diffusers/examples/community/stable_diffusion_controlnet_img2img.py

# Inspired by: https://github.com/haofanwang/ControlNet-for-Diffusers/

import inspect
from typing import Any, Callable, Dict, List, Optional, Tuple, Union

import numpy as np
import PIL.Image
import torch
from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer

from diffusers import AutoencoderKL, ControlNetModel, UNet2DConditionModel, logging
from diffusers.pipelines.controlnet.multicontrolnet import MultiControlNetModel
from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput, StableDiffusionSafetyChecker
from diffusers.schedulers import KarrasDiffusionSchedulers
from diffusers.utils import (
    PIL_INTERPOLATION,
    replace_example_docstring,
)
from diffusers.utils.torch_utils import randn_tensor


logger = logging.get_logger(__name__)  # pylint: disable=invalid-name

EXAMPLE_DOC_STRING = """
    Examples:
        ```py
        >>> import numpy as np
        >>> import torch
        >>> from PIL import Image
        >>> from diffusers import ControlNetModel, UniPCMultistepScheduler
        >>> from diffusers.utils import load_image

        >>> input_image = load_image("https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png")

        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)

        >>> pipe_controlnet = StableDiffusionControlNetImg2ImgPipeline.from_pretrained(
                "stable-diffusion-v1-5/stable-diffusion-v1-5",
                controlnet=controlnet,
                safety_checker=None,
                torch_dtype=torch.float16
                )

        >>> pipe_controlnet.scheduler = UniPCMultistepScheduler.from_config(pipe_controlnet.scheduler.config)
        >>> pipe_controlnet.enable_xformers_memory_efficient_attention()
        >>> pipe_controlnet.enable_model_cpu_offload()

        # using image with edges for our canny controlnet
        >>> control_image = load_image(
            "https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/vermeer_canny_edged.png")


        >>> result_img = pipe_controlnet(controlnet_conditioning_image=control_image,
                        image=input_image,
                        prompt="an android robot, cyberpank, digitl art masterpiece",
                        num_inference_steps=20).images[0]

        >>> result_img.show()
        ```
"""


def prepare_image(image):
    if isinstance(image, torch.Tensor):
        # Batch single image
        if image.ndim == 3:
            image = image.unsqueeze(0)

        image = image.to(dtype=torch.float32)
    else:
        # preprocess image
        if isinstance(image, (PIL.Image.Image, np.ndarray)):
            image = [image]

        if isinstance(image, list) and isinstance(image[0], PIL.Image.Image):
            image = [np.array(i.convert("RGB"))[None, :] for i in image]
            image = np.concatenate(image, axis=0)
        elif isinstance(image, list) and isinstance(image[0], np.ndarray):
            image = np.concatenate([i[None, :] for i in image], axis=0)

        image = image.transpose(0, 3, 1, 2)
        image = torch.from_numpy(image).to(dtype=torch.float32) / 127.5 - 1.0

    return image


def prepare_controlnet_conditioning_image(
    controlnet_conditioning_image,
    width,
    height,
    batch_size,
    num_images_per_prompt,
    device,
    dtype,
    do_classifier_free_guidance,
):
    if not isinstance(controlnet_conditioning_image, torch.Tensor):
        if isinstance(controlnet_conditioning_image, PIL.Image.Image):
            controlnet_conditioning_image = [controlnet_conditioning_image]

        if isinstance(controlnet_conditioning_image[0], PIL.Image.Image):
            controlnet_conditioning_image = [
                np.array(i.resize((width, height), resample=PIL_INTERPOLATION["lanczos"]))[None, :]
                for i in controlnet_conditioning_image
            ]
            controlnet_conditioning_image = np.concatenate(controlnet_conditioning_image, axis=0)
            controlnet_conditioning_image = np.array(controlnet_conditioning_image).astype(np.float32) / 255.0
            controlnet_conditioning_image = controlnet_conditioning_image.transpose(0, 3, 1, 2)
            controlnet_conditioning_image = torch.from_numpy(controlnet_conditioning_image)
        elif isinstance(controlnet_conditioning_image[0], torch.Tensor):
            controlnet_conditioning_image = torch.cat(controlnet_conditioning_image, dim=0)

    image_batch_size = controlnet_conditioning_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

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

    controlnet_conditioning_image = controlnet_conditioning_image.to(device=device, dtype=dtype)

    if do_classifier_free_guidance:
        controlnet_conditioning_image = torch.cat([controlnet_conditioning_image] * 2)

    return controlnet_conditioning_image


class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, StableDiffusionMixin):
    """
    Inspired by: https://github.com/haofanwang/ControlNet-for-Diffusers/
    """

    _optional_components = ["safety_checker", "feature_extractor"]

    def __init__(
        self,
        vae: AutoencoderKL,
        text_encoder: CLIPTextModel,
        tokenizer: CLIPTokenizer,
        unet: UNet2DConditionModel,
        controlnet: Union[ControlNetModel, List[ControlNetModel], Tuple[ControlNetModel], MultiControlNetModel],
        scheduler: KarrasDiffusionSchedulers,
        safety_checker: StableDiffusionSafetyChecker,
        feature_extractor: CLIPImageProcessor,
        requires_safety_checker: bool = True,
    ):
        super().__init__()

        if safety_checker is None and requires_safety_checker:
            logger.warning(
                f"You have disabled the safety checker for {self.__class__} by passing `safety_checker=None`. Ensure"
                " that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered"
                " results in services or applications open to the public. Both the diffusers team and Hugging Face"
                " strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling"
                " it only for use-cases that involve analyzing network behavior or auditing its results. For more"
                " information, please have a look at https://github.com/huggingface/diffusers/pull/254 ."
            )

        if safety_checker is not None and feature_extractor is None:
            raise ValueError(
                "Make sure to define a feature extractor when loading {self.__class__} if you want to use the safety"
                " checker. If you do not want to use the safety checker, you can pass `'safety_checker=None'` instead."
            )

        if isinstance(controlnet, (list, tuple)):
            controlnet = MultiControlNetModel(controlnet)

        self.register_modules(
            vae=vae,
            text_encoder=text_encoder,
            tokenizer=tokenizer,
            unet=unet,
            controlnet=controlnet,
            scheduler=scheduler,
            safety_checker=safety_checker,
            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.register_to_config(requires_safety_checker=requires_safety_checker)

    def _encode_prompt(
        self,
        prompt,
        device,
        num_images_per_prompt,
        do_classifier_free_guidance,
        negative_prompt=None,
        prompt_embeds: Optional[torch.Tensor] = None,
        negative_prompt_embeds: Optional[torch.Tensor] = None,
    ):
        r"""
        Encodes the prompt into text encoder hidden states.

        Args:
             prompt (`str` or `List[str]`, *optional*):
                prompt to be encoded
            device: (`torch.device`):
                torch device
            num_images_per_prompt (`int`):
                number of images that should be generated per prompt
            do_classifier_free_guidance (`bool`):
                whether to use classifier free guidance or not
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
            prompt_embeds (`torch.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            negative_prompt_embeds (`torch.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.
        """
        if prompt is not None and isinstance(prompt, str):
            batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            batch_size = len(prompt)
        else:
            batch_size = prompt_embeds.shape[0]

        if prompt_embeds is None:
            text_inputs = self.tokenizer(
                prompt,
                padding="max_length",
                max_length=self.tokenizer.model_max_length,
                truncation=True,
                return_tensors="pt",
            )
            text_input_ids = text_inputs.input_ids
            untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="pt").input_ids

            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal(
                text_input_ids, untruncated_ids
            ):
                removed_text = self.tokenizer.batch_decode(
                    untruncated_ids[:, self.tokenizer.model_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.model_max_length} tokens: {removed_text}"
                )

            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
                attention_mask = text_inputs.attention_mask.to(device)
            else:
                attention_mask = None

            prompt_embeds = self.text_encoder(
                text_input_ids.to(device),
                attention_mask=attention_mask,
            )
            prompt_embeds = prompt_embeds[0]

        prompt_embeds = prompt_embeds.to(dtype=self.text_encoder.dtype, device=device)

        bs_embed, seq_len, _ = prompt_embeds.shape
        # duplicate text embeddings 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(bs_embed * num_images_per_prompt, seq_len, -1)

        # get unconditional embeddings for classifier free guidance
        if do_classifier_free_guidance and negative_prompt_embeds is None:
            uncond_tokens: List[str]
            if negative_prompt is None:
                uncond_tokens = [""] * batch_size
            elif type(prompt) is not type(negative_prompt):
                raise TypeError(
                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
                    f" {type(prompt)}."
                )
            elif isinstance(negative_prompt, str):
                uncond_tokens = [negative_prompt]
            elif batch_size != len(negative_prompt):
                raise ValueError(
                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
                    " the batch size of `prompt`."
                )
            else:
                uncond_tokens = negative_prompt

            max_length = prompt_embeds.shape[1]
            uncond_input = self.tokenizer(
                uncond_tokens,
                padding="max_length",
                max_length=max_length,
                truncation=True,
                return_tensors="pt",
            )

            if hasattr(self.text_encoder.config, "use_attention_mask") and self.text_encoder.config.use_attention_mask:
                attention_mask = uncond_input.attention_mask.to(device)
            else:
                attention_mask = None

            negative_prompt_embeds = self.text_encoder(
                uncond_input.input_ids.to(device),
                attention_mask=attention_mask,
            )
            negative_prompt_embeds = negative_prompt_embeds[0]

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

            negative_prompt_embeds = negative_prompt_embeds.to(dtype=self.text_encoder.dtype, device=device)

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

            # For classifier free guidance, we need to do two forward passes.
            # Here we concatenate the unconditional and text embeddings into a single batch
            # to avoid doing two forward passes
            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])

        return prompt_embeds

    def run_safety_checker(self, image, device, dtype):
        if self.safety_checker is not None:
            safety_checker_input = self.feature_extractor(self.numpy_to_pil(image), return_tensors="pt").to(device)
            image, has_nsfw_concept = self.safety_checker(
                images=image, clip_input=safety_checker_input.pixel_values.to(dtype)
            )
        else:
            has_nsfw_concept = None
        return image, has_nsfw_concept

    def decode_latents(self, latents):
        latents = 1 / self.vae.config.scaling_factor * latents
        image = self.vae.decode(latents).sample
        image = (image / 2 + 0.5).clamp(0, 1)
        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
        image = image.cpu().permute(0, 2, 3, 1).float().numpy()
        return image

    def prepare_extra_step_kwargs(self, generator, eta):
        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
        # and should be between [0, 1]

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

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

    def check_controlnet_conditioning_image(self, image, prompt, prompt_embeds):
        image_is_pil = isinstance(image, PIL.Image.Image)
        image_is_tensor = isinstance(image, torch.Tensor)
        image_is_pil_list = isinstance(image, list) and isinstance(image[0], PIL.Image.Image)
        image_is_tensor_list = isinstance(image, list) and isinstance(image[0], torch.Tensor)

        if not image_is_pil and not image_is_tensor and not image_is_pil_list and not image_is_tensor_list:
            raise TypeError(
                "image must be passed and be one of PIL image, torch tensor, list of PIL images, or list of torch tensors"
            )

        if image_is_pil:
            image_batch_size = 1
        elif image_is_tensor:
            image_batch_size = image.shape[0]
        elif image_is_pil_list:
            image_batch_size = len(image)
        elif image_is_tensor_list:
            image_batch_size = len(image)
        else:
            raise ValueError("controlnet condition image is not valid")

        if prompt is not None and isinstance(prompt, str):
            prompt_batch_size = 1
        elif prompt is not None and isinstance(prompt, list):
            prompt_batch_size = len(prompt)
        elif prompt_embeds is not None:
            prompt_batch_size = prompt_embeds.shape[0]
        else:
            raise ValueError("prompt or prompt_embeds are not valid")

        if image_batch_size != 1 and image_batch_size != prompt_batch_size:
            raise ValueError(
                f"If image batch size is not 1, image batch size must be same as prompt batch size. image batch size: {image_batch_size}, prompt batch size: {prompt_batch_size}"
            )

    def check_inputs(
        self,
        prompt,
        image,
        controlnet_conditioning_image,
        height,
        width,
        callback_steps,
        negative_prompt=None,
        prompt_embeds=None,
        negative_prompt_embeds=None,
        strength=None,
        controlnet_guidance_start=None,
        controlnet_guidance_end=None,
        controlnet_conditioning_scale=None,
    ):
        if height % 8 != 0 or width % 8 != 0:
            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")

        if (callback_steps is None) or (
            callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0)
        ):
            raise ValueError(
                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
                f" {type(callback_steps)}."
            )

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

        # check controlnet condition image

        if isinstance(self.controlnet, ControlNetModel):
            self.check_controlnet_conditioning_image(controlnet_conditioning_image, prompt, prompt_embeds)
        elif isinstance(self.controlnet, MultiControlNetModel):
            if not isinstance(controlnet_conditioning_image, list):
                raise TypeError("For multiple controlnets: `image` must be type `list`")

            if len(controlnet_conditioning_image) != len(self.controlnet.nets):
                raise ValueError(
                    "For multiple controlnets: `image` must have the same length as the number of controlnets."
                )

            for image_ in controlnet_conditioning_image:
                self.check_controlnet_conditioning_image(image_, prompt, prompt_embeds)
        else:
            assert False

        # Check `controlnet_conditioning_scale`

        if isinstance(self.controlnet, ControlNetModel):
            if not isinstance(controlnet_conditioning_scale, float):
                raise TypeError("For single controlnet: `controlnet_conditioning_scale` must be type `float`.")
        elif isinstance(self.controlnet, MultiControlNetModel):
            if isinstance(controlnet_conditioning_scale, list) and len(controlnet_conditioning_scale) != len(
                self.controlnet.nets
            ):
                raise ValueError(
                    "For multiple controlnets: When `controlnet_conditioning_scale` is specified as `list`, it must have"
                    " the same length as the number of controlnets"
                )
        else:
            assert False

        if isinstance(image, torch.Tensor):
            if image.ndim != 3 and image.ndim != 4:
                raise ValueError("`image` must have 3 or 4 dimensions")

            if image.ndim == 3:
                image_batch_size = 1
                image_channels, image_height, image_width = image.shape
            elif image.ndim == 4:
                image_batch_size, image_channels, image_height, image_width = image.shape
            else:
                assert False

            if image_channels != 3:
                raise ValueError("`image` must have 3 channels")

            if image.min() < -1 or image.max() > 1:
                raise ValueError("`image` should be in range [-1, 1]")

        if self.vae.config.latent_channels != self.unet.config.in_channels:
            raise ValueError(
                f"The config of `pipeline.unet` expects {self.unet.config.in_channels} but received"
                f" latent channels: {self.vae.config.latent_channels},"
                f" Please verify the config of `pipeline.unet` and the `pipeline.vae`"
            )

        if strength < 0 or strength > 1:
            raise ValueError(f"The value of `strength` should in [0.0, 1.0] but is {strength}")

        if controlnet_guidance_start < 0 or controlnet_guidance_start > 1:
            raise ValueError(
                f"The value of `controlnet_guidance_start` should in [0.0, 1.0] but is {controlnet_guidance_start}"
            )

        if controlnet_guidance_end < 0 or controlnet_guidance_end > 1:
            raise ValueError(
                f"The value of `controlnet_guidance_end` should in [0.0, 1.0] but is {controlnet_guidance_end}"
            )

        if controlnet_guidance_start > controlnet_guidance_end:
            raise ValueError(
                "The value of `controlnet_guidance_start` should be less than `controlnet_guidance_end`, but got"
                f" `controlnet_guidance_start` {controlnet_guidance_start} >= `controlnet_guidance_end` {controlnet_guidance_end}"
            )

    def get_timesteps(self, num_inference_steps, strength, device):
        # get the original timestep using init_timestep
        init_timestep = min(int(num_inference_steps * strength), num_inference_steps)

        t_start = max(num_inference_steps - init_timestep, 0)
        timesteps = self.scheduler.timesteps[t_start:]

        return timesteps, num_inference_steps - t_start

    def prepare_latents(self, image, timestep, batch_size, num_images_per_prompt, dtype, device, generator=None):
        if not isinstance(image, (torch.Tensor, PIL.Image.Image, list)):
            raise ValueError(
                f"`image` has to be of type `torch.Tensor`, `PIL.Image.Image` or list but is {type(image)}"
            )

        image = image.to(device=device, dtype=dtype)

        batch_size = batch_size * num_images_per_prompt
        if isinstance(generator, list) and len(generator) != batch_size:
            raise ValueError(
                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
            )

        if isinstance(generator, list):
            init_latents = [
                self.vae.encode(image[i : i + 1]).latent_dist.sample(generator[i]) for i in range(batch_size)
            ]
            init_latents = torch.cat(init_latents, dim=0)
        else:
            init_latents = self.vae.encode(image).latent_dist.sample(generator)

        init_latents = self.vae.config.scaling_factor * init_latents

        if batch_size > init_latents.shape[0] and batch_size % init_latents.shape[0] == 0:
            raise ValueError(
                f"Cannot duplicate `image` of batch size {init_latents.shape[0]} to {batch_size} text prompts."
            )
        else:
            init_latents = torch.cat([init_latents], dim=0)

        shape = init_latents.shape
        noise = randn_tensor(shape, generator=generator, device=device, dtype=dtype)

        # get latents
        init_latents = self.scheduler.add_noise(init_latents, noise, timestep)
        latents = init_latents

        return latents

    def _default_height_width(self, height, width, image):
        if isinstance(image, list):
            image = image[0]

        if height is None:
            if isinstance(image, PIL.Image.Image):
                height = image.height
            elif isinstance(image, torch.Tensor):
                height = image.shape[3]

            height = (height // 8) * 8  # round down to nearest multiple of 8

        if width is None:
            if isinstance(image, PIL.Image.Image):
                width = image.width
            elif isinstance(image, torch.Tensor):
                width = image.shape[2]

            width = (width // 8) * 8  # round down to nearest multiple of 8

        return height, width

    @torch.no_grad()
    @replace_example_docstring(EXAMPLE_DOC_STRING)
    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        image: Union[torch.Tensor, PIL.Image.Image] = None,
        controlnet_conditioning_image: Union[
            torch.Tensor, PIL.Image.Image, List[torch.Tensor], List[PIL.Image.Image]
        ] = None,
        strength: float = 0.8,
        height: Optional[int] = None,
        width: Optional[int] = None,
        num_inference_steps: int = 50,
        guidance_scale: float = 7.5,
        negative_prompt: Optional[Union[str, List[str]]] = None,
        num_images_per_prompt: Optional[int] = 1,
        eta: float = 0.0,
        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
        latents: Optional[torch.Tensor] = None,
        prompt_embeds: Optional[torch.Tensor] = None,
        negative_prompt_embeds: Optional[torch.Tensor] = None,
        output_type: Optional[str] = "pil",
        return_dict: bool = True,
        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
        callback_steps: int = 1,
        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
        controlnet_conditioning_scale: Union[float, List[float]] = 1.0,
        controlnet_guidance_start: float = 0.0,
        controlnet_guidance_end: float = 1.0,
    ):
        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.
            image (`torch.Tensor` or `PIL.Image.Image`):
                `Image`, or tensor representing an image batch which will be inpainted, *i.e.* parts of the image will
                be masked out with `mask_image` and repainted according to `prompt`.
            controlnet_conditioning_image (`torch.Tensor`, `PIL.Image.Image`, `List[torch.Tensor]` or `List[PIL.Image.Image]`):
                The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
                the type is specified as `torch.Tensor`, it is passed to ControlNet as is. PIL.Image.Image` can
                also be accepted as an image. The control image is automatically resized to fit the output image.
            strength (`float`, *optional*):
                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`.
            height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                The height in pixels of the generated image.
            width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
                The width in pixels of the generated 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.
            guidance_scale (`float`, *optional*, defaults to 7.5):
                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.
            negative_prompt (`str` or `List[str]`, *optional*):
                The prompt or prompts not to guide the image generation. If not defined, one has to pass
                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
            num_images_per_prompt (`int`, *optional*, defaults to 1):
                The number of images to generate per prompt.
            eta (`float`, *optional*, defaults to 0.0):
                Corresponds to parameter eta (η) in the DDIM paper: https://huggingface.co/papers/2010.02502. Only applies to
                [`schedulers.DDIMScheduler`], will be ignored for others.
            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                to make generation deterministic.
            latents (`torch.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 be generated by sampling using the supplied random `generator`.
            prompt_embeds (`torch.Tensor`, *optional*):
                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                provided, text embeddings will be generated from `prompt` input argument.
            negative_prompt_embeds (`torch.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.
            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.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
                plain tuple.
            callback (`Callable`, *optional*):
                A function that will be called every `callback_steps` steps during inference. The function will be
                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
            callback_steps (`int`, *optional*, defaults to 1):
                The frequency at which the `callback` function will be called. If not specified, the callback will be
                called at every step.
            cross_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).
            controlnet_conditioning_scale (`float`, *optional*, defaults to 1.0):
                The outputs of the controlnet are multiplied by `controlnet_conditioning_scale` before they are added
                to the residual in the original unet.
            controlnet_guidance_start ('float', *optional*, defaults to 0.0):
                The percentage of total steps the controlnet starts applying. Must be between 0 and 1.
            controlnet_guidance_end ('float', *optional*, defaults to 1.0):
                The percentage of total steps the controlnet ends applying. Must be between 0 and 1. Must be greater
                than `controlnet_guidance_start`.

        Examples:

        Returns:
            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
            [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] if `return_dict` is True, otherwise a `tuple.
            When returning a tuple, the first element is a list with the generated images, and the second element is a
            list of `bool`s denoting whether the corresponding generated image likely represents "not-safe-for-work"
            (nsfw) content, according to the `safety_checker`.
        """
        # 0. Default height and width to unet
        height, width = self._default_height_width(height, width, controlnet_conditioning_image)

        # 1. Check inputs. Raise error if not correct
        self.check_inputs(
            prompt,
            image,
            controlnet_conditioning_image,
            height,
            width,
            callback_steps,
            negative_prompt,
            prompt_embeds,
            negative_prompt_embeds,
            strength,
            controlnet_guidance_start,
            controlnet_guidance_end,
            controlnet_conditioning_scale,
        )

        # 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]

        device = self._execution_device
        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
        # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
        # corresponds to doing no classifier free guidance.
        do_classifier_free_guidance = guidance_scale > 1.0

        if isinstance(self.controlnet, MultiControlNetModel) and isinstance(controlnet_conditioning_scale, float):
            controlnet_conditioning_scale = [controlnet_conditioning_scale] * len(self.controlnet.nets)

        # 3. Encode input prompt
        prompt_embeds = self._encode_prompt(
            prompt,
            device,
            num_images_per_prompt,
            do_classifier_free_guidance,
            negative_prompt,
            prompt_embeds=prompt_embeds,
            negative_prompt_embeds=negative_prompt_embeds,
        )

        # 4. Prepare image, and controlnet_conditioning_image
        image = prepare_image(image)

        # condition image(s)
        if isinstance(self.controlnet, ControlNetModel):
            controlnet_conditioning_image = prepare_controlnet_conditioning_image(
                controlnet_conditioning_image=controlnet_conditioning_image,
                width=width,
                height=height,
                batch_size=batch_size * num_images_per_prompt,
                num_images_per_prompt=num_images_per_prompt,
                device=device,
                dtype=self.controlnet.dtype,
                do_classifier_free_guidance=do_classifier_free_guidance,
            )
        elif isinstance(self.controlnet, MultiControlNetModel):
            controlnet_conditioning_images = []

            for image_ in controlnet_conditioning_image:
                image_ = prepare_controlnet_conditioning_image(
                    controlnet_conditioning_image=image_,
                    width=width,
                    height=height,
                    batch_size=batch_size * num_images_per_prompt,
                    num_images_per_prompt=num_images_per_prompt,
                    device=device,
                    dtype=self.controlnet.dtype,
                    do_classifier_free_guidance=do_classifier_free_guidance,
                )

                controlnet_conditioning_images.append(image_)

            controlnet_conditioning_image = controlnet_conditioning_images
        else:
            assert False

        # 5. Prepare timesteps
        self.scheduler.set_timesteps(num_inference_steps, device=device)
        timesteps, num_inference_steps = self.get_timesteps(num_inference_steps, strength, device)
        latent_timestep = timesteps[:1].repeat(batch_size * num_images_per_prompt)

        # 6. Prepare latent variables
        if latents is None:
            latents = self.prepare_latents(
                image,
                latent_timestep,
                batch_size,
                num_images_per_prompt,
                prompt_embeds.dtype,
                device,
                generator,
            )

        # 7. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)

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

                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)

                # compute the percentage of total steps we are at
                current_sampling_percent = i / len(timesteps)

                if (
                    current_sampling_percent < controlnet_guidance_start
                    or current_sampling_percent > controlnet_guidance_end
                ):
                    # do not apply the controlnet
                    down_block_res_samples = None
                    mid_block_res_sample = None
                else:
                    # apply the controlnet
                    down_block_res_samples, mid_block_res_sample = self.controlnet(
                        latent_model_input,
                        t,
                        encoder_hidden_states=prompt_embeds,
                        controlnet_cond=controlnet_conditioning_image,
                        conditioning_scale=controlnet_conditioning_scale,
                        return_dict=False,
                    )

                # predict the noise residual
                noise_pred = self.unet(
                    latent_model_input,
                    t,
                    encoder_hidden_states=prompt_embeds,
                    cross_attention_kwargs=cross_attention_kwargs,
                    down_block_additional_residuals=down_block_res_samples,
                    mid_block_additional_residual=mid_block_res_sample,
                ).sample

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

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

                # 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 callback is not None and i % callback_steps == 0:
                        step_idx = i // getattr(self.scheduler, "order", 1)
                        callback(step_idx, t, latents)

        # If we do sequential model offloading, let's offload unet and controlnet
        # manually for max memory savings
        if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None:
            self.unet.to("cpu")
            self.controlnet.to("cpu")
            torch.cuda.empty_cache()

        if output_type == "latent":
            image = latents
            has_nsfw_concept = None
        elif output_type == "pil":
            # 8. Post-processing
            image = self.decode_latents(latents)

            # 9. Run safety checker
            image, has_nsfw_concept = self.run_safety_checker(image, device, prompt_embeds.dtype)

            # 10. Convert to PIL
            image = self.numpy_to_pil(image)
        else:
            # 8. Post-processing
            image = self.decode_latents(latents)

            # 9. Run safety checker
            image, has_nsfw_concept = self.run_safety_checker(image, device, prompt_embeds.dtype)

        # Offload last model to CPU
        if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None:
            self.final_offload_hook.offload()

        if not return_dict:
            return (image, has_nsfw_concept)

        return StableDiffusionPipelineOutput(images=image, nsfw_content_detected=has_nsfw_concept)