Updated diffusers code

pipeline_stable_diffusion_xl_opt.py

@@ -13,14 +13,24 @@
 # limitations under the License.
 
 import inspect
-import os
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
 import torch
-from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer
+from transformers import (
+    CLIPImageProcessor,
+    CLIPTextModel,
+    CLIPTextModelWithProjection,
+    CLIPTokenizer,
+    CLIPVisionModelWithProjection,
+)
 
-from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
+from diffusers.loaders import (
+    FromSingleFileMixin,
+    IPAdapterMixin,
+    StableDiffusionXLLoraLoaderMixin,
+    TextualInversionLoaderMixin,
+)
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.attention_processor import (
     AttnProcessor2_0,
@@ -28,22 +38,33 @@ from diffusers.models.attention_processor import (
     LoRAXFormersAttnProcessor,
     XFormersAttnProcessor,
 )
+from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.schedulers import KarrasDiffusionSchedulers
 from diffusers.utils import (
-    is_accelerate_available,
-    is_accelerate_version,
+    USE_PEFT_BACKEND,
+    deprecate,
     is_invisible_watermark_available,
+    is_torch_xla_available,
     logging,
-    randn_tensor,
     replace_example_docstring,
+    scale_lora_layers,
+    unscale_lora_layers,
 )
-from diffusers.pipeline_utils import DiffusionPipeline
-from diffusers.pipelines.stable_diffusion_xl import StableDiffusionXLPipelineOutput
+from diffusers.utils.torch_utils import randn_tensor
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline
+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
 
@@ -79,7 +100,58 @@ def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
     return noise_cfg
 
 
-class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoaderMixin):
+# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.retrieve_timesteps
+def retrieve_timesteps(
+    scheduler,
+    num_inference_steps: Optional[int] = None,
+    device: Optional[Union[str, torch.device]] = None,
+    timesteps: Optional[List[int]] = 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 support arbitrary spacing between timesteps. If `None`, then the default
+                timestep spacing strategy of the scheduler is used. If `timesteps` is passed, `num_inference_steps`
+                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:
+        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)
+    else:
+        scheduler.set_timesteps(num_inference_steps, device=device, **kwargs)
+        timesteps = scheduler.timesteps
+    return timesteps, num_inference_steps
+
+
+class StableDiffusionXLPipeline(
+    DiffusionPipeline,
+    FromSingleFileMixin,
+    StableDiffusionXLLoraLoaderMixin,
+    TextualInversionLoaderMixin,
+    IPAdapterMixin,
+):
     r"""
     Pipeline for text-to-image generation using Stable Diffusion XL.
 
@@ -87,11 +159,11 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
     library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
 
     In addition the pipeline inherits the following loading methods:
-        - *LoRA*: [`StableDiffusionXLPipeline.load_lora_weights`]
+        - *LoRA*: [`loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights`]
         - *Ckpt*: [`loaders.FromSingleFileMixin.from_single_file`]
 
     as well as the following saving methods:
-        - *LoRA*: [`loaders.StableDiffusionXLPipeline.save_lora_weights`]
+        - *LoRA*: [`loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights`]
 
     Args:
         vae ([`AutoencoderKL`]):
@@ -116,8 +188,34 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
         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->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,
@@ -127,6 +225,8 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
         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,
     ):
@@ -140,10 +240,13 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
             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()
@@ -186,36 +289,6 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
         """
         self.vae.disable_tiling()
 
-    def enable_model_cpu_offload(self, gpu_id=0):
-        r"""
-        Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared
-        to `enable_sequential_cpu_offload`, this method moves one whole model at a time to the GPU when its `forward`
-        method is called, and the model remains in GPU until the next model runs. Memory savings are lower than with
-        `enable_sequential_cpu_offload`, but performance is much better due to the iterative execution of the `unet`.
-        """
-        if is_accelerate_available() and is_accelerate_version(">=", "0.17.0.dev0"):
-            from accelerate import cpu_offload_with_hook
-        else:
-            raise ImportError("`enable_model_cpu_offload` requires `accelerate v0.17.0` or higher.")
-
-        device = torch.device(f"cuda:{gpu_id}")
-
-        if self.device.type != "cpu":
-            self.to("cpu", silence_dtype_warnings=True)
-            torch.cuda.empty_cache()  # otherwise we don't see the memory savings (but they probably exist)
-
-        model_sequence = (
-            [self.text_encoder, self.text_encoder_2] if self.text_encoder is not None else [self.text_encoder_2]
-        )
-        model_sequence.extend([self.unet, self.vae])
-
-        hook = None
-        for cpu_offloaded_model in model_sequence:
-            _, hook = cpu_offload_with_hook(cpu_offloaded_model, device, prev_module_hook=hook)
-
-        # We'll offload the last model manually.
-        self.final_offload_hook = hook
-
     def encode_prompt(
         self,
         prompt: str,
@@ -230,6 +303,7 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
         pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
         negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
         lora_scale: Optional[float] = None,
+        clip_skip: Optional[int] = None,
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
@@ -269,17 +343,33 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
                 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
 
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, StableDiffusionXLLoraLoaderMixin):
             self._lora_scale = lora_scale
 
-        if prompt is not None and isinstance(prompt, str):
-            batch_size = 1
-        elif prompt is not None and isinstance(prompt, list):
+            # 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]
@@ -292,6 +382,8 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
 
         if prompt_embeds is None:
             prompt_2 = prompt_2 or prompt
+            prompt_2 = [prompt_2] if isinstance(prompt_2, str) else prompt_2
+
             # textual inversion: procecss multi-vector tokens if necessary
             prompt_embeds_list = []
             prompts = [prompt, prompt_2]
@@ -319,29 +411,15 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
                         f" {tokenizer.model_max_length} tokens: {removed_text}"
                     )
 
-                prompt_embeds = text_encoder(
-                    text_input_ids.to(device),
-                    output_hidden_states=True,
-                )
+                prompt_embeds = text_encoder(text_input_ids.to(device), output_hidden_states=True)
 
                 # We are only ALWAYS interested in the pooled output of the final text encoder
                 pooled_prompt_embeds = prompt_embeds[0]
-                ### TODO: remove
-                null_text_inputs = tokenizer(
-                    ['a realistic photo of an empty background'] * batch_size,
-                    padding="max_length",
-                    max_length=tokenizer.model_max_length,
-                    truncation=True,
-                    return_tensors="pt",
-                )
-                null_input_ids = null_text_inputs.input_ids
-                null_prompt_embeds = text_encoder(
-                    null_input_ids.to(device),
-                    output_hidden_states=True,
-                )
-                pooled_prompt_embeds = null_prompt_embeds[0]
-                ### TODO: remove
-                prompt_embeds = prompt_embeds.hidden_states[-2]
+                if clip_skip is None:
+                    prompt_embeds = prompt_embeds.hidden_states[-2]
+                else:
+                    # "2" because SDXL always indexes from the penultimate layer.
+                    prompt_embeds = prompt_embeds.hidden_states[-(clip_skip + 2)]
 
                 prompt_embeds_list.append(prompt_embeds)
 
@@ -356,14 +434,18 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
             negative_prompt = negative_prompt or ""
             negative_prompt_2 = negative_prompt_2 or negative_prompt
 
+            # normalize str to list
+            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 isinstance(negative_prompt, str):
-                uncond_tokens = [negative_prompt, negative_prompt_2]
             elif batch_size != len(negative_prompt):
                 raise ValueError(
                     f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
@@ -399,7 +481,11 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
 
             negative_prompt_embeds = torch.concat(negative_prompt_embeds_list, dim=-1)
 
-        prompt_embeds = prompt_embeds.to(dtype=self.text_encoder_2.dtype, device=device)
+        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
         # duplicate text embeddings for each generation per prompt, using mps friendly method
         prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
@@ -408,7 +494,12 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
         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_2.dtype, device=device)
+
+            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)
 
@@ -420,8 +511,32 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
                 bs_embed * num_images_per_prompt, -1
             )
 
+        if self.text_encoder is not None:
+            if isinstance(self, StableDiffusionXLLoraLoaderMixin) and USE_PEFT_BACKEND:
+                # Retrieve the original scale by scaling back the LoRA layers
+                unscale_lora_layers(self.text_encoder, lora_scale)
+
+        if self.text_encoder_2 is not None:
+            if isinstance(self, StableDiffusionXLLoraLoaderMixin) and USE_PEFT_BACKEND:
+                # Retrieve the original scale by scaling back the LoRA layers
+                unscale_lora_layers(self.text_encoder_2, lora_scale)
+
         return prompt_embeds, negative_prompt_embeds, pooled_prompt_embeds, negative_pooled_prompt_embeds
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
+    def encode_image(self, image, device, num_images_per_prompt):
+        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)
+        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
+
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
     def prepare_extra_step_kwargs(self, generator, eta):
         # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
@@ -453,18 +568,24 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
         negative_prompt_embeds=None,
         pooled_prompt_embeds=None,
         negative_pooled_prompt_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 None) or (
-            callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0)
-        ):
+        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"
@@ -531,11 +652,13 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
         latents = latents * self.scheduler.init_noise_sigma
         return latents
 
-    def _get_add_time_ids(self, original_size, crops_coords_top_left, target_size, dtype):
+    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) + self.text_encoder_2.config.projection_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
 
@@ -567,7 +690,7 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
             self.vae.decoder.conv_in.to(dtype)
             self.vae.decoder.mid_block.to(dtype)
 
-    def update_loss(self, latents, i, t, prompt_embeds, cross_attention_kwargs, add_text_embeds, add_time_ids):
+    def update_loss(self, latents, i, t, prompt_embeds, timestep_cond, add_text_embeds, add_time_ids):
         def forward_pass(latent_model_input):
             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}
@@ -575,7 +698,8 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
                 latent_model_input,
                 t,
                 encoder_hidden_states=prompt_embeds,
-                cross_attention_kwargs=cross_attention_kwargs,
+                timestep_cond=timestep_cond,
+                cross_attention_kwargs=self.cross_attention_kwargs,
                 added_cond_kwargs=added_cond_kwargs,
                 return_dict=False,
             )
@@ -583,6 +707,94 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
 
         return self.editor.update_loss(forward_pass, latents, i)
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_freeu
+    def enable_freeu(self, s1: float, s2: float, b1: float, b2: float):
+        r"""Enables the FreeU mechanism as in https://arxiv.org/abs/2309.11497.
+
+        The suffixes after the scaling factors represent the stages where they are being applied.
+
+        Please refer to the [official repository](https://github.com/ChenyangSi/FreeU) for combinations of the values
+        that are known to work well for different pipelines such as Stable Diffusion v1, v2, and Stable Diffusion XL.
+
+        Args:
+            s1 (`float`):
+                Scaling factor for stage 1 to attenuate the contributions of the skip features. This is done to
+                mitigate "oversmoothing effect" in the enhanced denoising process.
+            s2 (`float`):
+                Scaling factor for stage 2 to attenuate the contributions of the skip features. This is done to
+                mitigate "oversmoothing effect" in the enhanced denoising process.
+            b1 (`float`): Scaling factor for stage 1 to amplify the contributions of backbone features.
+            b2 (`float`): Scaling factor for stage 2 to amplify the contributions of backbone features.
+        """
+        if not hasattr(self, "unet"):
+            raise ValueError("The pipeline must have `unet` for using FreeU.")
+        self.unet.enable_freeu(s1=s1, s2=s2, b1=b1, b2=b2)
+
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_freeu
+    def disable_freeu(self):
+        """Disables the FreeU mechanism if enabled."""
+        self.unet.disable_freeu()
+
+    # Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
+    def get_guidance_scale_embedding(self, w, embedding_dim=512, dtype=torch.float32):
+        """
+        See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298
+
+        Args:
+            timesteps (`torch.Tensor`):
+                generate embedding vectors at these timesteps
+            embedding_dim (`int`, *optional*, defaults to 512):
+                dimension of the embeddings to generate
+            dtype:
+                data type of the generated embeddings
+
+        Returns:
+            `torch.FloatTensor`: Embedding vectors with shape `(len(timesteps), 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
+
+    # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
+    # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+    # corresponds to doing no classifier free guidance.
+    @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
+
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
@@ -592,6 +804,7 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
         height: Optional[int] = None,
         width: Optional[int] = None,
         num_inference_steps: int = 50,
+        timesteps: List[int] = None,
         denoising_end: Optional[float] = None,
         guidance_scale: float = 5.0,
         negative_prompt: Optional[Union[str, List[str]]] = None,
@@ -604,15 +817,21 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
         negative_prompt_embeds: Optional[torch.FloatTensor] = None,
         pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
         negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
+        ip_adapter_image: Optional[PipelineImageInput] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
-        callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
-        callback_steps: int = 1,
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         guidance_rescale: float = 0.0,
         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[Callable[[int, int, Dict], None]] = None,
+        callback_on_step_end_tensor_inputs: List[str] = ["latents"],
+        **kwargs,
     ):
         r"""
         Function invoked when calling the pipeline for generation.
@@ -625,12 +844,22 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
                 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.
+                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.
+                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.
             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
@@ -677,30 +906,25 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
                 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.
             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.
-            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.FloatTensor)`.
-            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).
-            guidance_rescale (`float`, *optional*, defaults to 0.7):
+            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 `(width, height)` if not specified. Part of SDXL's micro-conditioning as
+                `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)):
@@ -710,8 +934,32 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
                 [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 `(width, height)`. Part of SDXL's micro-conditioning as explained in
+                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`, *optional*):
+                A function that calls at the end of each denoising steps during the inference. The function is called
+                with the following arguments: `callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int,
+                callback_kwargs: Dict)`. `callback_kwargs` will include a list of all tensors as specified by
+                `callback_on_step_end_tensor_inputs`.
+            callback_on_step_end_tensor_inputs (`List`, *optional*):
+                The list of tensor inputs for the `callback_on_step_end` function. The tensors specified in the list
+                will be passed as `callback_kwargs` argument. You will only be able to include variables listed in the
+                `._callback_tensor_inputs` attribute of your pipeline class.
 
         Examples:
 
@@ -720,6 +968,23 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
             [`~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`",
+            )
+
         # 0. Default height and width to unet
         height = height or self.default_sample_size * self.vae_scale_factor
         width = width or self.default_sample_size * self.vae_scale_factor
@@ -740,8 +1005,15 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
             negative_prompt_embeds,
             pooled_prompt_embeds,
             negative_pooled_prompt_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
+
         # 2. Define call parameters
         if prompt is not None and isinstance(prompt, str):
             batch_size = 1
@@ -752,15 +1024,11 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
 
         device = self._execution_device
 
-        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
-        # corresponds to doing no classifier free guidance.
-        do_classifier_free_guidance = guidance_scale > 1.0
-
         # 3. Encode input prompt
-        text_encoder_lora_scale = (
-            cross_attention_kwargs.get("scale", None) if cross_attention_kwargs is not None else None
+        lora_scale = (
+            self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
         )
+
         (
             prompt_embeds,
             negative_prompt_embeds,
@@ -771,20 +1039,19 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
             prompt_2=prompt_2,
             device=device,
             num_images_per_prompt=num_images_per_prompt,
-            do_classifier_free_guidance=do_classifier_free_guidance,
+            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=text_encoder_lora_scale,
+            lora_scale=lora_scale,
+            clip_skip=self.clip_skip,
         )
 
         # 4. Prepare timesteps
-        self.scheduler.set_timesteps(num_inference_steps, device=device)
-
-        timesteps = self.scheduler.timesteps
+        timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, timesteps)
 
         # 5. Prepare latent variables
         num_channels_latents = self.unet.config.in_channels
@@ -804,165 +1071,162 @@ class StableDiffusionXLPipeline(DiffusionPipeline, FromSingleFileMixin, LoraLoad
 
         # 7. Prepare added time ids & embeddings
         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
+            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 do_classifier_free_guidance:
+        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([add_time_ids, add_time_ids], 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:
+            image_embeds, negative_image_embeds = self.encode_image(ip_adapter_image, device, num_images_per_prompt)
+            if self.do_classifier_free_guidance:
+                image_embeds = torch.cat([negative_image_embeds, image_embeds])
+                image_embeds = image_embeds.to(device)
+
         # 8. Denoising loop
         num_warmup_steps = max(len(timesteps) - num_inference_steps * self.scheduler.order, 0)
 
-        # 7.1 Apply denoising_end
-        if denoising_end is not None and type(denoising_end) == float and denoising_end > 0 and denoising_end < 1:
+        # 8.1 Apply denoising_end
+        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
-                    - (denoising_end * 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]
 
+        # 9. Optionally get Guidance Scale Embedding
+        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)
         latents = latents.half()
         prompt_embeds = prompt_embeds.half()
         with self.progress_bar(total=num_inference_steps) as progress_bar:
             for i, t in enumerate(timesteps):
-                latents = self.update_loss(latents, i, t, prompt_embeds, cross_attention_kwargs, add_text_embeds, add_time_ids)
+                latents = self.update_loss(latents, i, t, prompt_embeds, timestep_cond, add_text_embeds, add_time_ids)
 
                 # 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 = torch.cat([latents] * 2) if self.do_classifier_free_guidance else latents
 
                 latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
 
                 # predict the noise residual
                 added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
+                if ip_adapter_image is not None:
+                    added_cond_kwargs["image_embeds"] = image_embeds
                 noise_pred = self.unet(
                     latent_model_input,
                     t,
                     encoder_hidden_states=prompt_embeds,
-                    cross_attention_kwargs=cross_attention_kwargs,
+                    timestep_cond=timestep_cond,
+                    cross_attention_kwargs=self.cross_attention_kwargs,
                     added_cond_kwargs=added_cond_kwargs,
                     return_dict=False,
                 )[0]
 
                 # perform guidance
-                if do_classifier_free_guidance:
+                if self.do_classifier_free_guidance:
                     noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
-                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
+                    noise_pred = noise_pred_uncond + self.guidance_scale * (noise_pred_text - noise_pred_uncond)
 
-                if do_classifier_free_guidance and guidance_rescale > 0.0:
+                if self.do_classifier_free_guidance and self.guidance_rescale > 0.0:
                     # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
-                    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=guidance_rescale)
+                    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=self.guidance_rescale)
 
                 # compute the previous noisy sample x_t -> x_t-1
                 latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
 
+                if callback_on_step_end is not None:
+                    callback_kwargs = {}
+                    for k in callback_on_step_end_tensor_inputs:
+                        callback_kwargs[k] = locals()[k]
+                    callback_outputs = callback_on_step_end(self, i, t, callback_kwargs)
+
+                    latents = callback_outputs.pop("latents", latents)
+                    prompt_embeds = callback_outputs.pop("prompt_embeds", prompt_embeds)
+                    negative_prompt_embeds = callback_outputs.pop("negative_prompt_embeds", negative_prompt_embeds)
+                    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)
+
                 # 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:
-                        callback(i, t, latents)
+                        step_idx = i // getattr(self.scheduler, "order", 1)
+                        callback(step_idx, t, latents)
 
-        # make sure the VAE is in float32 mode, as it overflows in float16
-        if self.vae.dtype == torch.float16 and self.vae.config.force_upcast:
-            self.upcast_vae()
-            latents = latents.to(next(iter(self.vae.post_quant_conv.parameters())).dtype)
+                if XLA_AVAILABLE:
+                    xm.mark_step()
 
         if not output_type == "latent":
+            # make sure the VAE is in float32 mode, as it overflows in float16
+            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)
+
             image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
+
+            # cast back to fp16 if needed
+            if needs_upcasting:
+                self.vae.to(dtype=torch.float16)
         else:
             image = latents
-            return StableDiffusionXLPipelineOutput(images=image)
 
-        # apply watermark if available
-        if self.watermark is not None:
-            image = self.watermark.apply_watermark(image)
+        if not output_type == "latent":
+            # apply watermark if available
+            if self.watermark is not None:
+                image = self.watermark.apply_watermark(image)
 
-        image = self.image_processor.postprocess(image, output_type=output_type)
+            image = self.image_processor.postprocess(image, output_type=output_type)
 
-        # Offload last model to CPU
-        if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None:
-            self.final_offload_hook.offload()
+        # Offload all models
+        self.maybe_free_model_hooks()
 
         if not return_dict:
             return (image,)
 
         return StableDiffusionXLPipelineOutput(images=image)
-
-    # Overrride to properly handle the loading and unloading of the additional text encoder.
-    def load_lora_weights(self, pretrained_model_name_or_path_or_dict: Union[str, Dict[str, torch.Tensor]], **kwargs):
-        # We could have accessed the unet config from `lora_state_dict()` too. We pass
-        # it here explicitly to be able to tell that it's coming from an SDXL
-        # pipeline.
-        state_dict, network_alphas = self.lora_state_dict(
-            pretrained_model_name_or_path_or_dict,
-            unet_config=self.unet.config,
-            **kwargs,
-        )
-        self.load_lora_into_unet(state_dict, network_alphas=network_alphas, unet=self.unet)
-
-        text_encoder_state_dict = {k: v for k, v in state_dict.items() if "text_encoder." in k}
-        if len(text_encoder_state_dict) > 0:
-            self.load_lora_into_text_encoder(
-                text_encoder_state_dict,
-                network_alphas=network_alphas,
-                text_encoder=self.text_encoder,
-                prefix="text_encoder",
-                lora_scale=self.lora_scale,
-            )
-
-        text_encoder_2_state_dict = {k: v for k, v in state_dict.items() if "text_encoder_2." in k}
-        if len(text_encoder_2_state_dict) > 0:
-            self.load_lora_into_text_encoder(
-                text_encoder_2_state_dict,
-                network_alphas=network_alphas,
-                text_encoder=self.text_encoder_2,
-                prefix="text_encoder_2",
-                lora_scale=self.lora_scale,
-            )
-
-    @classmethod
-    def save_lora_weights(
-        self,
-        save_directory: Union[str, os.PathLike],
-        unet_lora_layers: Dict[str, Union[torch.nn.Module, torch.Tensor]] = None,
-        text_encoder_lora_layers: Dict[str, Union[torch.nn.Module, torch.Tensor]] = None,
-        text_encoder_2_lora_layers: Dict[str, Union[torch.nn.Module, torch.Tensor]] = None,
-        is_main_process: bool = True,
-        weight_name: str = None,
-        save_function: Callable = None,
-        safe_serialization: bool = True,
-    ):
-        state_dict = {}
-
-        def pack_weights(layers, prefix):
-            layers_weights = layers.state_dict() if isinstance(layers, torch.nn.Module) else layers
-            layers_state_dict = {f"{prefix}.{module_name}": param for module_name, param in layers_weights.items()}
-            return layers_state_dict
-
-        state_dict.update(pack_weights(unet_lora_layers, "unet"))
-
-        if text_encoder_lora_layers and text_encoder_2_lora_layers:
-            state_dict.update(pack_weights(text_encoder_lora_layers, "text_encoder"))
-            state_dict.update(pack_weights(text_encoder_2_lora_layers, "text_encoder_2"))
-
-        self.write_lora_layers(
-            state_dict=state_dict,
-            save_directory=save_directory,
-            is_main_process=is_main_process,
-            weight_name=weight_name,
-            save_function=save_function,
-            safe_serialization=safe_serialization,
-        )
-
-    def _remove_text_encoder_monkey_patch(self):
-        self._remove_text_encoder_monkey_patch_classmethod(self.text_encoder)
-        self._remove_text_encoder_monkey_patch_classmethod(self.text_encoder_2)