diff --git a/examples/community/llm_grounded_diffusion.py b/examples/community/llm_grounded_diffusion.py
index 14f4deabcea7..d953d435e870 100644
--- a/examples/community/llm_grounded_diffusion.py
+++ b/examples/community/llm_grounded_diffusion.py
@@ -30,7 +30,7 @@
 from diffusers.configuration_utils import FrozenDict
 from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
 from diffusers.loaders import FromSingleFileMixin, IPAdapterMixin, LoraLoaderMixin, TextualInversionLoaderMixin
-from diffusers.models import AutoencoderKL, UNet2DConditionModel
+from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
 from diffusers.models.attention import Attention, GatedSelfAttentionDense
 from diffusers.models.attention_processor import AttnProcessor2_0
 from diffusers.models.lora import adjust_lora_scale_text_encoder
@@ -911,7 +911,10 @@ def __call__(
             prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
 
         if ip_adapter_image is not None:
-            image_embeds, negative_image_embeds = self.encode_image(ip_adapter_image, device, num_images_per_prompt)
+            output_hidden_state = False if isinstance(self.unet.encoder_hid_proj, ImageProjection) else True
+            image_embeds, negative_image_embeds = self.encode_image(
+                ip_adapter_image, device, num_images_per_prompt, output_hidden_state
+            )
             if self.do_classifier_free_guidance:
                 image_embeds = torch.cat([negative_image_embeds, image_embeds])
 
@@ -1431,18 +1434,29 @@ def encode_prompt(
         return prompt_embeds, negative_prompt_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
-    def encode_image(self, image, device, num_images_per_prompt):
+    def encode_image(self, image, device, num_images_per_prompt, output_hidden_states=None):
         dtype = next(self.image_encoder.parameters()).dtype
 
         if not isinstance(image, torch.Tensor):
             image = self.feature_extractor(image, return_tensors="pt").pixel_values
 
         image = image.to(device=device, dtype=dtype)
-        image_embeds = self.image_encoder(image).image_embeds
-        image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
+        if output_hidden_states:
+            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True).hidden_states[-2]
+            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
+            uncond_image_enc_hidden_states = self.image_encoder(
+                torch.zeros_like(image), output_hidden_states=True
+            ).hidden_states[-2]
+            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
+                num_images_per_prompt, dim=0
+            )
+            return image_enc_hidden_states, uncond_image_enc_hidden_states
+        else:
+            image_embeds = self.image_encoder(image).image_embeds
+            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
+            uncond_image_embeds = torch.zeros_like(image_embeds)
 
-        uncond_image_embeds = torch.zeros_like(image_embeds)
-        return image_embeds, uncond_image_embeds
+            return image_embeds, uncond_image_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.run_safety_checker
     def run_safety_checker(self, image, device, dtype):
diff --git a/examples/community/pipeline_animatediff_controlnet.py b/examples/community/pipeline_animatediff_controlnet.py
index 785f1ee55ec2..5f2c2d2a4a96 100644
--- a/examples/community/pipeline_animatediff_controlnet.py
+++ b/examples/community/pipeline_animatediff_controlnet.py
@@ -24,7 +24,7 @@
 
 from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
 from diffusers.loaders import IPAdapterMixin, LoraLoaderMixin, TextualInversionLoaderMixin
-from diffusers.models import AutoencoderKL, ControlNetModel, UNet2DConditionModel, UNetMotionModel
+from diffusers.models import AutoencoderKL, ControlNetModel, ImageProjection, UNet2DConditionModel, UNetMotionModel
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.models.unet_motion_model import MotionAdapter
 from diffusers.pipelines.controlnet.multicontrolnet import MultiControlNetModel
@@ -366,18 +366,29 @@ def encode_prompt(
         return prompt_embeds, negative_prompt_embeds
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.encode_image
-    def encode_image(self, image, device, num_images_per_prompt):
+    def encode_image(self, image, device, num_images_per_prompt, output_hidden_states=None):
         dtype = next(self.image_encoder.parameters()).dtype
 
         if not isinstance(image, torch.Tensor):
             image = self.feature_extractor(image, return_tensors="pt").pixel_values
 
         image = image.to(device=device, dtype=dtype)
-        image_embeds = self.image_encoder(image).image_embeds
-        image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
+        if output_hidden_states:
+            image_enc_hidden_states = self.image_encoder(image, output_hidden_states=True).hidden_states[-2]
+            image_enc_hidden_states = image_enc_hidden_states.repeat_interleave(num_images_per_prompt, dim=0)
+            uncond_image_enc_hidden_states = self.image_encoder(
+                torch.zeros_like(image), output_hidden_states=True
+            ).hidden_states[-2]
+            uncond_image_enc_hidden_states = uncond_image_enc_hidden_states.repeat_interleave(
+                num_images_per_prompt, dim=0
+            )
+            return image_enc_hidden_states, uncond_image_enc_hidden_states
+        else:
+            image_embeds = self.image_encoder(image).image_embeds
+            image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
+            uncond_image_embeds = torch.zeros_like(image_embeds)
 
-        uncond_image_embeds = torch.zeros_like(image_embeds)
-        return image_embeds, uncond_image_embeds
+            return image_embeds, uncond_image_embeds
 
     # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
     def decode_latents(self, latents):
@@ -970,7 +981,10 @@ def __call__(
             prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
 
         if ip_adapter_image is not None:
-            image_embeds, negative_image_embeds = self.encode_image(ip_adapter_image, device, num_videos_per_prompt)
+            output_hidden_state = False if isinstance(self.unet.encoder_hid_proj, ImageProjection) else True
+            image_embeds, negative_image_embeds = self.encode_image(
+                ip_adapter_image, device, num_videos_per_prompt, output_hidden_state
+            )
             if self.do_classifier_free_guidance:
                 image_embeds = torch.cat([negative_image_embeds, image_embeds])