diff --git a/src/diffusers/pipelines/audioldm2/pipeline_audioldm2.py b/src/diffusers/pipelines/audioldm2/pipeline_audioldm2.py
index d5674593b4..8e82e1c5b1 100644
--- a/src/diffusers/pipelines/audioldm2/pipeline_audioldm2.py
+++ b/src/diffusers/pipelines/audioldm2/pipeline_audioldm2.py
@@ -223,7 +223,7 @@ class AudioLDM2Pipeline(DiffusionPipeline):
         )
         self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_utils.SDMixin.enable_vae_slicing
+    # Copied from diffusers.pipelines.pipeline_utils.StableDiffusionMixin.enable_vae_slicing
     def enable_vae_slicing(self):
         r"""
         Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
@@ -237,7 +237,7 @@ class AudioLDM2Pipeline(DiffusionPipeline):
         )
         self.vae.enable_slicing()
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_utils.SDMixin.disable_vae_slicing
+    # Copied from diffusers.pipelines.pipeline_utils.StableDiffusionMixin.disable_vae_slicing
     def disable_vae_slicing(self):
         r"""
         Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
diff --git a/src/diffusers/pipelines/stable_audio/pipeline_stable_audio.py b/src/diffusers/pipelines/stable_audio/pipeline_stable_audio.py
index 9ad4568e37..e3591883ac 100644
--- a/src/diffusers/pipelines/stable_audio/pipeline_stable_audio.py
+++ b/src/diffusers/pipelines/stable_audio/pipeline_stable_audio.py
@@ -124,7 +124,7 @@ class StableAudioPipeline(DiffusionPipeline):
         )
         self.rotary_embed_dim = self.transformer.config.attention_head_dim // 2
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_utils.SDMixin.enable_vae_slicing
+    # Copied from diffusers.pipelines.pipeline_utils.StableDiffusionMixin.enable_vae_slicing
     def enable_vae_slicing(self):
         r"""
         Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
@@ -138,7 +138,7 @@ class StableAudioPipeline(DiffusionPipeline):
         )
         self.vae.enable_slicing()
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_utils.SDMixin.disable_vae_slicing
+    # Copied from diffusers.pipelines.pipeline_utils.StableDiffusionMixin.disable_vae_slicing
     def disable_vae_slicing(self):
         r"""
         Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
diff --git a/src/diffusers/pipelines/unidiffuser/pipeline_unidiffuser.py b/src/diffusers/pipelines/unidiffuser/pipeline_unidiffuser.py
index 430de48c91..59d9275062 100644
--- a/src/diffusers/pipelines/unidiffuser/pipeline_unidiffuser.py
+++ b/src/diffusers/pipelines/unidiffuser/pipeline_unidiffuser.py
@@ -226,7 +226,7 @@ class UniDiffuserPipeline(DeprecatedPipelineMixin, DiffusionPipeline):
 
         return mode
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_utils.SDMixin.enable_vae_slicing
+    # Copied from diffusers.pipelines.pipeline_utils.StableDiffusionMixin.enable_vae_slicing
     def enable_vae_slicing(self):
         r"""
         Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to
@@ -240,7 +240,7 @@ class UniDiffuserPipeline(DeprecatedPipelineMixin, DiffusionPipeline):
         )
         self.vae.enable_slicing()
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_utils.SDMixin.disable_vae_slicing
+    # Copied from diffusers.pipelines.pipeline_utils.StableDiffusionMixin.disable_vae_slicing
     def disable_vae_slicing(self):
         r"""
         Disable sliced VAE decoding. If `enable_vae_slicing` was previously enabled, this method will go back to
@@ -254,7 +254,7 @@ class UniDiffuserPipeline(DeprecatedPipelineMixin, DiffusionPipeline):
         )
         self.vae.disable_slicing()
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_utils.SDMixin.enable_vae_tiling
+    # Copied from diffusers.pipelines.pipeline_utils.StableDiffusionMixin.enable_vae_tiling
     def enable_vae_tiling(self):
         r"""
         Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to
@@ -269,7 +269,7 @@ class UniDiffuserPipeline(DeprecatedPipelineMixin, DiffusionPipeline):
         )
         self.vae.enable_tiling()
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_utils.SDMixin.disable_vae_tiling
+    # Copied from diffusers.pipelines.pipeline_utils.StableDiffusionMixin.disable_vae_tiling
     def disable_vae_tiling(self):
         r"""
         Disable tiled VAE decoding. If `enable_vae_tiling` was previously enabled, this method will go back to