Upload 2 files

update to diffusers 0.31.0

controlnet.py

@@ -19,7 +19,7 @@ from torch import nn
 from torch.nn import functional as F
 
 from diffusers.configuration_utils import ConfigMixin, register_to_config
-from diffusers.loaders.controlnet import FromOriginalControlNetMixin
+from diffusers.loaders.single_file_model import FromOriginalModelMixin
 from diffusers.utils import BaseOutput, logging
 from diffusers.models.attention_processor import (
     ADDED_KV_ATTENTION_PROCESSORS,
@@ -54,7 +54,7 @@ class ControlNetOutput(BaseOutput):
             be of shape `(batch_size, channel * resolution, height //resolution, width // resolution)`. Output can be
             used to condition the original UNet's downsampling activations.
         mid_down_block_re_sample (`torch.Tensor`):
-            The activation of the midde block (the lowest sample resolution). Each tensor should be of shape
+            The activation of the middle block (the lowest sample resolution). Each tensor should be of shape
             `(batch_size, channel * lowest_resolution, height // lowest_resolution, width // lowest_resolution)`.
             Output can be used to condition the original UNet's middle block activation.
     """
@@ -76,12 +76,12 @@ class ControlNetConditioningEmbedding(nn.Module):
     def __init__(
         self,
         conditioning_embedding_channels: int,
-        conditioning_channels: int = 5, #update to 5
+        conditioning_channels: int = 5, # Bria: update to 5
         block_out_channels: Tuple[int, ...] = (16, 32, 96, 256),
     ):
         super().__init__()
 
-        self.conv_in = nn.Conv2d(conditioning_channels, block_out_channels[0], kernel_size=3, padding=1)
+        self.conv_in = nn.Conv2d(conditioning_channels, block_out_channels[0], kernel_size=3, padding=1) 
 
         self.blocks = nn.ModuleList([])
 
@@ -89,7 +89,7 @@ class ControlNetConditioningEmbedding(nn.Module):
             channel_in = block_out_channels[i]
             channel_out = block_out_channels[i + 1]
             self.blocks.append(nn.Conv2d(channel_in, channel_in, kernel_size=3, padding=1))
-            self.blocks.append(nn.Conv2d(channel_in, channel_out, kernel_size=3, padding=1, stride=1)) # update to 1
+            self.blocks.append(nn.Conv2d(channel_in, channel_out, kernel_size=3, padding=1, stride=1))  # Bria: update stride to 1
 
         self.conv_out = zero_module(
             nn.Conv2d(block_out_channels[-1], conditioning_embedding_channels, kernel_size=3, padding=1)
@@ -108,7 +108,7 @@ class ControlNetConditioningEmbedding(nn.Module):
         return embedding
 
 
-class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlNetMixin):
+class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalModelMixin):
     """
     A ControlNet model.
 
@@ -530,7 +530,7 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlNetMixin):
 
         def fn_recursive_add_processors(name: str, module: torch.nn.Module, processors: Dict[str, AttentionProcessor]):
             if hasattr(module, "get_processor"):
-                processors[f"{name}.processor"] = module.get_processor(return_deprecated_lora=True)
+                processors[f"{name}.processor"] = module.get_processor()
 
             for sub_name, child in module.named_children():
                 fn_recursive_add_processors(f"{name}.{sub_name}", child, processors)
@@ -665,10 +665,10 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlNetMixin):
 
     def forward(
         self,
-        sample: torch.FloatTensor,
+        sample: torch.Tensor,
         timestep: Union[torch.Tensor, float, int],
         encoder_hidden_states: torch.Tensor,
-        controlnet_cond: torch.FloatTensor,
+        controlnet_cond: torch.Tensor,
         conditioning_scale: float = 1.0,
         class_labels: Optional[torch.Tensor] = None,
         timestep_cond: Optional[torch.Tensor] = None,
@@ -677,18 +677,18 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlNetMixin):
         cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         guess_mode: bool = False,
         return_dict: bool = True,
-    ) -> Union[ControlNetOutput, Tuple[Tuple[torch.FloatTensor, ...], torch.FloatTensor]]:
+    ) -> Union[ControlNetOutput, Tuple[Tuple[torch.Tensor, ...], torch.Tensor]]:
         """
         The [`ControlNetModel`] forward method.
 
         Args:
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 The noisy input tensor.
             timestep (`Union[torch.Tensor, float, int]`):
                 The number of timesteps to denoise an input.
             encoder_hidden_states (`torch.Tensor`):
                 The encoder hidden states.
-            controlnet_cond (`torch.FloatTensor`):
+            controlnet_cond (`torch.Tensor`):
                 The conditional input tensor of shape `(batch_size, sequence_length, hidden_size)`.
             conditioning_scale (`float`, defaults to `1.0`):
                 The scale factor for ControlNet outputs.
@@ -710,12 +710,13 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlNetMixin):
                 In this mode, the ControlNet encoder tries its best to recognize the input content of the input even if
                 you remove all prompts. A `guidance_scale` between 3.0 and 5.0 is recommended.
             return_dict (`bool`, defaults to `True`):
-                Whether or not to return a [`~models.controlnet.ControlNetOutput`] instead of a plain tuple.
+                Whether or not to return a [`~models.controlnets.controlnet.ControlNetOutput`] instead of a plain
+                tuple.
 
         Returns:
-            [`~models.controlnet.ControlNetOutput`] **or** `tuple`:
-                If `return_dict` is `True`, a [`~models.controlnet.ControlNetOutput`] is returned, otherwise a tuple is
-                returned where the first element is the sample tensor.
+            [`~models.controlnets.controlnet.ControlNetOutput`] **or** `tuple`:
+                If `return_dict` is `True`, a [`~models.controlnets.controlnet.ControlNetOutput`] is returned,
+                otherwise a tuple is returned where the first element is the sample tensor.
         """
         # check channel order
         channel_order = self.config.controlnet_conditioning_channel_order
@@ -868,4 +869,4 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlNetMixin):
 def zero_module(module):
     for p in module.parameters():
         nn.init.zeros_(p)
-    return module
+    return module

pipeline_controlnet_sd_xl.py

@@ -30,14 +30,14 @@ from transformers import (
 
 from diffusers.utils.import_utils import is_invisible_watermark_available
 
-from image_processor import PipelineImageInput, VaeImageProcessor
+from .image_processor import PipelineImageInput, VaeImageProcessor
 from diffusers.loaders import (
     FromSingleFileMixin,
     IPAdapterMixin,
     StableDiffusionXLLoraLoaderMixin,
     TextualInversionLoaderMixin,
 )
-from controlnet import ControlNetModel
+from .controlnet import ControlNetModel
 # from diffusers.models import AutoencoderKL, ControlNetModel, ImageProjection, UNet2DConditionModel
 from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
 from diffusers.models.attention_processor import (
@@ -57,9 +57,9 @@ from diffusers.utils import (
     unscale_lora_layers,
 )
 from diffusers.utils.torch_utils import is_compiled_module, is_torch_version, randn_tensor
-from diffusers.pipelines.pipeline_utils import DiffusionPipeline
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
-
+from diffusers.callbacks import MultiPipelineCallbacks, PipelineCallback
 
 if is_invisible_watermark_available():
     from diffusers.pipelines.stable_diffusion_xl.watermark import StableDiffusionXLWatermarker
@@ -116,8 +116,69 @@ EXAMPLE_DOC_STRING = """
 """
 
 
+# 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,
+    sigmas: Optional[List[float]] = None,
+    **kwargs,
+):
+    r"""
+    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 StableDiffusionXLControlNetPipeline(
     DiffusionPipeline,
+    StableDiffusionMixin,
     TextualInversionLoaderMixin,
     StableDiffusionXLLoraLoaderMixin,
     IPAdapterMixin,
@@ -176,7 +237,16 @@ class StableDiffusionXLControlNetPipeline(
         "feature_extractor",
         "image_encoder",
     ]
-    _callback_tensor_inputs = ["latents", "prompt_embeds", "negative_prompt_embeds"]
+    _callback_tensor_inputs = [
+        "latents",
+        "prompt_embeds",
+        "negative_prompt_embeds",
+        "add_text_embeds",
+        "add_time_ids",
+        "negative_pooled_prompt_embeds",
+        "negative_add_time_ids",
+        "image",
+    ]
 
     def __init__(
         self,
@@ -224,39 +294,6 @@ class StableDiffusionXLControlNetPipeline(
 
         self.register_to_config(force_zeros_for_empty_prompt=force_zeros_for_empty_prompt)
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_vae_slicing
-    def enable_vae_slicing(self):
-        r"""
-        Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
-        compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
-        """
-        self.vae.enable_slicing()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_vae_slicing
-    def disable_vae_slicing(self):
-        r"""
-        Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_slicing()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.enable_vae_tiling
-    def enable_vae_tiling(self):
-        r"""
-        Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to
-        compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow
-        processing larger images.
-        """
-        self.vae.enable_tiling()
-
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.disable_vae_tiling
-    def disable_vae_tiling(self):
-        r"""
-        Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to
-        computing decoding in one step.
-        """
-        self.vae.disable_tiling()
-
     # Copied from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl.StableDiffusionXLPipeline.encode_prompt
     def encode_prompt(
         self,
@@ -267,10 +304,10 @@ class StableDiffusionXLControlNetPipeline(
         do_classifier_free_guidance: bool = True,
         negative_prompt: Optional[str] = None,
         negative_prompt_2: Optional[str] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = 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,
     ):
@@ -296,17 +333,17 @@ class StableDiffusionXLControlNetPipeline(
             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.FloatTensor`, *optional*):
+            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.FloatTensor`, *optional*):
+            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.FloatTensor`, *optional*):
+            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.FloatTensor`, *optional*):
+            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.
@@ -353,7 +390,7 @@ class StableDiffusionXLControlNetPipeline(
             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
+            # textual inversion: process multi-vector tokens if necessary
             prompt_embeds_list = []
             prompts = [prompt, prompt_2]
             for prompt, tokenizer, text_encoder in zip(prompts, tokenizers, text_encoders):
@@ -518,33 +555,50 @@ class StableDiffusionXLControlNetPipeline(
             return image_embeds, uncond_image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_ip_adapter_image_embeds
-    def prepare_ip_adapter_image_embeds(self, ip_adapter_image, device, num_images_per_prompt):
-        if not isinstance(ip_adapter_image, list):
-            ip_adapter_image = [ip_adapter_image]
+    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."
-            )
+            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."
+                )
 
-        image_embeds = []
-        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
-            )
-            single_image_embeds = torch.stack([single_image_embeds] * num_images_per_prompt, dim=0)
-            single_negative_image_embeds = torch.stack([single_negative_image_embeds] * num_images_per_prompt, dim=0)
+            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
+                )
 
-            if self.do_classifier_free_guidance:
-                single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
-                single_image_embeds = single_image_embeds.to(device)
+                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)
 
-            image_embeds.append(single_image_embeds)
+            single_image_embeds = single_image_embeds.to(device=device)
+            ip_adapter_image_embeds.append(single_image_embeds)
 
-        return image_embeds
+        return ip_adapter_image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
     def prepare_extra_step_kwargs(self, generator, eta):
@@ -575,6 +629,8 @@ class StableDiffusionXLControlNetPipeline(
         prompt_embeds=None,
         negative_prompt_embeds=None,
         pooled_prompt_embeds=None,
+        ip_adapter_image=None,
+        ip_adapter_image_embeds=None,
         negative_pooled_prompt_embeds=None,
         controlnet_conditioning_scale=1.0,
         control_guidance_start=0.0,
@@ -736,6 +792,21 @@ class StableDiffusionXLControlNetPipeline(
             if end > 1.0:
                 raise ValueError(f"control guidance end: {end} can't be larger than 1.0.")
 
+        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"
+                )
+
     # Copied from diffusers.pipelines.controlnet.pipeline_controlnet.StableDiffusionControlNetPipeline.check_image
     def check_image(self, image, prompt, prompt_embeds):
         image_is_pil = isinstance(image, PIL.Image.Image)
@@ -807,7 +878,12 @@ class StableDiffusionXLControlNetPipeline(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        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"
@@ -851,8 +927,6 @@ class StableDiffusionXLControlNetPipeline(
             (
                 AttnProcessor2_0,
                 XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
             ),
         )
         # if xformers or torch_2_0 is used attention block does not need
@@ -862,49 +936,23 @@ class StableDiffusionXLControlNetPipeline(
             self.vae.decoder.conv_in.to(dtype)
             self.vae.decoder.mid_block.to(dtype)
 
-    # 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):
+    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:
-            timesteps (`torch.Tensor`):
-                generate embedding vectors at these timesteps
+            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:
-                data type of the generated embeddings
+                Dimension of the embeddings to generate.
+            dtype (`torch.dtype`, *optional*, defaults to `torch.float32`):
+                Data type of the generated embeddings.
 
         Returns:
-            `torch.FloatTensor`: Embedding vectors with shape `(len(timesteps), embedding_dim)`
+            `torch.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
         """
         assert len(w.shape) == 1
         w = w * 1000.0
@@ -938,10 +986,18 @@ class StableDiffusionXLControlNetPipeline(
     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__(
@@ -952,18 +1008,22 @@ class StableDiffusionXLControlNetPipeline(
         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.FloatTensor] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = 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,
@@ -978,7 +1038,9 @@ class StableDiffusionXLControlNetPipeline(
         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: Optional[
+            Union[Callable[[int, int, Dict], None], PipelineCallback, MultiPipelineCallbacks]
+        ] = None,
         callback_on_step_end_tensor_inputs: List[str] = ["latents"],
         **kwargs,
     ):
@@ -991,14 +1053,14 @@ class StableDiffusionXLControlNetPipeline(
             prompt_2 (`str` or `List[str]`, *optional*):
                 The prompt or prompts to be sent to `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
                 used in both text-encoders.
-            image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
-                    `List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
+            image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
+                    `List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
                 The ControlNet input condition to provide guidance to the `unet` for generation. If the type is
-                specified as `torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be
-                accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If height
-                and/or width are passed, `image` is resized accordingly. If multiple ControlNets are specified in
-                `init`, images must be passed as a list such that each element of the list can be correctly batched for
-                input to a single ControlNet.
+                specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be accepted
+                as an image. The dimensions of the output image defaults to `image`'s dimensions. If height and/or
+                width are passed, `image` is resized accordingly. If multiple ControlNets are specified in `init`,
+                images must be passed as a list such that each element of the list can be correctly batched for input
+                to a single ControlNet.
             height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
                 The height in pixels of the generated image. 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)
@@ -1010,6 +1072,21 @@ class StableDiffusionXLControlNetPipeline(
             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):
                 A higher guidance scale value encourages the model to generate images closely linked to the text
                 `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
@@ -1027,24 +1104,29 @@ class StableDiffusionXLControlNetPipeline(
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                 generation deterministic.
-            latents (`torch.FloatTensor`, *optional*):
+            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 is generated by sampling using the supplied random `generator`.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
                 provided, text embeddings are generated from the `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
-            pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
+            pooled_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated pooled text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
                 not provided, pooled text embeddings are generated from `prompt` input argument.
-            negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs (prompt
                 weighting). If not provided, pooled `negative_prompt_embeds` are 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 generated image. Choose between `PIL.Image` or `np.array`.
             return_dict (`bool`, *optional*, defaults to `True`):
@@ -1096,15 +1178,15 @@ class StableDiffusionXLControlNetPipeline(
             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.
-            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 (`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 pipeine class.
+                `._callback_tensor_inputs` attribute of your pipeline class.
 
         Examples:
 
@@ -1130,6 +1212,9 @@ class StableDiffusionXLControlNetPipeline(
                 "Passing `callback_steps` as an input argument to `__call__` is deprecated, consider using `callback_on_step_end`",
             )
 
+        if isinstance(callback_on_step_end, (PipelineCallback, MultiPipelineCallbacks)):
+            callback_on_step_end_tensor_inputs = callback_on_step_end.tensor_inputs
+
         controlnet = self.controlnet._orig_mod if is_compiled_module(self.controlnet) else self.controlnet
 
         # align format for control guidance
@@ -1155,6 +1240,8 @@ class StableDiffusionXLControlNetPipeline(
             prompt_embeds,
             negative_prompt_embeds,
             pooled_prompt_embeds,
+            ip_adapter_image,
+            ip_adapter_image_embeds,
             negative_pooled_prompt_embeds,
             controlnet_conditioning_scale,
             control_guidance_start,
@@ -1165,6 +1252,8 @@ class StableDiffusionXLControlNetPipeline(
         self._guidance_scale = guidance_scale
         self._clip_skip = clip_skip
         self._cross_attention_kwargs = cross_attention_kwargs
+        self._denoising_end = denoising_end
+        self._interrupt = False
 
         # 2. Define call parameters
         if prompt is not None and isinstance(prompt, str):
@@ -1212,9 +1301,13 @@ class StableDiffusionXLControlNetPipeline(
         )
 
         # 3.2 Encode ip_adapter_image
-        if ip_adapter_image is not None:
+        if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare image
@@ -1231,7 +1324,7 @@ class StableDiffusionXLControlNetPipeline(
                 guess_mode=guess_mode,
             )
             height, width = image.shape[-2:]
-            height, width = height*self.vae_scale_factor, width*self.vae_scale_factor # for vae controlnet
+            height, width = height*self.vae_scale_factor, width*self.vae_scale_factor # Bria: update for vae controlnet 
         elif isinstance(controlnet, MultiControlNetModel):
             images = []
 
@@ -1256,8 +1349,9 @@ class StableDiffusionXLControlNetPipeline(
             assert False
 
         # 5. 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, sigmas
+        )
         self._num_timesteps = len(timesteps)
 
         # 6. Prepare latent variables
@@ -1336,11 +1430,31 @@ class StableDiffusionXLControlNetPipeline(
 
         # 8. Denoising loop
         num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
+
+        # 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
+                    - (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]
+
         is_unet_compiled = is_compiled_module(self.unet)
         is_controlnet_compiled = is_compiled_module(self.controlnet)
         is_torch_higher_equal_2_1 = is_torch_version(">=", "2.1")
         with self.progress_bar(total=num_inference_steps) as progress_bar:
             for i, t in enumerate(timesteps):
+                if self.interrupt:
+                    continue
+
                 # Relevant thread:
                 # https://dev-discuss.pytorch.org/t/cudagraphs-in-pytorch-2-0/1428
                 if (is_unet_compiled and is_controlnet_compiled) and is_torch_higher_equal_2_1:
@@ -1386,13 +1500,13 @@ class StableDiffusionXLControlNetPipeline(
                 )
 
                 if guess_mode and self.do_classifier_free_guidance:
-                    # Infered ControlNet only for the conditional batch.
+                    # Inferred ControlNet only for the conditional batch.
                     # To apply the output of ControlNet to both the unconditional and conditional batches,
                     # add 0 to the unconditional batch to keep it unchanged.
                     down_block_res_samples = [torch.cat([torch.zeros_like(d), d]) for d in down_block_res_samples]
                     mid_block_res_sample = torch.cat([torch.zeros_like(mid_block_res_sample), mid_block_res_sample])
 
-                if ip_adapter_image is not None:
+                if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
                     added_cond_kwargs["image_embeds"] = image_embeds
 
                 # predict the noise residual
@@ -1425,6 +1539,13 @@ class StableDiffusionXLControlNetPipeline(
                     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)
+                    image = callback_outputs.pop("image", image)
 
                 # call the callback, if provided
                 if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
@@ -1441,7 +1562,22 @@ class StableDiffusionXLControlNetPipeline(
                 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]
+            # unscale/denormalize the latents
+            # denormalize with the mean and std if available and not None
+            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]
 
             # cast back to fp16 if needed
             if needs_upcasting:
@@ -1462,4 +1598,4 @@ class StableDiffusionXLControlNetPipeline(
         if not return_dict:
             return (image,)
 
-        return StableDiffusionXLPipelineOutput(images=image)
+        return StableDiffusionXLPipelineOutput(images=image)