred_uncond)

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

                # 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()

        self._current_timestep = None

        if output_type == "latent":
            image = latents
        else:
            latents = self._unpack_latents(latents, height, width, self.vae_scale_factor)
            latents = (latents / self.vae.config.scaling_factor) + self.vae.config.shift_factor
            image = self.vae.decode(latents, return_dict=False)[0]
            image = self.image_processor.postprocess(image, output_type=output_type)

        if not return_dict:
            return (image,)

        return ChromaPipelineOutput(images=image)

mindone.diffusers.ChromaImg2ImgPipeline.__call__(prompt=None, negative_prompt=None, image=None, height=None, width=None, num_inference_steps=35, sigmas=None, guidance_scale=5.0, strength=0.9, num_images_per_prompt=1, generator=None, latents=None, prompt_embeds=None, ip_adapter_image=None, ip_adapter_image_embeds=None, negative_ip_adapter_image=None, negative_ip_adapter_image_embeds=None, negative_prompt_embeds=None, prompt_attention_mask=None, negative_prompt_attention_mask=None, output_type='pil', return_dict=False, joint_attention_kwargs=None, callback_on_step_end=None, callback_on_step_end_tensor_inputs=['latents'], max_sequence_length=512)

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 not greater than 1). TYPE: `str` or `List[str]`, *optional* DEFAULT: None
height	The height in pixels of the generated image. This is set to 1024 by default for the best results. TYPE: `int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor DEFAULT: None
width	The width in pixels of the generated image. This is set to 1024 by default for the best results. TYPE: `int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor DEFAULT: None
num_inference_steps	The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. TYPE: `int`, *optional*, defaults to 35 DEFAULT: 35
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 5.0 DEFAULT: 5.0
strength	Conceptually, indicates how much to transform the reference image. Must be between 0 and 1. image will be used as a starting point, adding more noise to it the larger the strength. The number of denoising steps depends on the amount of noise initially added. When strength is 1, added noise will be maximum and the denoising process will run for the full number of iterations specified in num_inference_steps. A value of 1, therefore, essentially ignores image. TYPE: `float, *optional*, defaults to 0.9 DEFAULT: 0.9
num_images_per_prompt	The number of images to generate per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
generator	One or a list of np.random.Generator(s) to make generation deterministic. TYPE: `np.random.Generator` or `List[np.random.Generator]`, *optional* DEFAULT: None
latents	Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied random generator. TYPE: `ms.Tensor`, *optional* DEFAULT: None
prompt_embeds	Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument. TYPE: `ms.Tensor`, *optional* DEFAULT: None
ip_adapter_image	(PipelineImageInput, optional): Optional image input to work with IP Adapters. TYPE: Optional[PipelineImageInput] DEFAULT: None
ip_adapter_image_embeds	Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters. Each element should be a tensor of shape (batch_size, num_images, emb_dim). If not provided, embeddings are computed from the ip_adapter_image input argument. TYPE: `List[ms.Tensor]`, *optional* DEFAULT: None
negative_ip_adapter_image	(PipelineImageInput, optional): Optional image input to work with IP Adapters. TYPE: Optional[PipelineImageInput] DEFAULT: None
negative_ip_adapter_image_embeds	Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters. Each element should be a tensor of shape (batch_size, num_images, emb_dim). If not provided, embeddings are computed from the ip_adapter_image input argument. TYPE: `List[ms.Tensor]`, *optional* DEFAULT: None
negative_prompt_embeds	Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument. TYPE: `ms.Tensor`, *optional* DEFAULT: None
prompt_attention_mask	Attention mask for the prompt embeddings. Used to mask out padding tokens in the prompt sequence. Chroma requires a single padding token remain unmasked. Please refer to https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training TYPE: ms.Tensor, *optional* DEFAULT: None
negative_prompt_attention_mask	Attention mask for the negative prompt embeddings. Used to mask out padding tokens in the negative prompt sequence. Chroma requires a single padding token remain unmasked. PLease refer to https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training 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.flux.ChromaPipelineOutput] instead of a plain tuple. TYPE: `bool`, *optional*, defaults to `True` DEFAULT: False
joint_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: `dict`, *optional* DEFAULT: None
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 512 DEFAULT: 512

RETURNS	DESCRIPTION
	[~pipelines.chroma.ChromaPipelineOutput] or tuple: [~pipelines.chroma.ChromaPipelineOutput] if
	return_dict is True, otherwise a tuple. When returning a tuple, the first element is a list with the
	generated images.

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma_img2img.py

def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    negative_prompt: Union[str, List[str]] = None,
    image: PipelineImageInput = None,
    height: Optional[int] = None,
    width: Optional[int] = None,
    num_inference_steps: int = 35,
    sigmas: Optional[List[float]] = None,
    guidance_scale: float = 5.0,
    strength: float = 0.9,
    num_images_per_prompt: Optional[int] = 1,
    generator: Optional[Union[np.random.Generator, List[np.random.Generator]]] = None,
    latents: Optional[ms.Tensor] = None,
    prompt_embeds: Optional[ms.Tensor] = None,
    ip_adapter_image: Optional[PipelineImageInput] = None,
    ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
    negative_ip_adapter_image: Optional[PipelineImageInput] = None,
    negative_ip_adapter_image_embeds: Optional[List[ms.Tensor]] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    output_type: Optional[str] = "pil",
    return_dict: bool = False,
    joint_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 = 512,
):
    r"""
    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
            not greater than `1`).
        height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
            The height in pixels of the generated image. This is set to 1024 by default for the best results.
        width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
            The width in pixels of the generated image. This is set to 1024 by default for the best results.
        num_inference_steps (`int`, *optional*, defaults to 35):
            The number of denoising steps. More denoising steps usually lead to a higher quality image at the
            expense of slower inference.
        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 5.0):
            Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
            `guidance_scale` is defined as `w` of equation 2. of [Imagen
            Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
            1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
            usually at the expense of lower image quality.
        strength (`float, *optional*, defaults to 0.9):
            Conceptually, indicates how much to transform the reference image. Must be between 0 and 1. image will
            be used as a starting point, adding more noise to it the larger the strength. The number of denoising
            steps depends on the amount of noise initially added. When strength is 1, added noise will be maximum
            and the denoising process will run for the full number of iterations specified in num_inference_steps.
            A value of 1, therefore, essentially ignores image.
        num_images_per_prompt (`int`, *optional*, defaults to 1):
            The number of images to generate per prompt.
        generator (`np.random.Generator` or `List[np.random.Generator]`, *optional*):
            One or a list of [np.random.Generator(s)](https://numpy.org/doc/stable/reference/random/generator.html)
            to make generation deterministic.
        latents (`ms.Tensor`, *optional*):
            Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
            generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
            tensor will ge generated by sampling using the supplied random `generator`.
        prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
            provided, text embeddings will be generated from `prompt` input argument.
        ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
        ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
            Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
            IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. If not
            provided, embeddings are computed from the `ip_adapter_image` input argument.
        negative_ip_adapter_image:
            (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
        negative_ip_adapter_image_embeds (`List[ms.Tensor]`, *optional*):
            Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
            IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. If not
            provided, embeddings are computed from the `ip_adapter_image` input argument.
        negative_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
            weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
            argument.
        prompt_attention_mask (ms.Tensor, *optional*):
            Attention mask for the prompt embeddings. Used to mask out padding tokens in the prompt sequence.
            Chroma requires a single padding token remain unmasked. Please refer to
            https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training
        negative_prompt_attention_mask (ms.Tensor, *optional*):
            Attention mask for the negative prompt embeddings. Used to mask out padding tokens in the negative
            prompt sequence. Chroma requires a single padding token remain unmasked. PLease refer to
            https://huggingface.co/lodestones/Chroma#tldr-masking-t5-padding-tokens-enhanced-fidelity-and-increased-stability-during-training
        output_type (`str`, *optional*, defaults to `"pil"`):
            The output format of the generate image. Choose between
            [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
        return_dict (`bool`, *optional*, defaults to `True`):
            Whether or not to return a [`~pipelines.flux.ChromaPipelineOutput`] instead of a plain tuple.
        joint_attention_kwargs (`dict`, *optional*):
            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).
        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 512): Maximum sequence length to use with the `prompt`.

    Examples:

    Returns:
        [`~pipelines.chroma.ChromaPipelineOutput`] or `tuple`: [`~pipelines.chroma.ChromaPipelineOutput`] if
        `return_dict` is True, otherwise a `tuple`. When returning a tuple, the first element is a list with the
        generated images.
    """

    height = height or self.default_sample_size * self.vae_scale_factor
    width = width or self.default_sample_size * self.vae_scale_factor

    # 1. Check inputs. Raise error if not correct
    self.check_inputs(
        prompt,
        height,
        width,
        strength,
        negative_prompt=negative_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        prompt_attention_mask=prompt_attention_mask,
        negative_prompt_attention_mask=negative_prompt_attention_mask,
        callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
        max_sequence_length=max_sequence_length,
    )

    self._guidance_scale = guidance_scale
    self._joint_attention_kwargs = joint_attention_kwargs
    self._current_timestep = None
    self._interrupt = False

    # 2. Preprocess image
    init_image = self.image_processor.preprocess(image, height=height, width=width)
    init_image = init_image.to(dtype=ms.float32)

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

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

    (
        prompt_embeds,
        text_ids,
        prompt_attention_mask,
        negative_prompt_embeds,
        negative_text_ids,
        negative_prompt_attention_mask,
    ) = self.encode_prompt(
        prompt=prompt,
        negative_prompt=negative_prompt,
        prompt_embeds=prompt_embeds,
        negative_prompt_embeds=negative_prompt_embeds,
        prompt_attention_mask=prompt_attention_mask,
        negative_prompt_attention_mask=negative_prompt_attention_mask,
        do_classifier_free_guidance=self.do_classifier_free_guidance,
        num_images_per_prompt=num_images_per_prompt,
        max_sequence_length=max_sequence_length,
        lora_scale=lora_scale,
    )

    # 4. Prepare timesteps
    sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps) if sigmas is None else sigmas
    image_seq_len = (int(height) // self.vae_scale_factor // 2) * (int(width) // self.vae_scale_factor // 2)
    mu = calculate_shift(
        image_seq_len,
        self.scheduler.config.get("base_image_seq_len", 256),
        self.scheduler.config.get("max_image_seq_len", 4096),
        self.scheduler.config.get("base_shift", 0.5),
        self.scheduler.config.get("max_shift", 1.15),
    )
    timesteps, num_inference_steps = retrieve_timesteps(
        self.scheduler,
        num_inference_steps,
        sigmas=sigmas,
        mu=mu,
    )
    timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, strength)

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

    if num_inference_steps < 1:
        raise ValueError(
            f"After adjusting the num_inference_steps by strength parameter: {strength}, the number of pipeline"
            f"steps is {num_inference_steps} which is < 1 and not appropriate for this pipeline."
        )
    latent_timestep = timesteps[:1].repeat(batch_size * num_images_per_prompt)

    # 5. Prepare latent variables
    num_channels_latents = self.transformer.config.in_channels // 4
    latents, latent_image_ids = self.prepare_latents(
        init_image,
        latent_timestep,
        batch_size * num_images_per_prompt,
        num_channels_latents,
        height,
        width,
        prompt_embeds.dtype,
        generator,
        latents,
    )

    attention_mask = self._prepare_attention_mask(
        batch_size=latents.shape[0],
        sequence_length=image_seq_len,
        dtype=latents.dtype,
        attention_mask=prompt_attention_mask,
    )
    negative_attention_mask = self._prepare_attention_mask(
        batch_size=latents.shape[0],
        sequence_length=image_seq_len,
        dtype=latents.dtype,
        attention_mask=negative_prompt_attention_mask,
    )

    # 6. Prepare image embeddings
    if (ip_adapter_image is not None or ip_adapter_image_embeds is not None) and (
        negative_ip_adapter_image is None and negative_ip_adapter_image_embeds is None
    ):
        negative_ip_adapter_image = np.zeros((width, height, 3), dtype=np.uint8)
        negative_ip_adapter_image = [negative_ip_adapter_image] * self.transformer.encoder_hid_proj.num_ip_adapters

    elif (ip_adapter_image is None and ip_adapter_image_embeds is None) and (
        negative_ip_adapter_image is not None or negative_ip_adapter_image_embeds is not None
    ):
        ip_adapter_image = np.zeros((width, height, 3), dtype=np.uint8)
        ip_adapter_image = [ip_adapter_image] * self.transformer.encoder_hid_proj.num_ip_adapters

    if self.joint_attention_kwargs is None:
        self._joint_attention_kwargs = {}

    image_embeds = None
    negative_image_embeds = None
    if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
        image_embeds = self.prepare_ip_adapter_image_embeds(
            ip_adapter_image,
            ip_adapter_image_embeds,
            batch_size * num_images_per_prompt,
        )
    if negative_ip_adapter_image is not None or negative_ip_adapter_image_embeds is not None:
        negative_image_embeds = self.prepare_ip_adapter_image_embeds(
            negative_ip_adapter_image,
            negative_ip_adapter_image_embeds,
            batch_size * num_images_per_prompt,
        )

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

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

            if image_embeds is not None:
                self._joint_attention_kwargs["ip_adapter_image_embeds"] = image_embeds

            noise_pred = self.transformer(
                hidden_states=latents,
                timestep=timestep / 1000,
                encoder_hidden_states=prompt_embeds,
                txt_ids=text_ids,
                img_ids=latent_image_ids,
                attention_mask=attention_mask,
                joint_attention_kwargs=self.joint_attention_kwargs,
                return_dict=False,
            )[0]

            if self.do_classifier_free_guidance:
                if negative_image_embeds is not None:
                    self._joint_attention_kwargs["ip_adapter_image_embeds"] = negative_image_embeds

                noise_pred_uncond = self.transformer(
                    hidden_states=latents,
                    timestep=timestep / 1000,
                    encoder_hidden_states=negative_prompt_embeds,
                    txt_ids=negative_text_ids,
                    img_ids=latent_image_ids,
                    attention_mask=negative_attention_mask,
                    joint_attention_kwargs=self.joint_attention_kwargs,
                    return_dict=False,
                )[0]
                noise_pred = noise_pred_uncond + guidance_scale * (noise_pred - noise_pred_uncond)

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

            # 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()

    self._current_timestep = None

    if output_type == "latent":
        image = latents
    else:
        latents = self._unpack_latents(latents, height, width, self.vae_scale_factor)
        latents = (latents / self.vae.config.scaling_factor) + self.vae.config.shift_factor
        image = self.vae.decode(latents, return_dict=False)[0]
        image = self.image_processor.postprocess(image, output_type=output_type)

    if not return_dict:
        return (image,)

    return ChromaPipelineOutput(images=image)

mindone.diffusers.ChromaImg2ImgPipeline.disable_vae_slicing()

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

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma_img2img.py

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

mindone.diffusers.ChromaImg2ImgPipeline.disable_vae_tiling()

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

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma_img2img.py

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

mindone.diffusers.ChromaImg2ImgPipeline.enable_vae_slicing()

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

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma_img2img.py

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

mindone.diffusers.ChromaImg2ImgPipeline.enable_vae_tiling()

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

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma_img2img.py

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

mindone.diffusers.ChromaImg2ImgPipeline.encode_prompt(prompt, negative_prompt=None, num_images_per_prompt=1, prompt_embeds=None, negative_prompt_embeds=None, prompt_attention_mask=None, negative_prompt_attention_mask=None, do_classifier_free_guidance=True, max_sequence_length=512, lora_scale=None)

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). TYPE: `str` or `List[str]`, *optional* DEFAULT: None
num_images_per_prompt	number of images that should be generated per prompt TYPE: `int` 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
lora_scale	A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded. TYPE: `float`, *optional* DEFAULT: None

Source code in mindone/diffusers/pipelines/chroma/pipeline_chroma_img2img.py

def encode_prompt(
    self,
    prompt: Union[str, List[str]],
    negative_prompt: Union[str, List[str]] = None,
    num_images_per_prompt: int = 1,
    prompt_embeds: Optional[ms.Tensor] = None,
    negative_prompt_embeds: Optional[ms.Tensor] = None,
    prompt_attention_mask: Optional[ms.Tensor] = None,
    negative_prompt_attention_mask: Optional[ms.Tensor] = None,
    do_classifier_free_guidance: bool = True,
    max_sequence_length: int = 512,
    lora_scale: Optional[float] = None,
):
    r"""

    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`).
        num_images_per_prompt (`int`):
            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.
        lora_scale (`float`, *optional*):
            A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.
    """
    # 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, FluxLoraLoaderMixin):
        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)

    prompt = [prompt] if isinstance(prompt, str) else prompt

    if prompt is not None:
        batch_size = len(prompt)
    else:
        batch_size = prompt_embeds.shape[0]

    if prompt_embeds is None:
        prompt_embeds, prompt_attention_mask = self._get_t5_prompt_embeds(
            prompt=prompt,
            num_images_per_prompt=num_images_per_prompt,
            max_sequence_length=max_sequence_length,
        )

    dtype = self.text_encoder.dtype if self.text_encoder is not None else self.transformer.dtype
    text_ids = mint.zeros((prompt_embeds.shape[1], 3)).to(dtype=dtype)
    negative_text_ids = None

    if do_classifier_free_guidance:
        if negative_prompt_embeds is None:
            negative_prompt = negative_prompt or ""
            negative_prompt = (
                batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt
            )

            if prompt is not None and type(prompt) is not type(negative_prompt):
                raise TypeError(
                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                    f" {type(prompt)}."
                )
            elif batch_size != len(negative_prompt):
                raise ValueError(
                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                    " the batch size of `prompt`."
                )

            negative_prompt_embeds, negative_prompt_attention_mask = self._get_t5_prompt_embeds(
                prompt=negative_prompt,
                num_images_per_prompt=num_images_per_prompt,
                max_sequence_length=max_sequence_length,
            )

        negative_text_ids = mint.zeros((negative_prompt_embeds.shape[1], 3)).to(dtype=dtype)

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

    return (
        prompt_embeds,
        text_ids,
        prompt_attention_mask,
        negative_prompt_embeds,
        negative_text_ids,
        negative_prompt_attention_mask,
    )