FluxControlInpaint

FluxControlInpaintPipeline is an implementation of Inpainting for Flux.1 Depth/Canny models. It is a pipeline that allows you to inpaint images using the Flux.1 Depth/Canny models. The pipeline takes an image and a mask as input and returns the inpainted image.

FLUX.1 Depth and Canny [dev] is a 12 billion parameter rectified flow transformer capable of generating an image based on a text description while following the structure of a given input image. This is not a ControlNet model.

Control type	Developer	Link
Depth	Black Forest Labs	Link
Canny	Black Forest Labs	Link

Tip

Flux can be quite expensive to run on consumer hardware devices. However, you can perform a suite of optimizations to run it faster and in a more memory-friendly manner. Check out this section for more details. Additionally, Flux can benefit from quantization for memory efficiency with a trade-off in inference latency. Refer to this blog post to learn more. For an exhaustive list of resources, check out this gist.

import mindspore as ms
from mindone.diffusers import FluxControlInpaintPipeline
from mindone.diffusers.models.transformers import FluxTransformer2DModel
from mindone.transformers import T5EncoderModel
from mindone.diffusers.utils import load_image, make_image_grid
from image_gen_aux import DepthPreprocessor # https://github.com/huggingface/image_gen_aux
from PIL import Image
import numpy as np

pipe = FluxControlInpaintPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-Depth-dev",
    mindspore_dtype=ms.bfloat16,
)
# use following lines if you have NPU constraints
# ---------------------------------------------------------------
transformer = FluxTransformer2DModel.from_pretrained(
    "sayakpaul/FLUX.1-Depth-dev-nf4", subfolder="transformer", mindspore_dtype=ms.bfloat16
)
text_encoder_2 = T5EncoderModel.from_pretrained(
    "sayakpaul/FLUX.1-Depth-dev-nf4", subfolder="text_encoder_2", mindspore_dtype=ms.bfloat16
)
pipe.transformer = transformer
pipe.text_encoder_2 = text_encoder_2
# ---------------------------------------------------------------

prompt = "a blue robot singing opera with human-like expressions"
image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")

head_mask = np.zeros_like(image)
head_mask[65:580,300:642] = 255
mask_image = Image.fromarray(head_mask)

processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
control_image = processor(image)[0].convert("RGB")

output = pipe(
    prompt=prompt,
    image=image,
    control_image=control_image,
    mask_image=mask_image,
    num_inference_steps=30,
    strength=0.9,
    guidance_scale=10.0,
    generator=np.random.default_rng(42),
)[0][0]
make_image_grid([image, control_image, mask_image, output.resize(image.size)], rows=1, cols=4).save("output.png")

mindone.diffusers.FluxControlInpaintPipeline

Bases: DiffusionPipeline, FluxLoraLoaderMixin, FromSingleFileMixin, TextualInversionLoaderMixin

The Flux pipeline for image inpainting using Flux-dev-Depth/Canny.

Reference: https://blackforestlabs.ai/announcing-black-forest-labs/

PARAMETER	DESCRIPTION
transformer	Conditional Transformer (MMDiT) architecture to denoise the encoded image latents. TYPE: [`FluxTransformer2DModel`]
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 representations. TYPE: [`AutoencoderKL`]
text_encoder	CLIP, specifically the clip-vit-large-patch14 variant. TYPE: [`CLIPTextModel`]
text_encoder_2	T5, specifically the google/t5-v1_1-xxl variant. TYPE: [`T5EncoderModel`]
tokenizer	Tokenizer of class CLIPTokenizer. TYPE: `CLIPTokenizer`
tokenizer_2	Second Tokenizer of class T5TokenizerFast. TYPE: `T5TokenizerFast`

Source code in mindone/diffusers/pipelines/flux/pipeline_flux_control_inpaint.py

class FluxControlInpaintPipeline(
    DiffusionPipeline,
    FluxLoraLoaderMixin,
    FromSingleFileMixin,
    TextualInversionLoaderMixin,
):
    r"""
    The Flux pipeline for image inpainting using Flux-dev-Depth/Canny.

    Reference: https://blackforestlabs.ai/announcing-black-forest-labs/

    Args:
        transformer ([`FluxTransformer2DModel`]):
            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 representations.
        text_encoder ([`CLIPTextModel`]):
            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel), specifically
            the [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) variant.
        text_encoder_2 ([`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 (`CLIPTokenizer`):
            Tokenizer of class
            [CLIPTokenizer](https://huggingface.co/docs/transformers/en/model_doc/clip#transformers.CLIPTokenizer).
        tokenizer_2 (`T5TokenizerFast`):
            Second Tokenizer of class
            [T5TokenizerFast](https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5TokenizerFast).
    """

    model_cpu_offload_seq = "text_encoder->text_encoder_2->transformer->vae"
    _optional_components = []
    _callback_tensor_inputs = ["latents", "prompt_embeds"]

    def __init__(
        self,
        scheduler: FlowMatchEulerDiscreteScheduler,
        vae: AutoencoderKL,
        text_encoder: CLIPTextModel,
        tokenizer: CLIPTokenizer,
        text_encoder_2: T5EncoderModel,
        tokenizer_2: T5TokenizerFast,
        transformer: FluxTransformer2DModel,
    ):
        super().__init__()

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            text_encoder_2=text_encoder_2,
            tokenizer=tokenizer,
            tokenizer_2=tokenizer_2,
            transformer=transformer,
            scheduler=scheduler,
        )
        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)
        latent_channels = self.vae.config.latent_channels if getattr(self, "vae", None) else 16
        self.mask_processor = VaeImageProcessor(
            vae_scale_factor=self.vae_scale_factor * 2,
            vae_latent_channels=latent_channels,
            do_normalize=False,
            do_binarize=True,
            do_convert_grayscale=True,
        )
        self.tokenizer_max_length = (
            self.tokenizer.model_max_length if hasattr(self, "tokenizer") and self.tokenizer is not None else 77
        )
        self.default_sample_size = 128

    # Copied from diffusers.pipelines.flux.pipeline_flux.FluxPipeline._get_t5_prompt_embeds
    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_2)

        text_inputs = self.tokenizer_2(
            prompt,
            padding="max_length",
            max_length=max_sequence_length,
            truncation=True,
            return_length=False,
            return_overflowing_tokens=False,
            return_tensors="np",
        )
        text_input_ids = text_inputs.input_ids
        untruncated_ids = self.tokenizer_2(prompt, padding="longest", return_tensors="np").input_ids

        if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
            text_input_ids, untruncated_ids
        ):
            removed_text = self.tokenizer_2.batch_decode(untruncated_ids[:, self.tokenizer_max_length - 1 : -1])
            logger.warning(
                "The following part of your input was truncated because `max_sequence_length` is set to "
                f" {max_sequence_length} tokens: {removed_text}"
            )

        prompt_embeds = self.text_encoder_2(ms.tensor(text_input_ids), output_hidden_states=False)[0]

        dtype = self.text_encoder_2.dtype
        prompt_embeds = prompt_embeds.to(dtype=dtype)

        _, seq_len, _ = prompt_embeds.shape

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

        return prompt_embeds

    # Copied from diffusers.pipelines.flux.pipeline_flux.FluxPipeline._get_clip_prompt_embeds
    def _get_clip_prompt_embeds(
        self,
        prompt: Union[str, List[str]],
        num_images_per_prompt: int = 1,
    ):
        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=self.tokenizer_max_length,
            truncation=True,
            return_overflowing_tokens=False,
            return_length=False,
            return_tensors="np",
        )

        text_input_ids = text_inputs.input_ids
        untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="np").input_ids
        if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not np.array_equal(
            text_input_ids, untruncated_ids
        ):
            removed_text = self.tokenizer.batch_decode(untruncated_ids[:, self.tokenizer_max_length - 1 : -1])
            logger.warning(
                "The following part of your input was truncated because CLIP can only handle sequences up to"
                f" {self.tokenizer_max_length} tokens: {removed_text}"
            )
        prompt_embeds = self.text_encoder(ms.tensor(text_input_ids), output_hidden_states=False)

        # Use pooled output of CLIPTextModel
        prompt_embeds = prompt_embeds[1]
        prompt_embeds = prompt_embeds.to(dtype=self.text_encoder.dtype)

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

        return prompt_embeds

    # Copied from diffusers.pipelines.flux.pipeline_flux.FluxPipeline.encode_prompt
    def encode_prompt(
        self,
        prompt: Union[str, List[str]],
        prompt_2: Optional[Union[str, List[str]]] = None,
        num_images_per_prompt: int = 1,
        prompt_embeds: Optional[ms.Tensor] = None,
        pooled_prompt_embeds: Optional[ms.Tensor] = None,
        max_sequence_length: int = 512,
        lora_scale: Optional[float] = None,
    ):
        r"""

        Args:
            prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            prompt_2 (`str` or `List[str]`, *optional*):
                The prompt or prompts to be sent to the `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
                used in all text-encoders
            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.
            pooled_prompt_embeds (`ms.Tensor`, *optional*):
                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
                If not provided, pooled 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)
            if self.text_encoder_2 is not None:
                scale_lora_layers(self.text_encoder_2, lora_scale)

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

        if prompt_embeds is None:
            prompt_2 = prompt_2 or prompt
            prompt_2 = [prompt_2] if isinstance(prompt_2, str) else prompt_2

            # We only use the pooled prompt output from the CLIPTextModel
            pooled_prompt_embeds = self._get_clip_prompt_embeds(
                prompt=prompt,
                num_images_per_prompt=num_images_per_prompt,
            )
            prompt_embeds = self._get_t5_prompt_embeds(
                prompt=prompt_2,
                num_images_per_prompt=num_images_per_prompt,
                max_sequence_length=max_sequence_length,
            )

        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)

        if self.text_encoder_2 is not None:
            if isinstance(self, FluxLoraLoaderMixin):
                # Retrieve the original scale by scaling back the LoRA layers
                unscale_lora_layers(self.text_encoder_2, lora_scale)

        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)

        return prompt_embeds, pooled_prompt_embeds, text_ids

    # Copied from 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.encode(image[i : i + 1]), 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

    # Copied from 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 check_inputs(
        self,
        prompt,
        prompt_2,
        strength,
        height,
        width,
        prompt_embeds=None,
        pooled_prompt_embeds=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 E501
            )

        if prompt is not None and prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
                " only forward one of the two."
            )
        elif prompt_2 is not None and prompt_embeds is not None:
            raise ValueError(
                f"Cannot forward both `prompt_2`: {prompt_2} 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)}")
        elif prompt_2 is not None and (not isinstance(prompt_2, str) and not isinstance(prompt_2, list)):
            raise ValueError(f"`prompt_2` has to be of type `str` or `list` but is {type(prompt_2)}")

        if prompt_embeds is not None and pooled_prompt_embeds is None:
            raise ValueError(
                "If `prompt_embeds` are provided, `pooled_prompt_embeds` also have to be passed. Make sure to generate `pooled_prompt_embeds` from the same text encoder that was used to generate `prompt_embeds`."  # noqa E501
            )

        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
    # Copied from diffusers.pipelines.flux.pipeline_flux.FluxPipeline._prepare_latent_image_ids
    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
    # Copied from diffusers.pipelines.flux.pipeline_flux.FluxPipeline._pack_latents
    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
    # Copied from diffusers.pipelines.flux.pipeline_flux.FluxPipeline._unpack_latents
    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()

    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(batch_size, height // 2, width // 2, dtype)

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

        image = image.to(dtype=dtype)
        image_latents = self._encode_vae_image(image=image, generator=generator)
        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, noise, image_latents, latent_image_ids

    # Copied from diffusers.pipelines.controlnet_sd3.pipeline_stable_diffusion_3_controlnet.StableDiffusion3ControlNetPipeline.prepare_image
    def prepare_image(
        self,
        image,
        width,
        height,
        batch_size,
        num_images_per_prompt,
        dtype,
        do_classifier_free_guidance=False,
        guess_mode=False,
    ):
        if isinstance(image, ms.Tensor):
            pass
        else:
            image = self.image_processor.preprocess(image, height=height, width=width)

        image_batch_size = image.shape[0]

        if image_batch_size == 1:
            repeat_by = batch_size
        else:
            # image batch size is the same as prompt batch size
            repeat_by = num_images_per_prompt

        image = image.repeat_interleave(repeat_by, dim=0)

        image = image.to(dtype=dtype)

        if do_classifier_free_guidance and not guess_mode:
            image = mint.cat([image] * 2)

        return image

    def prepare_mask_latents(
        self,
        image,
        mask_image,
        batch_size,
        num_channels_latents,
        num_images_per_prompt,
        height,
        width,
        dtype,
        generator,
    ):
        # VAE applies 8x compression on images but we must also account for packing which requires
        # latent height and width to be divisible by 2.
        image = self.image_processor.preprocess(image, height=height, width=width)
        mask_image = self.mask_processor.preprocess(mask_image, height=height, width=width)

        masked_image = image * (1 - mask_image)
        masked_image = masked_image.to(dtype=dtype)

        height = 2 * (int(height) // (self.vae_scale_factor * 2))
        width = 2 * (int(width) // (self.vae_scale_factor * 2))
        # resize the mask to latents shape as we concatenate the mask to the latents
        # we do that before converting to dtype to avoid breaking in case we're using cpu_offload
        # and half precision
        mask_image = mint.nn.functional.interpolate(mask_image, size=(height, width))
        mask_image = mask_image.to(dtype=dtype)

        batch_size = batch_size * num_images_per_prompt

        masked_image = masked_image.to(dtype=dtype)

        if masked_image.shape[1] == num_channels_latents:
            masked_image_latents = masked_image
        else:
            masked_image_latents = retrieve_latents(self.vae, self.vae.encode(masked_image)[0], generator=generator)

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

        # duplicate mask and masked_image_latents for each generation per prompt, using mps friendly method
        if mask_image.shape[0] < batch_size:
            if not batch_size % mask_image.shape[0] == 0:
                raise ValueError(
                    "The passed mask and the required batch size don't match. Masks are supposed to be duplicated to"
                    f" a total batch size of {batch_size}, but {mask_image.shape[0]} mask_image were passed. Make sure the number"
                    " of masks that you pass is divisible by the total requested batch size."
                )
            mask_image = mask_image.tile((batch_size // mask_image.shape[0], 1, 1, 1))
        if masked_image_latents.shape[0] < batch_size:
            if not batch_size % masked_image_latents.shape[0] == 0:
                raise ValueError(
                    "The passed images and the required batch size don't match. Images are supposed to be duplicated"
                    f" to a total batch size of {batch_size}, but {masked_image_latents.shape[0]} images were passed."
                    " Make sure the number of images that you pass is divisible by the total requested batch size."
                )
            masked_image_latents = masked_image_latents.tile((batch_size // masked_image_latents.shape[0], 1, 1, 1))

        # aligning device to prevent device errors when concating it with the latent model input
        masked_image_latents = masked_image_latents.to(dtype=dtype)
        masked_image_latents = self._pack_latents(
            masked_image_latents,
            batch_size,
            num_channels_latents,
            height,
            width,
        )
        mask_image = self._pack_latents(
            mask_image.tile((1, num_channels_latents, 1, 1)),
            batch_size,
            num_channels_latents,
            height,
            width,
        )
        masked_image_latents = mint.cat((masked_image_latents, mask_image), -1)

        return mask_image, masked_image_latents

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

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

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

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

    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        prompt_2: Optional[Union[str, List[str]]] = None,
        image: PipelineImageInput = None,
        control_image: PipelineImageInput = None,
        mask_image: PipelineImageInput = None,
        masked_image_latents: PipelineImageInput = None,
        height: Optional[int] = None,
        width: Optional[int] = None,
        strength: float = 0.6,
        num_inference_steps: int = 28,
        sigmas: Optional[List[float]] = None,
        guidance_scale: float = 7.0,
        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,
        pooled_prompt_embeds: 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.
            prompt_2 (`str` or `List[str]`, *optional*):
                The prompt or prompts to be sent to `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
                will be used instead
            image (`ms.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[ms.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                `Image`, numpy array or tensor representing an image batch to be used as the starting point. For both
                numpy array and ms tensor, the expected value range is between `[0, 1]` If it's a tensor or a list
                or tensors, the expected shape should be `(B, C, H, W)` or `(C, H, W)`. If it is a numpy array or a
                list of arrays, the expected shape should be `(B, H, W, C)` or `(H, W, C)` It can also accept image
                latents as `image`, but if passing latents directly it is not encoded again.
            control_image (`ms.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[ms.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
                    `List[List[ms.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
                The ControlNet input condition to provide guidance to the `unet` for generation. If the type is
                specified as `ms.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be accepted
                as an image. The dimensions of the output image defaults to `image`'s dimensions. If height and/or
                width are passed, `image` is resized accordingly. If multiple ControlNets are specified in `init`,
                images must be passed as a list such that each element of the list can be correctly batched for input
                to a single ControlNet.
            mask_image (`ms.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[ms.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
                `Image`, numpy array or tensor representing an image batch to mask `image`. White pixels in the mask
                are repainted while black pixels are preserved. If `mask_image` is a PIL image, it is converted to a
                single channel (luminance) before use. If it's a numpy array or ms tensor, it should contain one
                color channel (L) instead of 3, so the expected shape for ms tensor would be `(B, 1, H, W)`, `(B,
                H, W)`, `(1, H, W)`, `(H, W)`. And for numpy array would be for `(B, H, W, 1)`, `(B, H, W)`, `(H, W,
                1)`, or `(H, W)`.
            mask_image_latent (`ms.Tensor`, `List[ms.Tensor]`):
                `Tensor` representing an image batch to mask `image` generated by VAE. If not provided, the mask
                latents tensor will ge generated by `mask_image`.
            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.
            strength (`float`, *optional*, defaults to 1.0):
                Indicates extent to transform the reference `image`. Must be between 0 and 1. `image` is used as a
                starting point and more noise is added the higher the `strength`. The number of denoising steps depends
                on the amount of noise initially added. When `strength` is 1, added noise is maximum and the denoising
                process runs for the full number of iterations specified in `num_inference_steps`. A value of 1
                essentially ignores `image`.
            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 7.0):
                Guidance scale as defined in [Classifier-Free Diffusion
                Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
                of [Imagen Paper](https://huggingface.co/papers/2205.11487). 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 more [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.FloatTensor`, *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.
            pooled_prompt_embeds (`ms.FloatTensor`, *optional*):
                Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
                If not provided, pooled text embeddings will be generated from `prompt` input argument.
            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.FluxPipelineOutput`] 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.flux.FluxPipelineOutput`] or `tuple`: [`~pipelines.flux.FluxPipelineOutput`] 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,
            prompt_2,
            strength,
            height,
            width,
            prompt_embeds=prompt_embeds,
            pooled_prompt_embeds=pooled_prompt_embeds,
            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._interrupt = False

        # 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]

        # 3. Prepare text embeddings
        lora_scale = self.joint_attention_kwargs.get("scale", None) if self.joint_attention_kwargs is not None else None
        (
            prompt_embeds,
            pooled_prompt_embeds,
            text_ids,
        ) = self.encode_prompt(
            prompt=prompt,
            prompt_2=prompt_2,
            prompt_embeds=prompt_embeds,
            pooled_prompt_embeds=pooled_prompt_embeds,
            num_images_per_prompt=num_images_per_prompt,
            max_sequence_length=max_sequence_length,
            lora_scale=lora_scale,
        )

        # 3. Preprocess mask and image
        num_channels_latents = self.vae.config.latent_channels
        if masked_image_latents is not None:
            # pre computed masked_image_latents and mask_image
            mask = mask_image
        else:
            mask, masked_image_latents = self.prepare_mask_latents(
                image,
                mask_image,
                batch_size,
                num_channels_latents,
                num_images_per_prompt,
                height,
                width,
                prompt_embeds.dtype,
                generator,
            )

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

        # 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)

        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].tile((batch_size * num_images_per_prompt,))

        # 5. Prepare latent variables
        num_channels_latents = self.transformer.config.in_channels // 8

        control_image = self.prepare_image(
            image=control_image,
            width=width,
            height=height,
            batch_size=batch_size * num_images_per_prompt,
            num_images_per_prompt=num_images_per_prompt,
            dtype=self.vae.dtype,
        )

        if control_image.ndim == 4:
            control_image = self.vae.diag_gauss_dist.sample(self.vae.encode(control_image)[0], generator=generator)
            control_image = (control_image - self.vae.config.shift_factor) * self.vae.config.scaling_factor

            height_control_image, width_control_image = control_image.shape[2:]
            control_image = self._pack_latents(
                control_image,
                batch_size * num_images_per_prompt,
                num_channels_latents,
                height_control_image,
                width_control_image,
            )

        latents, noise, image_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,
        )

        # 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_8 = 2 * (int(height) // (self.vae_scale_factor * 2))
        width_8 = 2 * (int(width) // (self.vae_scale_factor * 2))

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

        # handle guidance
        if self.transformer.config.guidance_embeds:
            guidance = mint.full([1], guidance_scale, dtype=ms.float32)
            guidance = guidance.broadcast_to((latents.shape[0],))
        else:
            guidance = None

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

                latent_model_input = mint.cat([latents, control_image], dim=2)

                # 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=latent_model_input,
                    timestep=timestep / 1000,
                    guidance=guidance,
                    pooled_projections=pooled_prompt_embeds,
                    encoder_hidden_states=prompt_embeds,
                    txt_ids=text_ids,
                    img_ids=latent_image_ids,
                    joint_attention_kwargs=self.joint_attention_kwargs,
                    return_dict=False,
                )[0]

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

                # for 64 channel transformer only.
                init_mask = mask
                if i < len(timesteps) - 1:
                    noise_timestep = timesteps[i + 1]
                    init_latents_proper = self.scheduler.scale_noise(
                        image_latents, ms.tensor([noise_timestep.item()]), noise
                    )
                else:
                    init_latents_proper = image_latents
                init_latents_proper = self._pack_latents(
                    init_latents_proper, batch_size * num_images_per_prompt, num_channels_latents, height_8, width_8
                )

                latents = (1 - init_mask) * init_latents_proper + init_mask * latents

                if latents.dtype != latents_dtype:
                    latents = latents.to(latents_dtype)

                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()

        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 FluxPipelineOutput(images=image)

mindone.diffusers.FluxControlInpaintPipeline.__call__(prompt=None, prompt_2=None, image=None, control_image=None, mask_image=None, masked_image_latents=None, height=None, width=None, strength=0.6, num_inference_steps=28, sigmas=None, guidance_scale=7.0, num_images_per_prompt=1, generator=None, latents=None, prompt_embeds=None, pooled_prompt_embeds=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
prompt_2	The prompt or prompts to be sent to tokenizer_2 and text_encoder_2. If not defined, prompt is will be used instead TYPE: `str` or `List[str]`, *optional* DEFAULT: None
image	Image, numpy array or tensor representing an image batch to be used as the starting point. For both numpy array and ms tensor, the expected value range is between [0, 1] If it's a tensor or a list or tensors, the expected shape should be (B, C, H, W) or (C, H, W). If it is a numpy array or a list of arrays, the expected shape should be (B, H, W, C) or (H, W, C) It can also accept image latents as image, but if passing latents directly it is not encoded again. TYPE: `ms.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[ms.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]` DEFAULT: None
control_image (`ms.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[ms.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,	`List[List[ms.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`): The ControlNet input condition to provide guidance to the unet for generation. If the type is specified as ms.Tensor, it is passed to ControlNet as is. PIL.Image.Image can also be accepted as an image. The dimensions of the output image defaults to image's dimensions. If height and/or width are passed, image is resized accordingly. If multiple ControlNets are specified in init, images must be passed as a list such that each element of the list can be correctly batched for input to a single ControlNet.
mask_image	Image, numpy array or tensor representing an image batch to mask image. White pixels in the mask are repainted while black pixels are preserved. If mask_image is a PIL image, it is converted to a single channel (luminance) before use. If it's a numpy array or ms tensor, it should contain one color channel (L) instead of 3, so the expected shape for ms tensor would be (B, 1, H, W), (B, H, W), (1, H, W), (H, W). And for numpy array would be for (B, H, W, 1), (B, H, W), (H, W, 1), or (H, W). TYPE: `ms.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[ms.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]` DEFAULT: None
mask_image_latent	Tensor representing an image batch to mask image generated by VAE. If not provided, the mask latents tensor will ge generated by mask_image. TYPE: `ms.Tensor`, `List[ms.Tensor]`
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
strength	Indicates extent to transform the reference image. Must be between 0 and 1. image is used as a starting point and more noise is added the higher the strength. The number of denoising steps depends on the amount of noise initially added. When strength is 1, added noise is maximum and the denoising process runs for the full number of iterations specified in num_inference_steps. A value of 1 essentially ignores image. TYPE: `float`, *optional*, defaults to 1.0 DEFAULT: 0.6
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: 28
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 7.0 DEFAULT: 7.0
num_images_per_prompt	The number of images to generate per prompt. TYPE: `int`, *optional*, defaults to 1 DEFAULT: 1
generator	One or more 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.FloatTensor`, *optional* DEFAULT: None
pooled_prompt_embeds	Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, pooled text embeddings will be generated from prompt input argument. TYPE: `ms.FloatTensor`, *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.FluxPipelineOutput] 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.flux.FluxPipelineOutput] or tuple: [~pipelines.flux.FluxPipelineOutput] 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/flux/pipeline_flux_control_inpaint.py

def __call__(
    self,
    prompt: Union[str, List[str]] = None,
    prompt_2: Optional[Union[str, List[str]]] = None,
    image: PipelineImageInput = None,
    control_image: PipelineImageInput = None,
    mask_image: PipelineImageInput = None,
    masked_image_latents: PipelineImageInput = None,
    height: Optional[int] = None,
    width: Optional[int] = None,
    strength: float = 0.6,
    num_inference_steps: int = 28,
    sigmas: Optional[List[float]] = None,
    guidance_scale: float = 7.0,
    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,
    pooled_prompt_embeds: 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.
        prompt_2 (`str` or `List[str]`, *optional*):
            The prompt or prompts to be sent to `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
            will be used instead
        image (`ms.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[ms.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
            `Image`, numpy array or tensor representing an image batch to be used as the starting point. For both
            numpy array and ms tensor, the expected value range is between `[0, 1]` If it's a tensor or a list
            or tensors, the expected shape should be `(B, C, H, W)` or `(C, H, W)`. If it is a numpy array or a
            list of arrays, the expected shape should be `(B, H, W, C)` or `(H, W, C)` It can also accept image
            latents as `image`, but if passing latents directly it is not encoded again.
        control_image (`ms.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[ms.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
                `List[List[ms.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
            The ControlNet input condition to provide guidance to the `unet` for generation. If the type is
            specified as `ms.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be accepted
            as an image. The dimensions of the output image defaults to `image`'s dimensions. If height and/or
            width are passed, `image` is resized accordingly. If multiple ControlNets are specified in `init`,
            images must be passed as a list such that each element of the list can be correctly batched for input
            to a single ControlNet.
        mask_image (`ms.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[ms.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
            `Image`, numpy array or tensor representing an image batch to mask `image`. White pixels in the mask
            are repainted while black pixels are preserved. If `mask_image` is a PIL image, it is converted to a
            single channel (luminance) before use. If it's a numpy array or ms tensor, it should contain one
            color channel (L) instead of 3, so the expected shape for ms tensor would be `(B, 1, H, W)`, `(B,
            H, W)`, `(1, H, W)`, `(H, W)`. And for numpy array would be for `(B, H, W, 1)`, `(B, H, W)`, `(H, W,
            1)`, or `(H, W)`.
        mask_image_latent (`ms.Tensor`, `List[ms.Tensor]`):
            `Tensor` representing an image batch to mask `image` generated by VAE. If not provided, the mask
            latents tensor will ge generated by `mask_image`.
        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.
        strength (`float`, *optional*, defaults to 1.0):
            Indicates extent to transform the reference `image`. Must be between 0 and 1. `image` is used as a
            starting point and more noise is added the higher the `strength`. The number of denoising steps depends
            on the amount of noise initially added. When `strength` is 1, added noise is maximum and the denoising
            process runs for the full number of iterations specified in `num_inference_steps`. A value of 1
            essentially ignores `image`.
        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 7.0):
            Guidance scale as defined in [Classifier-Free Diffusion
            Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
            of [Imagen Paper](https://huggingface.co/papers/2205.11487). 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 more [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.FloatTensor`, *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.
        pooled_prompt_embeds (`ms.FloatTensor`, *optional*):
            Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
            If not provided, pooled text embeddings will be generated from `prompt` input argument.
        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.FluxPipelineOutput`] 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.flux.FluxPipelineOutput`] or `tuple`: [`~pipelines.flux.FluxPipelineOutput`] 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,
        prompt_2,
        strength,
        height,
        width,
        prompt_embeds=prompt_embeds,
        pooled_prompt_embeds=pooled_prompt_embeds,
        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._interrupt = False

    # 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]

    # 3. Prepare text embeddings
    lora_scale = self.joint_attention_kwargs.get("scale", None) if self.joint_attention_kwargs is not None else None
    (
        prompt_embeds,
        pooled_prompt_embeds,
        text_ids,
    ) = self.encode_prompt(
        prompt=prompt,
        prompt_2=prompt_2,
        prompt_embeds=prompt_embeds,
        pooled_prompt_embeds=pooled_prompt_embeds,
        num_images_per_prompt=num_images_per_prompt,
        max_sequence_length=max_sequence_length,
        lora_scale=lora_scale,
    )

    # 3. Preprocess mask and image
    num_channels_latents = self.vae.config.latent_channels
    if masked_image_latents is not None:
        # pre computed masked_image_latents and mask_image
        mask = mask_image
    else:
        mask, masked_image_latents = self.prepare_mask_latents(
            image,
            mask_image,
            batch_size,
            num_channels_latents,
            num_images_per_prompt,
            height,
            width,
            prompt_embeds.dtype,
            generator,
        )

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

    # 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)

    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].tile((batch_size * num_images_per_prompt,))

    # 5. Prepare latent variables
    num_channels_latents = self.transformer.config.in_channels // 8

    control_image = self.prepare_image(
        image=control_image,
        width=width,
        height=height,
        batch_size=batch_size * num_images_per_prompt,
        num_images_per_prompt=num_images_per_prompt,
        dtype=self.vae.dtype,
    )

    if control_image.ndim == 4:
        control_image = self.vae.diag_gauss_dist.sample(self.vae.encode(control_image)[0], generator=generator)
        control_image = (control_image - self.vae.config.shift_factor) * self.vae.config.scaling_factor

        height_control_image, width_control_image = control_image.shape[2:]
        control_image = self._pack_latents(
            control_image,
            batch_size * num_images_per_prompt,
            num_channels_latents,
            height_control_image,
            width_control_image,
        )

    latents, noise, image_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,
    )

    # 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_8 = 2 * (int(height) // (self.vae_scale_factor * 2))
    width_8 = 2 * (int(width) // (self.vae_scale_factor * 2))

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

    # handle guidance
    if self.transformer.config.guidance_embeds:
        guidance = mint.full([1], guidance_scale, dtype=ms.float32)
        guidance = guidance.broadcast_to((latents.shape[0],))
    else:
        guidance = None

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

            latent_model_input = mint.cat([latents, control_image], dim=2)

            # 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=latent_model_input,
                timestep=timestep / 1000,
                guidance=guidance,
                pooled_projections=pooled_prompt_embeds,
                encoder_hidden_states=prompt_embeds,
                txt_ids=text_ids,
                img_ids=latent_image_ids,
                joint_attention_kwargs=self.joint_attention_kwargs,
                return_dict=False,
            )[0]

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

            # for 64 channel transformer only.
            init_mask = mask
            if i < len(timesteps) - 1:
                noise_timestep = timesteps[i + 1]
                init_latents_proper = self.scheduler.scale_noise(
                    image_latents, ms.tensor([noise_timestep.item()]), noise
                )
            else:
                init_latents_proper = image_latents
            init_latents_proper = self._pack_latents(
                init_latents_proper, batch_size * num_images_per_prompt, num_channels_latents, height_8, width_8
            )

            latents = (1 - init_mask) * init_latents_proper + init_mask * latents

            if latents.dtype != latents_dtype:
                latents = latents.to(latents_dtype)

            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()

    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 FluxPipelineOutput(images=image)

mindone.diffusers.FluxControlInpaintPipeline.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/flux/pipeline_flux_control_inpaint.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.FluxControlInpaintPipeline.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/flux/pipeline_flux_control_inpaint.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.FluxControlInpaintPipeline.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/flux/pipeline_flux_control_inpaint.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.FluxControlInpaintPipeline.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/flux/pipeline_flux_control_inpaint.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.FluxControlInpaintPipeline.encode_prompt(prompt, prompt_2=None, num_images_per_prompt=1, prompt_embeds=None, pooled_prompt_embeds=None, max_sequence_length=512, lora_scale=None)

PARAMETER	DESCRIPTION
prompt	prompt to be encoded TYPE: `str` or `List[str]`, *optional*
prompt_2	The prompt or prompts to be sent to the tokenizer_2 and text_encoder_2. If not defined, prompt is used in all text-encoders 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
pooled_prompt_embeds	Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, pooled 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/flux/pipeline_flux_control_inpaint.py

def encode_prompt(
    self,
    prompt: Union[str, List[str]],
    prompt_2: Optional[Union[str, List[str]]] = None,
    num_images_per_prompt: int = 1,
    prompt_embeds: Optional[ms.Tensor] = None,
    pooled_prompt_embeds: Optional[ms.Tensor] = None,
    max_sequence_length: int = 512,
    lora_scale: Optional[float] = None,
):
    r"""

    Args:
        prompt (`str` or `List[str]`, *optional*):
            prompt to be encoded
        prompt_2 (`str` or `List[str]`, *optional*):
            The prompt or prompts to be sent to the `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
            used in all text-encoders
        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.
        pooled_prompt_embeds (`ms.Tensor`, *optional*):
            Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
            If not provided, pooled 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)
        if self.text_encoder_2 is not None:
            scale_lora_layers(self.text_encoder_2, lora_scale)

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

    if prompt_embeds is None:
        prompt_2 = prompt_2 or prompt
        prompt_2 = [prompt_2] if isinstance(prompt_2, str) else prompt_2

        # We only use the pooled prompt output from the CLIPTextModel
        pooled_prompt_embeds = self._get_clip_prompt_embeds(
            prompt=prompt,
            num_images_per_prompt=num_images_per_prompt,
        )
        prompt_embeds = self._get_t5_prompt_embeds(
            prompt=prompt_2,
            num_images_per_prompt=num_images_per_prompt,
            max_sequence_length=max_sequence_length,
        )

    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)

    if self.text_encoder_2 is not None:
        if isinstance(self, FluxLoraLoaderMixin):
            # Retrieve the original scale by scaling back the LoRA layers
            unscale_lora_layers(self.text_encoder_2, lora_scale)

    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)

    return prompt_embeds, pooled_prompt_embeds, text_ids

mindone.diffusers.pipelines.flux.pipeline_output.FluxPipelineOutput dataclass

Bases: BaseOutput

Output class for Flux image generation pipelines.

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

@dataclass
class FluxPipelineOutput(BaseOutput):
    """
    Output class for Flux image generation pipelines.

    Args:
        images (`List[PIL.Image.Image]` or `ms.Tensor` or `np.ndarray`)
            List of denoised PIL images of length `batch_size` or numpy array or mindspore tensor of shape `(batch_size,
            height, width, num_channels)`. PIL images or numpy array present the denoised images of the diffusion
            pipeline. Mindspore tensors can represent either the denoised images or the intermediate latents ready to be
            passed to the decoder.
    """

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