Update src/pipeline.py

src/pipeline.py

@@ -1,1246 +1,12 @@
 import torch
+#import xformers
+#import triton
 from PIL.Image import Image
+from onediffx.deep_cache import StableDiffusionXLPipeline
+#from diffusers import StableDiffusionXLPipeline
 from pipelines.models import TextToImageRequest
 from torch import Generator
 
-import inspect
-from typing import Any, Callable, Dict, List, Optional, Tuple, Union
-
-from transformers import (
-    CLIPImageProcessor,
-    CLIPTextModel,
-    CLIPTextModelWithProjection,
-    CLIPTokenizer,
-    CLIPVisionModelWithProjection,
-)
-
-from diffusers.callbacks import MultiPipelineCallbacks, PipelineCallback
-from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
-from diffusers.loaders import (
-    FromSingleFileMixin,
-    IPAdapterMixin,
-    StableDiffusionXLLoraLoaderMixin,
-    TextualInversionLoaderMixin,
-)
-from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    FusedAttnProcessor2_0,
-    XFormersAttnProcessor,
-)
-from diffusers.models.lora import adjust_lora_scale_text_encoder
-from diffusers.schedulers import KarrasDiffusionSchedulers
-from diffusers.utils import (
-    USE_PEFT_BACKEND,
-    deprecate,
-    is_invisible_watermark_available,
-    is_torch_xla_available,
-    logging,
-    replace_example_docstring,
-    scale_lora_layers,
-    unscale_lora_layers,
-)
-from diffusers.utils.torch_utils import randn_tensor
-from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
-
-
-if is_invisible_watermark_available():
-    from .watermark import StableDiffusionXLWatermarker
-
-if is_torch_xla_available():
-    import torch_xla.core.xla_model as xm
-
-    XLA_AVAILABLE = True
-else:
-    XLA_AVAILABLE = False
-
-
-logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
-
-EXAMPLE_DOC_STRING = """
-    Examples:
-        ```py
-        >>> import torch
-        >>> from diffusers import StableDiffusionXLPipeline
-
-        >>> pipe = StableDiffusionXLPipeline.from_pretrained(
-        diffusers.     "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
-        diffusers. )
-        >>> pipe = pipe.to("cuda")
-
-        >>> prompt = "a photo of an astronaut riding a horse on mars"
-        >>> image = pipe(prompt).images[0]
-        ```
-"""
-
-def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
-    """
-    Rescale `noise_cfg` according to `guidance_rescale`. Based on findings of [Common Diffusion Noise Schedules and
-    Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf). See Section 3.4
-    """
-    std_text = noise_pred_text.std(dim=list(range(1, noise_pred_text.ndim)), keepdim=True)
-    std_cfg = noise_cfg.std(dim=list(range(1, noise_cfg.ndim)), keepdim=True)
-    # rescale the results from guidance (fixes overexposure)
-    noise_pred_rescaled = noise_cfg * (std_text / std_cfg)
-    # mix with the original results from guidance by factor guidance_rescale to avoid "plain looking" images
-    noise_cfg = guidance_rescale * noise_pred_rescaled + (1 - guidance_rescale) * noise_cfg
-    return noise_cfg
-
-
-def retrieve_timesteps(
-    scheduler,
-    num_inference_steps: Optional[int] = None,
-    device: Optional[Union[str, torch.device]] = None,
-    timesteps: Optional[List[int]] = None,
-    sigmas: Optional[List[float]] = None,
-    **kwargs,
-):
-    """
-    Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles
-    custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`.
-
-    Args:
-        scheduler (`SchedulerMixin`):
-            The scheduler to get timesteps from.
-        num_inference_steps (`int`):
-            The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps`
-            must be `None`.
-        device (`str` or `torch.device`, *optional*):
-            The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
-        timesteps (`List[int]`, *optional*):
-            Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed,
-            `num_inference_steps` and `sigmas` must be `None`.
-        sigmas (`List[float]`, *optional*):
-            Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed,
-            `num_inference_steps` and `timesteps` must be `None`.
-
-    Returns:
-        `Tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the
-        second element is the number of inference steps.
-    """
-    if timesteps is not None and sigmas is not None:
-        raise ValueError("Only one of `timesteps` or `sigmas` can be passed. Please choose one to set custom values")
-    if timesteps is not None:
-        accepts_timesteps = "timesteps" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accepts_timesteps:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" timestep schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(timesteps=timesteps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    elif sigmas is not None:
-        accept_sigmas = "sigmas" in set(inspect.signature(scheduler.set_timesteps).parameters.keys())
-        if not accept_sigmas:
-            raise ValueError(
-                f"The current scheduler class {scheduler.__class__}'s `set_timesteps` does not support custom"
-                f" sigmas schedules. Please check whether you are using the correct scheduler."
-            )
-        scheduler.set_timesteps(sigmas=sigmas, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-        num_inference_steps = len(timesteps)
-    else:
-        scheduler.set_timesteps(num_inference_steps, device=device, **kwargs)
-        timesteps = scheduler.timesteps
-    return timesteps, num_inference_steps
-
-
-class StableDiffusionXLPipeline(
-    DiffusionPipeline,
-    StableDiffusionMixin,
-    FromSingleFileMixin,
-    StableDiffusionXLLoraLoaderMixin,
-    TextualInversionLoaderMixin,
-    IPAdapterMixin,
-):
-    r"""
-    Pipeline for text-to-image generation using Stable Diffusion XL.
-
-    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
-    library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
-
-    The pipeline also inherits the following loading methods:
-        - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
-        - [`~loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
-        - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
-
-    Args:
-        vae ([`AutoencoderKL`]):
-            Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
-        text_encoder ([`CLIPTextModel`]):
-            Frozen text-encoder. Stable Diffusion XL uses the text portion of
-            [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 ([` CLIPTextModelWithProjection`]):
-            Second frozen text-encoder. Stable Diffusion XL uses the text and pool portion of
-            [CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModelWithProjection),
-            specifically the
-            [laion/CLIP-ViT-bigG-14-laion2B-39B-b160k](https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k)
-            variant.
-        tokenizer (`CLIPTokenizer`):
-            Tokenizer of class
-            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
-        tokenizer_2 (`CLIPTokenizer`):
-            Second Tokenizer of class
-            [CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
-        unet ([`UNet2DConditionModel`]): Conditional U-Net architecture to denoise the encoded image latents.
-        scheduler ([`SchedulerMixin`]):
-            A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
-            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
-        force_zeros_for_empty_prompt (`bool`, *optional*, defaults to `"True"`):
-            Whether the negative prompt embeddings shall be forced to always be set to 0. Also see the config of
-            `stabilityai/stable-diffusion-xl-base-1-0`.
-        add_watermarker (`bool`, *optional*):
-            Whether to use the [invisible_watermark library](https://github.com/ShieldMnt/invisible-watermark/) to
-            watermark output images. If not defined, it will default to True if the package is installed, otherwise no
-            watermarker will be used.
-    """
-
-    model_cpu_offload_seq = "text_encoder->text_encoder_2->image_encoder->unet->vae"
-    _optional_components = [
-        "tokenizer",
-        "tokenizer_2",
-        "text_encoder",
-        "text_encoder_2",
-        "image_encoder",
-        "feature_extractor",
-    ]
-    _callback_tensor_inputs = [
-        "latents",
-        "prompt_embeds",
-        "negative_prompt_embeds",
-        "add_text_embeds",
-        "add_time_ids",
-        "negative_pooled_prompt_embeds",
-        "negative_add_time_ids",
-    ]
-
-    def __init__(
-        self,
-        vae: AutoencoderKL,
-        text_encoder: CLIPTextModel,
-        text_encoder_2: CLIPTextModelWithProjection,
-        tokenizer: CLIPTokenizer,
-        tokenizer_2: CLIPTokenizer,
-        unet: UNet2DConditionModel,
-        scheduler: KarrasDiffusionSchedulers,
-        image_encoder: CLIPVisionModelWithProjection = None,
-        feature_extractor: CLIPImageProcessor = None,
-        force_zeros_for_empty_prompt: bool = True,
-        add_watermarker: Optional[bool] = None,
-    ):
-        super().__init__()
-
-        self.register_modules(
-            vae=vae,
-            text_encoder=text_encoder,
-            text_encoder_2=text_encoder_2,
-            tokenizer=tokenizer,
-            tokenizer_2=tokenizer_2,
-            unet=unet,
-            scheduler=scheduler,
-            image_encoder=image_encoder,
-            feature_extractor=feature_extractor,
-        )
-        self.register_to_config(force_zeros_for_empty_prompt=force_zeros_for_empty_prompt)
-        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
-        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
-
-        self.default_sample_size = self.unet.config.sample_size
-
-        add_watermarker = add_watermarker if add_watermarker is not None else is_invisible_watermark_available()
-
-        if add_watermarker:
-            self.watermark = StableDiffusionXLWatermarker()
-        else:
-            self.watermark = None
-
-    def encode_prompt(
-        self,
-        prompt: str,
-        prompt_2: Optional[str] = None,
-        device: Optional[torch.device] = None,
-        num_images_per_prompt: int = 1,
-        do_classifier_free_guidance: bool = True,
-        negative_prompt: Optional[str] = None,
-        negative_prompt_2: Optional[str] = None,
-        prompt_embeds: Optional[torch.Tensor] = None,
-        negative_prompt_embeds: Optional[torch.Tensor] = None,
-        pooled_prompt_embeds: Optional[torch.Tensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
-        lora_scale: Optional[float] = None,
-        clip_skip: Optional[int] = None,
-    ):
-        r"""
-        Encodes the prompt into text encoder hidden states.
-
-        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 both text-encoders
-            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`).
-            negative_prompt_2 (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation to be sent to `tokenizer_2` and
-                `text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
-            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.
-            pooled_prompt_embeds (`torch.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.
-            negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_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.
-            clip_skip (`int`, *optional*):
-                Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
-                the output of the pre-final layer will be used for computing the prompt embeddings.
-        """
-        device = device or self._execution_device
-
-        if lora_scale is not None and isinstance(self, StableDiffusionXLLoraLoaderMixin):
-            self._lora_scale = lora_scale
-
-            # dynamically adjust the LoRA scale
-            if self.text_encoder is not None:
-                if not USE_PEFT_BACKEND:
-                    adjust_lora_scale_text_encoder(self.text_encoder, lora_scale)
-                else:
-                    scale_lora_layers(self.text_encoder, lora_scale)
-
-            if self.text_encoder_2 is not None:
-                if not USE_PEFT_BACKEND:
-                    adjust_lora_scale_text_encoder(self.text_encoder_2, lora_scale)
-                else:
-                    scale_lora_layers(self.text_encoder_2, lora_scale)
-
-        prompt = [prompt] if isinstance(prompt, str) else prompt
-
-        if prompt is not None:
-            batch_size = len(prompt)
-        else:
-            batch_size = prompt_embeds.shape[0]
-
-        tokenizers = [self.tokenizer, self.tokenizer_2] if self.tokenizer is not None else [self.tokenizer_2]
-        text_encoders = (
-            [self.text_encoder, self.text_encoder_2] if self.text_encoder is not None else [self.text_encoder_2]
-        )
-
-        if prompt_embeds is None:
-            prompt_2 = prompt_2 or prompt
-            prompt_2 = [prompt_2] if isinstance(prompt_2, str) else prompt_2
-
-            prompt_embeds_list = []
-            prompts = [prompt, prompt_2]
-            for prompt, tokenizer, text_encoder in zip(prompts, tokenizers, text_encoders):
-                if isinstance(self, TextualInversionLoaderMixin):
-                    prompt = self.maybe_convert_prompt(prompt, tokenizer)
-
-                text_inputs = tokenizer(
-                    prompt,
-                    padding="max_length",
-                    max_length=tokenizer.model_max_length,
-                    truncation=True,
-                    return_tensors="pt",
-                )
-
-                text_input_ids = text_inputs.input_ids
-                untruncated_ids = 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 = tokenizer.batch_decode(untruncated_ids[:, 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" {tokenizer.model_max_length} tokens: {removed_text}"
-                    )
-
-                prompt_embeds = text_encoder(text_input_ids.to(device), output_hidden_states=True)
-
-                pooled_prompt_embeds = prompt_embeds[0]
-                if clip_skip is None:
-                    prompt_embeds = prompt_embeds.hidden_states[-2]
-                else:
-                    prompt_embeds = prompt_embeds.hidden_states[-(clip_skip + 2)]
-
-                prompt_embeds_list.append(prompt_embeds)
-
-            prompt_embeds = torch.concat(prompt_embeds_list, dim=-1)
-
-        zero_out_negative_prompt = negative_prompt is None and self.config.force_zeros_for_empty_prompt
-        if do_classifier_free_guidance and negative_prompt_embeds is None and zero_out_negative_prompt:
-            negative_prompt_embeds = torch.zeros_like(prompt_embeds)
-            negative_pooled_prompt_embeds = torch.zeros_like(pooled_prompt_embeds)
-        elif do_classifier_free_guidance and negative_prompt_embeds is None:
-            negative_prompt = negative_prompt or ""
-            negative_prompt_2 = negative_prompt_2 or negative_prompt
-
-            negative_prompt = batch_size * [negative_prompt] if isinstance(negative_prompt, str) else negative_prompt
-            negative_prompt_2 = (
-                batch_size * [negative_prompt_2] if isinstance(negative_prompt_2, str) else negative_prompt_2
-            )
-
-            uncond_tokens: List[str]
-            if prompt is not None and type(prompt) is not type(negative_prompt):
-                raise TypeError(
-                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
-                    f" {type(prompt)}."
-                )
-            elif batch_size != len(negative_prompt):
-                raise ValueError(
-                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
-                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
-                    " the batch size of `prompt`."
-                )
-            else:
-                uncond_tokens = [negative_prompt, negative_prompt_2]
-
-            negative_prompt_embeds_list = []
-            for negative_prompt, tokenizer, text_encoder in zip(uncond_tokens, tokenizers, text_encoders):
-                if isinstance(self, TextualInversionLoaderMixin):
-                    negative_prompt = self.maybe_convert_prompt(negative_prompt, tokenizer)
-
-                max_length = prompt_embeds.shape[1]
-                uncond_input = tokenizer(
-                    negative_prompt,
-                    padding="max_length",
-                    max_length=max_length,
-                    truncation=True,
-                    return_tensors="pt",
-                )
-
-                negative_prompt_embeds = text_encoder(
-                    uncond_input.input_ids.to(device),
-                    output_hidden_states=True,
-                )
-                negative_pooled_prompt_embeds = negative_prompt_embeds[0]
-                negative_prompt_embeds = negative_prompt_embeds.hidden_states[-2]
-
-                negative_prompt_embeds_list.append(negative_prompt_embeds)
-
-            negative_prompt_embeds = torch.concat(negative_prompt_embeds_list, dim=-1)
-
-        if self.text_encoder_2 is not None:
-            prompt_embeds = prompt_embeds.to(dtype=self.text_encoder_2.dtype, device=device)
-        else:
-            prompt_embeds = prompt_embeds.to(dtype=self.unet.dtype, device=device)
-
-        bs_embed, seq_len, _ = prompt_embeds.shape
-        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)
-
-        if do_classifier_free_guidance:
-            seq_len = negative_prompt_embeds.shape[1]
-
-            if self.text_encoder_2 is not None:
-                negative_prompt_embeds = negative_prompt_embeds.to(dtype=self.text_encoder_2.dtype, device=device)
-            else:
-                negative_prompt_embeds = negative_prompt_embeds.to(dtype=self.unet.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)
-
-        pooled_prompt_embeds = pooled_prompt_embeds.repeat(1, num_images_per_prompt).view(
-            bs_embed * num_images_per_prompt, -1
-        )
-        if do_classifier_free_guidance:
-            negative_pooled_prompt_embeds = negative_pooled_prompt_embeds.repeat(1, num_images_per_prompt).view(
-                bs_embed * num_images_per_prompt, -1
-            )
-
-        if self.text_encoder is not None:
-            if isinstance(self, StableDiffusionXLLoraLoaderMixin) and USE_PEFT_BACKEND:
-                unscale_lora_layers(self.text_encoder, lora_scale)
-
-        if self.text_encoder_2 is not None:
-            if isinstance(self, StableDiffusionXLLoraLoaderMixin) and USE_PEFT_BACKEND:
-                unscale_lora_layers(self.text_encoder_2, lora_scale)
-
-        return prompt_embeds, negative_prompt_embeds, pooled_prompt_embeds, negative_pooled_prompt_embeds
-
-    def encode_image(self, image, device, num_images_per_prompt, output_hidden_states=None):
-        dtype = next(self.image_encoder.parameters()).dtype
-
-        if not isinstance(image, torch.Tensor):
-            image = self.feature_extractor(image, return_tensors="pt").pixel_values
-
-        image = image.to(device=device, dtype=dtype)
-        if output_hidden_states:
-            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True).hidden_states[-2]
-            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
-            uncond_image_enc_hidden_states = self.image_encoder(
-                torch.zeros_like(image), output_hidden_states=True
-            ).hidden_states[-2]
-            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
-                num_images_per_prompt, dim=0
-            )
-            return image_enc_hidden_states, uncond_image_enc_hidden_states
-        else:
-            image_embeds = self.image_encoder(image).image_embeds
-            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
-            uncond_image_embeds = torch.zeros_like(image_embeds)
-
-            return image_embeds, uncond_image_embeds
-
-    def prepare_ip_adapter_image_embeds(
-        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
-    ):
-        image_embeds = []
-        if do_classifier_free_guidance:
-            negative_image_embeds = []
-        if ip_adapter_image_embeds is None:
-            if not isinstance(ip_adapter_image, list):
-                ip_adapter_image = [ip_adapter_image]
-
-            if len(ip_adapter_image) != len(self.unet.encoder_hid_proj.image_projection_layers):
-                raise ValueError(
-                    f"`ip_adapter_image` must have same length as the number of IP Adapters. Got {len(ip_adapter_image)} images and {len(self.unet.encoder_hid_proj.image_projection_layers)} IP Adapters."
-                )
-
-            for single_ip_adapter_image, image_proj_layer in zip(
-                ip_adapter_image, self.unet.encoder_hid_proj.image_projection_layers
-            ):
-                output_hidden_state = not isinstance(image_proj_layer, ImageProjection)
-                single_image_embeds, single_negative_image_embeds = self.encode_image(
-                    single_ip_adapter_image, device, 1, output_hidden_state
-                )
-
-                image_embeds.append(single_image_embeds[None, :])
-                if do_classifier_free_guidance:
-                    negative_image_embeds.append(single_negative_image_embeds[None, :])
-        else:
-            for single_image_embeds in ip_adapter_image_embeds:
-                if do_classifier_free_guidance:
-                    single_negative_image_embeds, single_image_embeds = single_image_embeds.chunk(2)
-                    negative_image_embeds.append(single_negative_image_embeds)
-                image_embeds.append(single_image_embeds)
-
-        ip_adapter_image_embeds = []
-        for i, single_image_embeds in enumerate(image_embeds):
-            single_image_embeds = torch.cat([single_image_embeds] * num_images_per_prompt, dim=0)
-            if do_classifier_free_guidance:
-                single_negative_image_embeds = torch.cat([negative_image_embeds[i]] * num_images_per_prompt, dim=0)
-                single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds], dim=0)
-
-            single_image_embeds = single_image_embeds.to(device=device)
-            ip_adapter_image_embeds.append(single_image_embeds)
-
-        return ip_adapter_image_embeds
-
-    def prepare_extra_step_kwargs(self, generator, eta):
-
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        # check if the scheduler accepts generator
-        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        if accepts_generator:
-            extra_step_kwargs["generator"] = generator
-        return extra_step_kwargs
-
-    def check_inputs(
-        self,
-        prompt,
-        prompt_2,
-        height,
-        width,
-        callback_steps,
-        negative_prompt=None,
-        negative_prompt_2=None,
-        prompt_embeds=None,
-        negative_prompt_embeds=None,
-        pooled_prompt_embeds=None,
-        negative_pooled_prompt_embeds=None,
-        ip_adapter_image=None,
-        ip_adapter_image_embeds=None,
-        callback_on_step_end_tensor_inputs=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 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 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]}"
-            )
-
-        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 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."
-            )
-        elif negative_prompt_2 is not None and negative_prompt_embeds is not None:
-            raise ValueError(
-                f"Cannot forward both `negative_prompt_2`: {negative_prompt_2} 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}."
-                )
-
-        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`."
-            )
-
-        if negative_prompt_embeds is not None and negative_pooled_prompt_embeds is None:
-            raise ValueError(
-                "If `negative_prompt_embeds` are provided, `negative_pooled_prompt_embeds` also have to be passed. Make sure to generate `negative_pooled_prompt_embeds` from the same text encoder that was used to generate `negative_prompt_embeds`."
-            )
-
-        if ip_adapter_image is not None and ip_adapter_image_embeds is not None:
-            raise ValueError(
-                "Provide either `ip_adapter_image` or `ip_adapter_image_embeds`. Cannot leave both `ip_adapter_image` and `ip_adapter_image_embeds` defined."
-            )
-
-        if ip_adapter_image_embeds is not None:
-            if not isinstance(ip_adapter_image_embeds, list):
-                raise ValueError(
-                    f"`ip_adapter_image_embeds` has to be of type `list` but is {type(ip_adapter_image_embeds)}"
-                )
-            elif ip_adapter_image_embeds[0].ndim not in [3, 4]:
-                raise ValueError(
-                    f"`ip_adapter_image_embeds` has to be a list of 3D or 4D tensors but is {ip_adapter_image_embeds[0].ndim}D"
-                )
-
-    def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (
-            batch_size,
-            num_channels_latents,
-            int(height) // self.vae_scale_factor,
-            int(width) // self.vae_scale_factor,
-        )
-        if isinstance(generator, list) and len(generator) != batch_size:
-            raise ValueError(
-                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
-                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
-            )
-
-        if latents is None:
-            latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
-        else:
-            latents = latents.to(device)
-
-        # scale the initial noise by the standard deviation required by the scheduler
-        latents = latents * self.scheduler.init_noise_sigma
-        return latents
-
-    def _get_add_time_ids(
-        self, original_size, crops_coords_top_left, target_size, dtype, text_encoder_projection_dim=None
-    ):
-        add_time_ids = list(original_size + crops_coords_top_left + target_size)
-
-        passed_add_embed_dim = (
-            self.unet.config.addition_time_embed_dim * len(add_time_ids) + text_encoder_projection_dim
-        )
-        expected_add_embed_dim = self.unet.add_embedding.linear_1.in_features
-
-        if expected_add_embed_dim != passed_add_embed_dim:
-            raise ValueError(
-                f"Model expects an added time embedding vector of length {expected_add_embed_dim}, but a vector of {passed_add_embed_dim} was created. The model has an incorrect config. Please check `unet.config.time_embedding_type` and `text_encoder_2.config.projection_dim`."
-            )
-
-        add_time_ids = torch.tensor([add_time_ids], dtype=dtype)
-        return add_time_ids
-
-    def upcast_vae(self):
-        dtype = self.vae.dtype
-        self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                FusedAttnProcessor2_0,
-            ),
-        )
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
-
-    def get_guidance_scale_embedding(
-        self, w: torch.Tensor, embedding_dim: int = 512, dtype: torch.dtype = torch.float32
-    ) -> torch.Tensor:
-        """
-        See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298
-
-        Args:
-            w (`torch.Tensor`):
-                Generate embedding vectors with a specified guidance scale to subsequently enrich timestep embeddings.
-            embedding_dim (`int`, *optional*, defaults to 512):
-                Dimension of the embeddings to generate.
-            dtype (`torch.dtype`, *optional*, defaults to `torch.float32`):
-                Data type of the generated embeddings.
-
-        Returns:
-            `torch.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
-        """
-        assert len(w.shape) == 1
-        w = w * 1000.0
-
-        half_dim = embedding_dim // 2
-        emb = torch.log(torch.tensor(10000.0)) / (half_dim - 1)
-        emb = torch.exp(torch.arange(half_dim, dtype=dtype) * -emb)
-        emb = w.to(dtype)[:, None] * emb[None, :]
-        emb = torch.cat([torch.sin(emb), torch.cos(emb)], dim=1)
-        if embedding_dim % 2 == 1:  # zero pad
-            emb = torch.nn.functional.pad(emb, (0, 1))
-        assert emb.shape == (w.shape[0], embedding_dim)
-        return emb
-
-    @property
-    def guidance_scale(self):
-        return self._guidance_scale
-
-    @property
-    def guidance_rescale(self):
-        return self._guidance_rescale
-
-    @property
-    def clip_skip(self):
-        return self._clip_skip
-
-    @property
-    def do_classifier_free_guidance(self):
-        return self._guidance_scale > 1 and self.unet.config.time_cond_proj_dim is None
-
-    @property
-    def cross_attention_kwargs(self):
-        return self._cross_attention_kwargs
-
-    @property
-    def denoising_end(self):
-        return self._denoising_end
-
-    @property
-    def num_timesteps(self):
-        return self._num_timesteps
-
-    @property
-    def interrupt(self):
-        return self._interrupt
-
-    @torch.no_grad()
-    @replace_example_docstring(EXAMPLE_DOC_STRING)
-    def __call__(
-        self,
-        prompt: Union[str, List[str]] = None,
-        prompt_2: Optional[Union[str, List[str]]] = None,
-        height: Optional[int] = None,
-        width: Optional[int] = None,
-        num_inference_steps: int = 50,
-        timesteps: List[int] = None,
-        sigmas: List[float] = None,
-        denoising_end: Optional[float] = None,
-        guidance_scale: float = 5.0,
-        negative_prompt: Optional[Union[str, List[str]]] = None,
-        negative_prompt_2: 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,
-        pooled_prompt_embeds: Optional[torch.Tensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
-        ip_adapter_image: Optional[PipelineImageInput] = None,
-        ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
-        output_type: Optional[str] = "pil",
-        return_dict: bool = True,
-        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
-        guidance_rescale: float = 0.0,
-        end_cfg: float = 0.73,
-        original_size: Optional[Tuple[int, int]] = None,
-        crops_coords_top_left: Tuple[int, int] = (0, 0),
-        target_size: Optional[Tuple[int, int]] = None,
-        negative_original_size: Optional[Tuple[int, int]] = None,
-        negative_crops_coords_top_left: Tuple[int, int] = (0, 0),
-        negative_target_size: Optional[Tuple[int, int]] = None,
-        clip_skip: Optional[int] = None,
-        callback_on_step_end: Optional[
-            Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
-        ] = None,
-        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
-        **kwargs,
-    ):
-        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 the `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
-                used in both text-encoders
-            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.
-                Anything below 512 pixels won't work well for
-                [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
-                and checkpoints that are not specifically fine-tuned on low resolutions.
-            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.
-                Anything below 512 pixels won't work well for
-                [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
-                and checkpoints that are not specifically fine-tuned on low resolutions.
-            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.
-            timesteps (`List[int]`, *optional*):
-                Custom timesteps to use for the denoising process with schedulers which support a `timesteps` argument
-                in their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is
-                passed will be used. Must be in descending order.
-            sigmas (`List[float]`, *optional*):
-                Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
-                their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
-                will be used.
-            denoising_end (`float`, *optional*):
-                When specified, determines the fraction (between 0.0 and 1.0) of the total denoising process to be
-                completed before it is intentionally prematurely terminated. As a result, the returned sample will
-                still retain a substantial amount of noise as determined by the discrete timesteps selected by the
-                scheduler. The denoising_end parameter should ideally be utilized when this pipeline forms a part of a
-                "Mixture of Denoisers" multi-pipeline setup, as elaborated in [**Refining the Image
-                Output**](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl#refining-the-image-output)
-            guidance_scale (`float`, *optional*, defaults to 5.0):
-                Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-                `guidance_scale` is defined as `w` of equation 2. of [Imagen
-                Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
-                1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
-                usually at the expense of lower image quality.
-            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`).
-            negative_prompt_2 (`str` or `List[str]`, *optional*):
-                The prompt or prompts not to guide the image generation to be sent to `tokenizer_2` and
-                `text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
-            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://arxiv.org/abs/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 ge 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.
-            pooled_prompt_embeds (`torch.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.
-            negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
-                Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
-                weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
-                input argument.
-            ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
-            ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
-                IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
-                contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
-                provided, embeddings are computed from the `ip_adapter_image` 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_xl.StableDiffusionXLPipelineOutput`] instead
-                of a plain tuple.
-            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).
-            guidance_rescale (`float`, *optional*, defaults to 0.0):
-                Guidance rescale factor proposed by [Common Diffusion Noise Schedules and Sample Steps are
-                Flawed](https://arxiv.org/pdf/2305.08891.pdf) `guidance_scale` is defined as `φ` in equation 16. of
-                [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf).
-                Guidance rescale factor should fix overexposure when using zero terminal SNR.
-            original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                If `original_size` is not the same as `target_size` the image will appear to be down- or upsampled.
-                `original_size` defaults to `(height, width)` if not specified. Part of SDXL's micro-conditioning as
-                explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
-            crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
-                `crops_coords_top_left` can be used to generate an image that appears to be "cropped" from the position
-                `crops_coords_top_left` downwards. Favorable, well-centered images are usually achieved by setting
-                `crops_coords_top_left` to (0, 0). Part of SDXL's micro-conditioning as explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
-            target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                For most cases, `target_size` should be set to the desired height and width of the generated image. If
-                not specified it will default to `(height, width)`. Part of SDXL's micro-conditioning as explained in
-                section 2.2 of [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952).
-            negative_original_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                To negatively condition the generation process based on a specific image resolution. Part of SDXL's
-                micro-conditioning as explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
-                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
-            negative_crops_coords_top_left (`Tuple[int]`, *optional*, defaults to (0, 0)):
-                To negatively condition the generation process based on a specific crop coordinates. Part of SDXL's
-                micro-conditioning as explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
-                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
-            negative_target_size (`Tuple[int]`, *optional*, defaults to (1024, 1024)):
-                To negatively condition the generation process based on a target image resolution. It should be as same
-                as the `target_size` for most cases. Part of SDXL's micro-conditioning as explained in section 2.2 of
-                [https://huggingface.co/papers/2307.01952](https://huggingface.co/papers/2307.01952). For more
-                information, refer to this issue thread: https://github.com/huggingface/diffusers/issues/4208.
-            callback_on_step_end (`Callable`, `PipelineCallback`, `MultiPipelineCallbacks`, *optional*):
-                A function or a subclass of `PipelineCallback` or `MultiPipelineCallbacks` that is called at the end of
-                each denoising step during the inference. with the following arguments: `callback_on_step_end(self:
-                DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)`. `callback_kwargs` will include a
-                list of all tensors as specified by `callback_on_step_end_tensor_inputs`.
-            callback_on_step_end_tensor_inputs (`List`, *optional*):
-                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
-                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
-                `._callback_tensor_inputs` attribute of your pipeline class.
-
-        Examples:
-
-        Returns:
-            [`~pipelines.stable_diffusion_xl.StableDiffusionXLPipelineOutput`] or `tuple`:
-            [`~pipelines.stable_diffusion_xl.StableDiffusionXLPipelineOutput`] if `return_dict` is True, otherwise a
-            `tuple`. When returning a tuple, the first element is a list with the generated images.
-        """
-
-        callback = kwargs.pop("callback", None)
-        callback_steps = kwargs.pop("callback_steps", None)
-
-        if callback is not None:
-            deprecate(
-                "callback",
-                "1.0.0",
-                "Passing `callback` as an input argument to `__call__` is deprecated, consider use `callback_on_step_end`",
-            )
-        if callback_steps is not None:
-            deprecate(
-                "callback_steps",
-                "1.0.0",
-                "Passing `callback_steps` as an input argument to `__call__` is deprecated, consider use `callback_on_step_end`",
-            )
-
-        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
-            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs
-
-        height = height or self.default_sample_size * self.vae_scale_factor
-        width = width or self.default_sample_size * self.vae_scale_factor
-
-        original_size = original_size or (height, width)
-        target_size = target_size or (height, width)
-
-        self.check_inputs(
-            prompt,
-            prompt_2,
-            height,
-            width,
-            callback_steps,
-            negative_prompt,
-            negative_prompt_2,
-            prompt_embeds,
-            negative_prompt_embeds,
-            pooled_prompt_embeds,
-            negative_pooled_prompt_embeds,
-            ip_adapter_image,
-            ip_adapter_image_embeds,
-            callback_on_step_end_tensor_inputs,
-        )
-
-        self._guidance_scale = guidance_scale
-        self._guidance_rescale = guidance_rescale
-        self._clip_skip = clip_skip
-        self._cross_attention_kwargs = cross_attention_kwargs
-        self._denoising_end = denoising_end
-        self._interrupt = False
-
-        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
-
-        lora_scale = (
-            self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
-        )
-
-        (
-            prompt_embeds,
-            negative_prompt_embeds,
-            pooled_prompt_embeds,
-            negative_pooled_prompt_embeds,
-        ) = self.encode_prompt(
-            prompt=prompt,
-            prompt_2=prompt_2,
-            device=device,
-            num_images_per_prompt=num_images_per_prompt,
-            do_classifier_free_guidance=self.do_classifier_free_guidance,
-            negative_prompt=negative_prompt,
-            negative_prompt_2=negative_prompt_2,
-            prompt_embeds=prompt_embeds,
-            negative_prompt_embeds=negative_prompt_embeds,
-            pooled_prompt_embeds=pooled_prompt_embeds,
-            negative_pooled_prompt_embeds=negative_pooled_prompt_embeds,
-            lora_scale=lora_scale,
-            clip_skip=self.clip_skip,
-        )
-
-        timesteps, num_inference_steps = retrieve_timesteps(
-            self.scheduler, num_inference_steps, device, timesteps, sigmas
-        )
-
-        # 5. Prepare latent variables
-        num_channels_latents = self.unet.config.in_channels
-        latents = self.prepare_latents(
-            batch_size * num_images_per_prompt,
-            num_channels_latents,
-            height,
-            width,
-            prompt_embeds.dtype,
-            device,
-            generator,
-            latents,
-        )
-
-        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
-
-        add_text_embeds = pooled_prompt_embeds
-        if self.text_encoder_2 is None:
-            text_encoder_projection_dim = int(pooled_prompt_embeds.shape[-1])
-        else:
-            text_encoder_projection_dim = self.text_encoder_2.config.projection_dim
-
-        add_time_ids = self._get_add_time_ids(
-            original_size,
-            crops_coords_top_left,
-            target_size,
-            dtype=prompt_embeds.dtype,
-            text_encoder_projection_dim=text_encoder_projection_dim,
-        )
-        if negative_original_size is not None and negative_target_size is not None:
-            negative_add_time_ids = self._get_add_time_ids(
-                negative_original_size,
-                negative_crops_coords_top_left,
-                negative_target_size,
-                dtype=prompt_embeds.dtype,
-                text_encoder_projection_dim=text_encoder_projection_dim,
-            )
-        else:
-            negative_add_time_ids = add_time_ids
-
-        if self.do_classifier_free_guidance:
-            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
-            add_text_embeds = torch.cat([negative_pooled_prompt_embeds, add_text_embeds], dim=0)
-            add_time_ids = torch.cat([negative_add_time_ids, add_time_ids], dim=0)
-
-        prompt_embeds = prompt_embeds.to(device)
-        add_text_embeds = add_text_embeds.to(device)
-        add_time_ids = add_time_ids.to(device).repeat(batch_size * num_images_per_prompt, 1)
-
-        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
-            image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image,
-                ip_adapter_image_embeds,
-                device,
-                batch_size * num_images_per_prompt,
-                self.do_classifier_free_guidance,
-            )
-
-        num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
-
-        if (
-            self.denoising_end is not None
-            and isinstance(self.denoising_end, float)
-            and self.denoising_end > 0
-            and self.denoising_end < 1
-        ):
-            discrete_timestep_cutoff = int(
-                round(
-                    self.scheduler.config.num_train_timesteps
-                    - (self.denoising_end * self.scheduler.config.num_train_timesteps)
-                )
-            )
-            num_inference_steps = len(list(filter(lambda ts: ts >= discrete_timestep_cutoff, timesteps)))
-            timesteps = timesteps[:num_inference_steps]
-
-        timestep_cond = None
-        if self.unet.config.time_cond_proj_dim is not None:
-            guidance_scale_tensor = torch.tensor(self.guidance_scale - 1).repeat(batch_size * num_images_per_prompt)
-            timestep_cond = self.get_guidance_scale_embedding(
-                guidance_scale_tensor, embedding_dim=self.unet.config.time_cond_proj_dim
-            ).to(device=device, dtype=latents.dtype)
-
-        self._num_timesteps = len(timesteps)
-        with self.progress_bar(total=num_inference_steps) as progress_bar:
-            do_classifier_free_guidance = self.do_classifier_free_guidance
-            for i, t in enumerate(timesteps):
-                if self.interrupt:
-                    continue
-                if end_cfg is not None and i / num_inference_steps > end_cfg and do_classifier_free_guidance:
-                    do_classifier_free_guidance = False
-                    prompt_embeds = torch.chunk(prompt_embeds, 2, dim=0)[-1]
-                    add_text_embeds = torch.chunk(add_text_embeds, 2, dim=0)[-1]
-                    add_time_ids = torch.chunk(add_time_ids, 2, dim=0)[-1]
-                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)
-
-                added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
-                if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
-                    added_cond_kwargs["image_embeds"] = image_embeds
-                noise_pred = self.unet(
-                    latent_model_input,
-                    t,
-                    encoder_hidden_states=prompt_embeds,
-                    timestep_cond=timestep_cond,
-                    cross_attention_kwargs=self.cross_attention_kwargs,
-                    added_cond_kwargs=added_cond_kwargs,
-                    return_dict=False,
-                )[0]
-
-                if do_classifier_free_guidance:
-                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                    noise_pred = noise_pred_uncond + self.guidance_scale * (noise_pred_text - noise_pred_uncond)
-
-                if do_classifier_free_guidance and self.guidance_rescale > 0.0:
-                    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=self.guidance_rescale)
-
-                latents_dtype = latents.dtype
-                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
-                if latents.dtype != latents_dtype:
-                    if torch.backends.mps.is_available():
-                        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)
-                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)
-                    add_text_embeds = callback_outputs.pop("add_text_embeds", add_text_embeds)
-                    negative_pooled_prompt_embeds = callback_outputs.pop(
-                        "negative_pooled_prompt_embeds", negative_pooled_prompt_embeds
-                    )
-                    add_time_ids = callback_outputs.pop("add_time_ids", add_time_ids)
-                    negative_add_time_ids = callback_outputs.pop("negative_add_time_ids", negative_add_time_ids)
-
-                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 XLA_AVAILABLE:
-                    xm.mark_step()
-
-        if not output_type == "latent":
-            needs_upcasting = self.vae.dtype == torch.float16 and self.vae.config.force_upcast
-
-            if needs_upcasting:
-                self.upcast_vae()
-                latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)
-            elif latents.dtype != self.vae.dtype:
-                if torch.backends.mps.is_available():
-                    self.vae = self.vae.to(latents.dtype)
-
-            has_latents_mean = hasattr(self.vae.config, "latents_mean") and self.vae.config.latents_mean is not None
-            has_latents_std = hasattr(self.vae.config, "latents_std") and self.vae.config.latents_std is not None
-            if has_latents_mean and has_latents_std:
-                latents_mean = (
-                    torch.tensor(self.vae.config.latents_mean).view(1, 4, 1, 1).to(latents.device, latents.dtype)
-                )
-                latents_std = (
-                    torch.tensor(self.vae.config.latents_std).view(1, 4, 1, 1).to(latents.device, latents.dtype)
-                )
-                latents = latents * latents_std / self.vae.config.scaling_factor + latents_mean
-            else:
-                latents = latents / self.vae.config.scaling_factor
-
-            image = self.vae.decode(latents, return_dict=False)[0]
-
-            if needs_upcasting:
-                self.vae.to(dtype=torch.float16)
-        else:
-            image = latents
-
-        if not output_type == "latent":
-            if self.watermark is not None:
-                image = self.watermark.apply_watermark(image)
-
-            image = self.image_processor.postprocess(image, output_type=output_type)
-
-        self.maybe_free_model_hooks()
-
-        if not return_dict:
-            return (image,)
-
-        return StableDiffusionXLPipelineOutput(images=image)
-
 #from onediff.schedulers import EulerDiscreteScheduler
 from onediffx import compile_pipe
 
@@ -1256,15 +22,12 @@ def load_pipeline(pipeline=None) -> StableDiffusionXLPipeline:
  #   pipeline.scheduler.config,)
 
     pipeline.to("cuda")
+    
     pipeline = compile_pipe(pipeline)
     for _ in range(4):
-        pipeline(prompt="kamala harris flying to the moon", num_inference_steps=20, end_cfg=0.73)
-
-
-
+        deepcache_output = pipeline(prompt="kamala harris defends my submission", output_type="pil", cache_interval=1, cache_layer_id=1, cache_block_id=0)
     return pipeline
 
-
 def infer(request: TextToImageRequest, pipeline: StableDiffusionXLPipeline) -> Image:
     if request.seed is None:
         generator = None
@@ -1277,6 +40,12 @@ def infer(request: TextToImageRequest, pipeline: StableDiffusionXLPipeline) -> I
         width=request.width,
         height=request.height,
         generator=generator,
-        end_cfg=0.73,
+        end_cfg=0.5,
         num_inference_steps=20,
+        cache_interval=1,
+        cache_layer_id=1,
+        cache_block_id=0,
+        eta=1,
+        guidance_scale = 5.0,
+        guidance_rescale = 0.0,
     ).images[0]