diff --git a/docs/source/en/using-diffusers/ip_adapter.md b/docs/source/en/using-diffusers/ip_adapter.md
index fdb45c5b637c..38f7b12398df 100644
--- a/docs/source/en/using-diffusers/ip_adapter.md
+++ b/docs/source/en/using-diffusers/ip_adapter.md
@@ -234,6 +234,39 @@ export_to_gif(frames, "gummy_bear.gif")
 > [!TIP]
 > While calling `load_ip_adapter()`, pass `low_cpu_mem_usage=True` to speed up the loading time.
 
+All the pipelines supporting IP-Adapter accept a `ip_adapter_image_embeds` argument. If you need to run the IP-Adapter multiple times with the same image, you can encode the image once and save the embedding to the disk.
+
+```py
+image_embeds = pipeline.prepare_ip_adapter_image_embeds(
+    ip_adapter_image=image,
+    ip_adapter_image_embeds=None,
+    device="cuda",
+    num_images_per_prompt=1,
+    do_classifier_free_guidance=True,
+)
+
+torch.save(image_embeds, "image_embeds.ipadpt")
+```
+
+Load the image embedding and pass it to the pipeline as `ip_adapter_image_embeds`
+
+> [!TIP]
+> ComfyUI image embeddings for IP-Adapters are fully compatible in Diffusers and should work out-of-box.
+
+```py
+image_embeds = torch.load("image_embeds.ipadpt")
+images = pipeline(
+    prompt="a polar bear sitting in a chair drinking a milkshake",
+    ip_adapter_image_embeds=image_embeds,
+    negative_prompt="deformed, ugly, wrong proportion, low res, bad anatomy, worst quality, low quality",
+    num_inference_steps=100,
+    generator=generator,
+).images
+```
+
+> [!TIP]
+> If you use IP-Adapter with `ip_adapter_image_embedding` instead of `ip_adapter_image`, you can choose not to load an image encoder by passing `image_encoder_folder=None` to `load_ip_adapter()`. 
+
 ## Specific use cases
 
 IP-Adapter's image prompting and compatibility with other adapters and models makes it a versatile tool for a variety of use cases. This section covers some of the more popular applications of IP-Adapter, and we can't wait to see what you come up with!
diff --git a/examples/community/pipeline_animatediff_controlnet.py b/examples/community/pipeline_animatediff_controlnet.py
index 44fc1bae6f7f..56dd856e1811 100644
--- a/examples/community/pipeline_animatediff_controlnet.py
+++ b/examples/community/pipeline_animatediff_controlnet.py
@@ -799,8 +799,10 @@ def __call__(
             ip_adapter_image (`PipelineImageInput`, *optional*):
                 Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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.
             conditioning_frames (`List[PipelineImageInput]`, *optional*):
                 The ControlNet input condition to provide guidance to the `unet` for generation. If multiple ControlNets
                 are specified, images must be passed as a list such that each element of the list can be correctly
diff --git a/examples/community/pipeline_animatediff_img2video.py b/examples/community/pipeline_animatediff_img2video.py
index 982bed08140b..fecb7211c7b9 100644
--- a/examples/community/pipeline_animatediff_img2video.py
+++ b/examples/community/pipeline_animatediff_img2video.py
@@ -798,8 +798,10 @@ def __call__(
             ip_adapter_image: (`PipelineImageInput`, *optional*):
                 Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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 video. Choose between `torch.FloatTensor`, `PIL.Image` or
                 `np.array`.
diff --git a/src/diffusers/loaders/ip_adapter.py b/src/diffusers/loaders/ip_adapter.py
index d6bf50e51eee..2b70ed84d7ed 100644
--- a/src/diffusers/loaders/ip_adapter.py
+++ b/src/diffusers/loaders/ip_adapter.py
@@ -13,7 +13,7 @@
 # limitations under the License.
 
 from pathlib import Path
-from typing import Dict, List, Union
+from typing import Dict, List, Optional, Union
 
 import torch
 from huggingface_hub.utils import validate_hf_hub_args
@@ -52,11 +52,12 @@ def load_ip_adapter(
         pretrained_model_name_or_path_or_dict: Union[str, List[str], Dict[str, torch.Tensor]],
         subfolder: Union[str, List[str]],
         weight_name: Union[str, List[str]],
+        image_encoder_folder: Optional[str] = "image_encoder",
         **kwargs,
     ):
         """
         Parameters:
-            pretrained_model_name_or_path_or_dict (`str` or `os.PathLike` or `dict`):
+            pretrained_model_name_or_path_or_dict (`str` or `List[str]` or `os.PathLike` or `List[os.PathLike]` or `dict` or `List[dict]`):
                 Can be either:
 
                     - A string, the *model id* (for example `google/ddpm-celebahq-256`) of a pretrained model hosted on
@@ -65,7 +66,18 @@ def load_ip_adapter(
                       with [`ModelMixin.save_pretrained`].
                     - A [torch state
                       dict](https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict).
-
+            subfolder (`str` or `List[str]`):
+                The subfolder location of a model file within a larger model repository on the Hub or locally.
+                If a list is passed, it should have the same length as `weight_name`.
+            weight_name (`str` or `List[str]`):
+                The name of the weight file to load. If a list is passed, it should have the same length as
+                `weight_name`.
+            image_encoder_folder (`str`, *optional*, defaults to `image_encoder`):
+                The subfolder location of the image encoder within a larger model repository on the Hub or locally.
+                Pass `None` to not load the image encoder. If the image encoder is located in a folder inside `subfolder`,
+                you only need to pass the name of the folder that contains image encoder weights, e.g. `image_encoder_folder="image_encoder"`.
+                If the image encoder is located in a folder other than `subfolder`, you should pass the path to the folder that contains image encoder weights,
+                for example, `image_encoder_folder="different_subfolder/image_encoder"`.
             cache_dir (`Union[str, os.PathLike]`, *optional*):
                 Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
                 is not used.
@@ -87,8 +99,6 @@ def load_ip_adapter(
             revision (`str`, *optional*, defaults to `"main"`):
                 The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
                 allowed by Git.
-            subfolder (`str`, *optional*, defaults to `""`):
-                The subfolder location of a model file within a larger model repository on the Hub or locally.
             low_cpu_mem_usage (`bool`, *optional*, defaults to `True` if torch version >= 1.9.0 else `False`):
                 Speed up model loading only loading the pretrained weights and not initializing the weights. This also
                 tries to not use more than 1x model size in CPU memory (including peak memory) while loading the model.
@@ -184,16 +194,29 @@ def load_ip_adapter(
 
             # load CLIP image encoder here if it has not been registered to the pipeline yet
             if hasattr(self, "image_encoder") and getattr(self, "image_encoder", None) is None:
-                if not isinstance(pretrained_model_name_or_path_or_dict, dict):
-                    logger.info(f"loading image_encoder from {pretrained_model_name_or_path_or_dict}")
-                    image_encoder = CLIPVisionModelWithProjection.from_pretrained(
-                        pretrained_model_name_or_path_or_dict,
-                        subfolder=Path(subfolder, "image_encoder").as_posix(),
-                        low_cpu_mem_usage=low_cpu_mem_usage,
-                    ).to(self.device, dtype=self.dtype)
-                    self.register_modules(image_encoder=image_encoder)
+                if image_encoder_folder is not None:
+                    if not isinstance(pretrained_model_name_or_path_or_dict, dict):
+                        logger.info(f"loading image_encoder from {pretrained_model_name_or_path_or_dict}")
+                        if image_encoder_folder.count("/") == 0:
+                            image_encoder_subfolder = Path(subfolder, image_encoder_folder).as_posix()
+                        else:
+                            image_encoder_subfolder = Path(image_encoder_folder).as_posix()
+
+                        image_encoder = CLIPVisionModelWithProjection.from_pretrained(
+                            pretrained_model_name_or_path_or_dict,
+                            subfolder=image_encoder_subfolder,
+                            low_cpu_mem_usage=low_cpu_mem_usage,
+                        ).to(self.device, dtype=self.dtype)
+                        self.register_modules(image_encoder=image_encoder)
+                    else:
+                        raise ValueError(
+                            "`image_encoder` cannot be loaded because `pretrained_model_name_or_path_or_dict` is a state dict."
+                        )
                 else:
-                    raise ValueError("`image_encoder` cannot be None when using IP Adapters.")
+                    logger.warning(
+                        "image_encoder is not loaded since `image_encoder_folder=None` passed. You will not be able to use `ip_adapter_image` when calling the pipeline with IP-Adapter."
+                        "Use `ip_adapter_image_embedding` to pass pre-geneated image embedding instead."
+                    )
 
             # create feature extractor if it has not been registered to the pipeline yet
             if hasattr(self, "feature_extractor") and getattr(self, "feature_extractor", None) is None:
diff --git a/src/diffusers/pipelines/animatediff/pipeline_animatediff.py b/src/diffusers/pipelines/animatediff/pipeline_animatediff.py
index db52e75fce23..e98d4ad4e37b 100644
--- a/src/diffusers/pipelines/animatediff/pipeline_animatediff.py
+++ b/src/diffusers/pipelines/animatediff/pipeline_animatediff.py
@@ -370,7 +370,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -394,13 +394,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
@@ -494,6 +504,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
     def prepare_latents(
         self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents=None
@@ -612,8 +632,10 @@ def __call__(
             ip_adapter_image: (`PipelineImageInput`, *optional*):
                 Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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 video. Choose between `torch.FloatTensor`, `PIL.Image` or
                 `np.array`.
@@ -717,7 +739,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_videos_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_videos_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare timesteps
diff --git a/src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py b/src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py
index 2963d181b274..ced64889044f 100644
--- a/src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py
+++ b/src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py
@@ -448,7 +448,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -472,13 +472,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
@@ -523,6 +533,8 @@ def check_inputs(
         negative_prompt=None,
         prompt_embeds=None,
         negative_prompt_embeds=None,
+        ip_adapter_image=None,
+        ip_adapter_image_embeds=None,
         callback_on_step_end_tensor_inputs=None,
     ):
         if strength < 0 or strength > 1:
@@ -567,6 +579,21 @@ def check_inputs(
         if video is not None and latents is not None:
             raise ValueError("Only one of `video` or `latents` should be provided")
 
+        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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     def get_timesteps(self, num_inference_steps, timesteps, strength, device):
         # get the original timestep using init_timestep
         init_timestep = min(int(num_inference_steps * strength), num_inference_steps)
@@ -765,8 +792,10 @@ def __call__(
             ip_adapter_image: (`PipelineImageInput`, *optional*):
                 Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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 video. Choose between `torch.FloatTensor`, `PIL.Image` or
                 `np.array`.
@@ -814,6 +843,8 @@ def __call__(
             negative_prompt_embeds=negative_prompt_embeds,
             video=video,
             latents=latents,
+            ip_adapter_image=ip_adapter_image,
+            ip_adapter_image_embeds=ip_adapter_image_embeds,
             callback_on_step_end_tensor_inputs=callback_on_step_end_tensor_inputs,
         )
 
@@ -855,7 +886,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_videos_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_videos_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare timesteps
diff --git a/src/diffusers/pipelines/controlnet/pipeline_controlnet.py b/src/diffusers/pipelines/controlnet/pipeline_controlnet.py
index 0f5fcfeca3c1..eab2f7aa22d0 100644
--- a/src/diffusers/pipelines/controlnet/pipeline_controlnet.py
+++ b/src/diffusers/pipelines/controlnet/pipeline_controlnet.py
@@ -480,7 +480,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -504,13 +504,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
@@ -711,6 +721,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     def check_image(self, image, prompt, prompt_embeds):
         image_is_pil = isinstance(image, PIL.Image.Image)
         image_is_tensor = isinstance(image, torch.Tensor)
@@ -933,8 +953,10 @@ def __call__(
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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`):
@@ -1076,7 +1098,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare image
diff --git a/src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py b/src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py
index fe672db5bf8e..4fc9791d3d8e 100644
--- a/src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py
+++ b/src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py
@@ -473,7 +473,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -497,13 +497,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
@@ -698,6 +708,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D 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)
@@ -951,8 +971,10 @@ def __call__(
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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`):
@@ -1088,7 +1110,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare image
diff --git a/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py b/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py
index 80a430b15592..ce7537d84215 100644
--- a/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py
+++ b/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py
@@ -598,7 +598,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -622,13 +622,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
@@ -856,6 +866,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D 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)
@@ -1180,8 +1200,10 @@ def __call__(
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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`):
@@ -1330,7 +1352,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare image
diff --git a/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py b/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py
index e42977a7b55a..0f1d5ea48e71 100644
--- a/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py
+++ b/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py
@@ -507,7 +507,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -531,13 +531,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
@@ -802,6 +812,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     def prepare_control_image(
         self,
         image,
@@ -1220,8 +1240,10 @@ def __call__(
                 argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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.
             pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
                 Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
                 If not provided, pooled text embeddings will be generated from `prompt` input argument.
@@ -1411,7 +1433,11 @@ def __call__(
         # 3.1 Encode ip_adapter_image
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. set timesteps
diff --git a/src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl.py b/src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl.py
index 4e0a880a4a11..9883b4f64790 100644
--- a/src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl.py
+++ b/src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl.py
@@ -485,7 +485,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -509,13 +509,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
@@ -715,6 +725,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D 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)
@@ -998,8 +1018,10 @@ def __call__(
                 argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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`):
@@ -1171,7 +1193,11 @@ def __call__(
         # 3.2 Encode ip_adapter_image
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare image
diff --git a/src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl_img2img.py b/src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl_img2img.py
index 41a8c4fa005e..cf32ae81c562 100644
--- a/src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl_img2img.py
+++ b/src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl_img2img.py
@@ -537,7 +537,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -561,13 +561,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
@@ -779,6 +789,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     # Copied from diffusers.pipelines.controlnet.pipeline_controlnet_sd_xl.StableDiffusionXLControlNetPipeline.check_image
     def check_image(self, image, prompt, prompt_embeds):
         image_is_pil = isinstance(image, PIL.Image.Image)
@@ -1149,8 +1169,10 @@ def __call__(
                 input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters.
+                Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should contain the negative image embedding
+                if `do_classifier_free_guidance` is set to `True`.
+                If not provided, embeddings are computed from the `ip_adapter_image` input argument.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
                 [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
@@ -1334,7 +1356,11 @@ def __call__(
         # 3.2 Encode ip_adapter_image
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare image and controlnet_conditioning_image
diff --git a/src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_img2img.py b/src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_img2img.py
index e6adae97ea6c..6d1b1a0db444 100644
--- a/src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_img2img.py
+++ b/src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_img2img.py
@@ -423,7 +423,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -447,13 +447,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
@@ -632,6 +642,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     @property
     def guidance_scale(self):
         return self._guidance_scale
@@ -720,8 +740,10 @@ def __call__(
             ip_adapter_image: (`PipelineImageInput`, *optional*):
                 Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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`):
@@ -794,7 +816,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 3. Encode input prompt
diff --git a/src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_text2img.py b/src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_text2img.py
index 0112fb916369..fa27c0fbd5bc 100644
--- a/src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_text2img.py
+++ b/src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_text2img.py
@@ -407,7 +407,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -431,13 +431,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
@@ -527,6 +537,8 @@ def check_inputs(
         width: int,
         callback_steps: int,
         prompt_embeds: Optional[torch.FloatTensor] = None,
+        ip_adapter_image=None,
+        ip_adapter_image_embeds=None,
         callback_on_step_end_tensor_inputs=None,
     ):
         if height % 8 != 0 or width % 8 != 0:
@@ -557,6 +569,21 @@ def check_inputs(
         elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
             raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
 
+        if 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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     @property
     def guidance_scale(self):
         return self._guidance_scale
@@ -645,8 +672,10 @@ def __call__(
             ip_adapter_image: (`PipelineImageInput`, *optional*):
                 Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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`):
@@ -699,7 +728,16 @@ def __call__(
         width = width or self.unet.config.sample_size * self.vae_scale_factor
 
         # 1. Check inputs. Raise error if not correct
-        self.check_inputs(prompt, height, width, callback_steps, prompt_embeds, callback_on_step_end_tensor_inputs)
+        self.check_inputs(
+            prompt,
+            height,
+            width,
+            callback_steps,
+            prompt_embeds,
+            ip_adapter_image,
+            ip_adapter_image_embeds,
+            callback_on_step_end_tensor_inputs,
+        )
         self._guidance_scale = guidance_scale
         self._clip_skip = clip_skip
         self._cross_attention_kwargs = cross_attention_kwargs
@@ -716,7 +754,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 3. Encode input prompt
diff --git a/src/diffusers/pipelines/pia/pipeline_pia.py b/src/diffusers/pipelines/pia/pipeline_pia.py
index 9feebf29d797..485ccb22e5e9 100644
--- a/src/diffusers/pipelines/pia/pipeline_pia.py
+++ b/src/diffusers/pipelines/pia/pipeline_pia.py
@@ -577,9 +577,19 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -603,13 +613,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
@@ -798,8 +818,10 @@ def __call__(
             ip_adapter_image: (`PipelineImageInput`, *optional*):
                 Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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.
             motion_scale: (`int`, *optional*, defaults to 0):
                 Parameter that controls the amount and type of motion that is added to the image. Increasing the value increases the amount of motion, while specific
                 ranges of values control the type of motion that is added. Must be between 0 and 8.
@@ -891,7 +913,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_videos_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_videos_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare timesteps
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
index 762565ea1fd3..5126e6f4c378 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
@@ -490,7 +490,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
             return image_embeds, uncond_image_embeds
 
     def prepare_ip_adapter_image_embeds(
-        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -514,13 +514,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     def run_safety_checker(self, image, device, dtype):
@@ -624,6 +634,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
         shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
         if isinstance(generator, list) and len(generator) != batch_size:
@@ -772,8 +792,10 @@ def __call__(
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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`):
@@ -885,7 +907,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare timesteps
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py
index 23b6e0f20520..9c6fbb2310ac 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py
@@ -534,7 +534,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -558,13 +558,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
@@ -670,6 +680,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     def get_timesteps(self, num_inference_steps, strength, device):
         # get the original timestep using init_timestep
         init_timestep = min(int(num_inference_steps * strength), num_inference_steps)
@@ -868,8 +888,10 @@ def __call__(
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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`):
@@ -967,7 +989,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Preprocess image
diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py
index 4664da1550f2..3392fd6ddecc 100644
--- a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py
+++ b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py
@@ -606,7 +606,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -630,13 +630,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
@@ -752,6 +762,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     def prepare_latents(
         self,
         batch_size,
@@ -1037,8 +1057,10 @@ def __call__(
                 not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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`):
@@ -1175,7 +1197,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. set timesteps
diff --git a/src/diffusers/pipelines/stable_diffusion_ldm3d/pipeline_stable_diffusion_ldm3d.py b/src/diffusers/pipelines/stable_diffusion_ldm3d/pipeline_stable_diffusion_ldm3d.py
index ddbf9ebbb1d0..502cd340bcd8 100644
--- a/src/diffusers/pipelines/stable_diffusion_ldm3d/pipeline_stable_diffusion_ldm3d.py
+++ b/src/diffusers/pipelines/stable_diffusion_ldm3d/pipeline_stable_diffusion_ldm3d.py
@@ -410,8 +410,9 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
             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, ip_adapter_image_embeds, do_classifier_free_guidance, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -441,7 +442,17 @@ def prepare_ip_adapter_image_embeds(
 
                 image_embeds.append(single_image_embeds)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     def run_safety_checker(self, image, device, dtype):
@@ -537,6 +548,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
         shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
         if isinstance(generator, list) and len(generator) != batch_size:
@@ -619,8 +640,10 @@ def __call__(
             ip_adapter_image: (`PipelineImageInput`, *optional*):
                 Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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`):
@@ -682,9 +705,9 @@ def __call__(
             image_embeds = self.prepare_ip_adapter_image_embeds(
                 ip_adapter_image,
                 ip_adapter_image_embeds,
-                do_classifier_free_guidance,
                 device,
                 batch_size * num_images_per_prompt,
+                do_classifier_free_guidance,
             )
 
         # 3. Encode input prompt
diff --git a/src/diffusers/pipelines/stable_diffusion_panorama/pipeline_stable_diffusion_panorama.py b/src/diffusers/pipelines/stable_diffusion_panorama/pipeline_stable_diffusion_panorama.py
index 1b371b4746ad..49cc68926b7e 100644
--- a/src/diffusers/pipelines/stable_diffusion_panorama/pipeline_stable_diffusion_panorama.py
+++ b/src/diffusers/pipelines/stable_diffusion_panorama/pipeline_stable_diffusion_panorama.py
@@ -384,7 +384,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -408,13 +408,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
@@ -535,6 +545,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     # 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)
@@ -644,8 +664,10 @@ def __call__(
             ip_adapter_image: (`PipelineImageInput`, *optional*):
                 Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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`):
@@ -710,7 +732,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 3. Encode input prompt
diff --git a/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py b/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py
index 98028f8be50e..4a34ae89d245 100644
--- a/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py
+++ b/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py
@@ -519,7 +519,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -543,13 +543,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
@@ -656,6 +666,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     # 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)
@@ -890,8 +910,10 @@ def __call__(
                 input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters.
+                Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should contain the negative image embedding
+                if `do_classifier_free_guidance` is set to `True`.
+                If not provided, embeddings are computed from the `ip_adapter_image` input argument.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
                 [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
@@ -1093,7 +1115,11 @@ def __call__(
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 8. Denoising loop
diff --git a/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py b/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py
index 58c6f3ff6ebf..ef25ca94d16c 100644
--- a/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py
+++ b/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py
@@ -611,6 +611,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     def get_timesteps(self, num_inference_steps, strength, device, denoising_start=None):
         # get the original timestep using init_timestep
         if denoising_start is None:
@@ -742,7 +752,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -766,13 +776,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     def _get_add_time_ids(
@@ -1038,8 +1058,10 @@ def __call__(
                 input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters.
+                Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should contain the negative image embedding
+                if `do_classifier_free_guidance` is set to `True`.
+                If not provided, embeddings are computed from the `ip_adapter_image` input argument.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
                 [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
@@ -1264,7 +1286,11 @@ def denoising_value_valid(dnv):
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 9. Denoising loop
diff --git a/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py b/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py
index 7c966c73acf8..2cb946eb56ad 100644
--- a/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py
+++ b/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py
@@ -456,7 +456,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -480,13 +480,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl.StableDiffusionXLPipeline.encode_prompt
@@ -836,6 +846,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     def prepare_latents(
         self,
         batch_size,
@@ -1290,8 +1310,10 @@ def __call__(
                 input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                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.
             num_images_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             eta (`float`, *optional*, defaults to 0.0):
@@ -1612,7 +1634,11 @@ def denoising_value_valid(dnv):
 
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 11. Denoising loop
diff --git a/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py b/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py
index 96c7c6857c05..abf743f4f305 100644
--- a/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py
+++ b/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py
@@ -533,7 +533,7 @@ def encode_image(self, image, device, num_images_per_prompt, output_hidden_state
 
     # 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, ip_adapter_image_embeds, device, num_images_per_prompt
+        self, ip_adapter_image, ip_adapter_image_embeds, device, num_images_per_prompt, do_classifier_free_guidance
     ):
         if ip_adapter_image_embeds is None:
             if not isinstance(ip_adapter_image, list):
@@ -557,13 +557,23 @@ def prepare_ip_adapter_image_embeds(
                     [single_negative_image_embeds] * num_images_per_prompt, dim=0
                 )
 
-                if self.do_classifier_free_guidance:
+                if 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)
         else:
-            image_embeds = ip_adapter_image_embeds
+            image_embeds = []
+            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)
+                    single_negative_image_embeds = single_negative_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                    single_image_embeds = torch.cat([single_negative_image_embeds, single_image_embeds])
+                else:
+                    single_image_embeds = single_image_embeds.repeat(num_images_per_prompt, 1, 1)
+                image_embeds.append(single_image_embeds)
+
         return image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
@@ -671,6 +681,16 @@ def check_inputs(
                 "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 != 3:
+                raise ValueError(
+                    f"`ip_adapter_image_embeds` has to be a list of 3D tensors but is {ip_adapter_image_embeds[0].ndim}D"
+                )
+
     # 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)
@@ -914,8 +934,10 @@ def __call__(
                 input argument.
             ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
             ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
-                Pre-generated image embeddings for IP-Adapter. If not
-                provided, embeddings are computed from the `ip_adapter_image` input argument.
+                Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of IP-adapters.
+                Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should contain the negative image embedding
+                if `do_classifier_free_guidance` is set to `True`.
+                If not provided, embeddings are computed from the `ip_adapter_image` input argument.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
                 [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
@@ -1057,7 +1079,11 @@ def __call__(
         # 3.2 Encode ip_adapter_image
         if ip_adapter_image is not None or ip_adapter_image_embeds is not None:
             image_embeds = self.prepare_ip_adapter_image_embeds(
-                ip_adapter_image, ip_adapter_image_embeds, device, batch_size * num_images_per_prompt
+                ip_adapter_image,
+                ip_adapter_image_embeds,
+                device,
+                batch_size * num_images_per_prompt,
+                self.do_classifier_free_guidance,
             )
 
         # 4. Prepare timesteps
diff --git a/tests/pipelines/test_pipelines_common.py b/tests/pipelines/test_pipelines_common.py
index 0ca464d3bd13..1475e2ff07d2 100644
--- a/tests/pipelines/test_pipelines_common.py
+++ b/tests/pipelines/test_pipelines_common.py
@@ -319,6 +319,35 @@ def test_ip_adapter_multi(self, expected_max_diff: float = 1e-4):
             "Output with multi-ip-adapter scale must be different from normal inference",
         )
 
+    def test_ip_adapter_cfg(self, expected_max_diff: float = 1e-4):
+        parameters = inspect.signature(self.pipeline_class.__call__).parameters
+
+        if "guidance_scale" not in parameters:
+            return
+
+        components = self.get_dummy_components()
+        pipe = self.pipeline_class(**components).to(torch_device)
+        pipe.set_progress_bar_config(disable=None)
+        cross_attention_dim = pipe.unet.config.get("cross_attention_dim", 32)
+
+        adapter_state_dict = create_ip_adapter_state_dict(pipe.unet)
+        pipe.unet._load_ip_adapter_weights(adapter_state_dict)
+        pipe.set_ip_adapter_scale(1.0)
+
+        # forward pass with CFG not applied
+        inputs = self._modify_inputs_for_ip_adapter_test(self.get_dummy_inputs(torch_device))
+        inputs["ip_adapter_image_embeds"] = [self._get_dummy_image_embeds(cross_attention_dim)[0].unsqueeze(0)]
+        inputs["guidance_scale"] = 1.0
+        out_no_cfg = pipe(**inputs)[0]
+
+        # forward pass with CFG applied
+        inputs = self._modify_inputs_for_ip_adapter_test(self.get_dummy_inputs(torch_device))
+        inputs["ip_adapter_image_embeds"] = [self._get_dummy_image_embeds(cross_attention_dim)]
+        inputs["guidance_scale"] = 7.5
+        out_cfg = pipe(**inputs)[0]
+
+        assert out_cfg.shape == out_no_cfg.shape
+
 
 class PipelineLatentTesterMixin:
     """