diff --git a/src/diffusers/schedulers/scheduling_ddim.py b/src/diffusers/schedulers/scheduling_ddim.py
index aab5255abc..5881874ab5 100644
--- a/src/diffusers/schedulers/scheduling_ddim.py
+++ b/src/diffusers/schedulers/scheduling_ddim.py
@@ -276,13 +276,13 @@ class DDIMScheduler(SchedulerMixin, ConfigMixin):
         https://arxiv.org/abs/2205.11487
         """
         dtype = sample.dtype
-        batch_size, channels, height, width = sample.shape
+        batch_size, channels, *remaining_dims = sample.shape
 
         if dtype not in (torch.float32, torch.float64):
             sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half
 
         # Flatten sample for doing quantile calculation along each image
-        sample = sample.reshape(batch_size, channels * height * width)
+        sample = sample.reshape(batch_size, channels * np.prod(remaining_dims))
 
         abs_sample = sample.abs()  # "a certain percentile absolute pixel value"
 
@@ -290,11 +290,10 @@ class DDIMScheduler(SchedulerMixin, ConfigMixin):
         s = torch.clamp(
             s, min=1, max=self.config.sample_max_value
         )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
-
         s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
         sample = torch.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"
 
-        sample = sample.reshape(batch_size, channels, height, width)
+        sample = sample.reshape(batch_size, channels, *remaining_dims)
         sample = sample.to(dtype)
 
         return sample
diff --git a/src/diffusers/schedulers/scheduling_ddim_parallel.py b/src/diffusers/schedulers/scheduling_ddim_parallel.py
index f90a271dfc..8d698f6732 100644
--- a/src/diffusers/schedulers/scheduling_ddim_parallel.py
+++ b/src/diffusers/schedulers/scheduling_ddim_parallel.py
@@ -298,13 +298,13 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
         https://arxiv.org/abs/2205.11487
         """
         dtype = sample.dtype
-        batch_size, channels, height, width = sample.shape
+        batch_size, channels, *remaining_dims = sample.shape
 
         if dtype not in (torch.float32, torch.float64):
             sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half
 
         # Flatten sample for doing quantile calculation along each image
-        sample = sample.reshape(batch_size, channels * height * width)
+        sample = sample.reshape(batch_size, channels * np.prod(remaining_dims))
 
         abs_sample = sample.abs()  # "a certain percentile absolute pixel value"
 
@@ -312,11 +312,10 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
         s = torch.clamp(
             s, min=1, max=self.config.sample_max_value
         )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
-
         s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
         sample = torch.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"
 
-        sample = sample.reshape(batch_size, channels, height, width)
+        sample = sample.reshape(batch_size, channels, *remaining_dims)
         sample = sample.to(dtype)
 
         return sample
diff --git a/src/diffusers/schedulers/scheduling_ddpm.py b/src/diffusers/schedulers/scheduling_ddpm.py
index 86f7e84ff0..bbc390a5d9 100644
--- a/src/diffusers/schedulers/scheduling_ddpm.py
+++ b/src/diffusers/schedulers/scheduling_ddpm.py
@@ -330,13 +330,13 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
         https://arxiv.org/abs/2205.11487
         """
         dtype = sample.dtype
-        batch_size, channels, height, width = sample.shape
+        batch_size, channels, *remaining_dims = sample.shape
 
         if dtype not in (torch.float32, torch.float64):
             sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half
 
         # Flatten sample for doing quantile calculation along each image
-        sample = sample.reshape(batch_size, channels * height * width)
+        sample = sample.reshape(batch_size, channels * np.prod(remaining_dims))
 
         abs_sample = sample.abs()  # "a certain percentile absolute pixel value"
 
@@ -344,11 +344,10 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
         s = torch.clamp(
             s, min=1, max=self.config.sample_max_value
         )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
-
         s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
         sample = torch.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"
 
-        sample = sample.reshape(batch_size, channels, height, width)
+        sample = sample.reshape(batch_size, channels, *remaining_dims)
         sample = sample.to(dtype)
 
         return sample
diff --git a/src/diffusers/schedulers/scheduling_ddpm_parallel.py b/src/diffusers/schedulers/scheduling_ddpm_parallel.py
index 2f3bdd39aa..ca17ca5499 100644
--- a/src/diffusers/schedulers/scheduling_ddpm_parallel.py
+++ b/src/diffusers/schedulers/scheduling_ddpm_parallel.py
@@ -344,13 +344,13 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         https://arxiv.org/abs/2205.11487
         """
         dtype = sample.dtype
-        batch_size, channels, height, width = sample.shape
+        batch_size, channels, *remaining_dims = sample.shape
 
         if dtype not in (torch.float32, torch.float64):
             sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half
 
         # Flatten sample for doing quantile calculation along each image
-        sample = sample.reshape(batch_size, channels * height * width)
+        sample = sample.reshape(batch_size, channels * np.prod(remaining_dims))
 
         abs_sample = sample.abs()  # "a certain percentile absolute pixel value"
 
@@ -358,11 +358,10 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
         s = torch.clamp(
             s, min=1, max=self.config.sample_max_value
         )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
-
         s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
         sample = torch.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"
 
-        sample = sample.reshape(batch_size, channels, height, width)
+        sample = sample.reshape(batch_size, channels, *remaining_dims)
         sample = sample.to(dtype)
 
         return sample
diff --git a/src/diffusers/schedulers/scheduling_deis_multistep.py b/src/diffusers/schedulers/scheduling_deis_multistep.py
index af9b0381dc..a6afe744bd 100644
--- a/src/diffusers/schedulers/scheduling_deis_multistep.py
+++ b/src/diffusers/schedulers/scheduling_deis_multistep.py
@@ -268,13 +268,13 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
         https://arxiv.org/abs/2205.11487
         """
         dtype = sample.dtype
-        batch_size, channels, height, width = sample.shape
+        batch_size, channels, *remaining_dims = sample.shape
 
         if dtype not in (torch.float32, torch.float64):
             sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half
 
         # Flatten sample for doing quantile calculation along each image
-        sample = sample.reshape(batch_size, channels * height * width)
+        sample = sample.reshape(batch_size, channels * np.prod(remaining_dims))
 
         abs_sample = sample.abs()  # "a certain percentile absolute pixel value"
 
@@ -282,11 +282,10 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
         s = torch.clamp(
             s, min=1, max=self.config.sample_max_value
         )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
-
         s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
         sample = torch.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"
 
-        sample = sample.reshape(batch_size, channels, height, width)
+        sample = sample.reshape(batch_size, channels, *remaining_dims)
         sample = sample.to(dtype)
 
         return sample
diff --git a/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py b/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py
index 726ad138ad..6b1a43630f 100644
--- a/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py
+++ b/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py
@@ -288,13 +288,13 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
         https://arxiv.org/abs/2205.11487
         """
         dtype = sample.dtype
-        batch_size, channels, height, width = sample.shape
+        batch_size, channels, *remaining_dims = sample.shape
 
         if dtype not in (torch.float32, torch.float64):
             sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half
 
         # Flatten sample for doing quantile calculation along each image
-        sample = sample.reshape(batch_size, channels * height * width)
+        sample = sample.reshape(batch_size, channels * np.prod(remaining_dims))
 
         abs_sample = sample.abs()  # "a certain percentile absolute pixel value"
 
@@ -302,11 +302,10 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
         s = torch.clamp(
             s, min=1, max=self.config.sample_max_value
         )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
-
         s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
         sample = torch.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"
 
-        sample = sample.reshape(batch_size, channels, height, width)
+        sample = sample.reshape(batch_size, channels, *remaining_dims)
         sample = sample.to(dtype)
 
         return sample
diff --git a/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py b/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py
index c0b286a370..fa8f362bd3 100644
--- a/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py
+++ b/src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py
@@ -298,13 +298,13 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
         https://arxiv.org/abs/2205.11487
         """
         dtype = sample.dtype
-        batch_size, channels, height, width = sample.shape
+        batch_size, channels, *remaining_dims = sample.shape
 
         if dtype not in (torch.float32, torch.float64):
             sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half
 
         # Flatten sample for doing quantile calculation along each image
-        sample = sample.reshape(batch_size, channels * height * width)
+        sample = sample.reshape(batch_size, channels * np.prod(remaining_dims))
 
         abs_sample = sample.abs()  # "a certain percentile absolute pixel value"
 
@@ -312,11 +312,10 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
         s = torch.clamp(
             s, min=1, max=self.config.sample_max_value
         )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
-
         s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
         sample = torch.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"
 
-        sample = sample.reshape(batch_size, channels, height, width)
+        sample = sample.reshape(batch_size, channels, *remaining_dims)
         sample = sample.to(dtype)
 
         return sample
diff --git a/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py b/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py
index 6744a68b4c..bb7dc21e6f 100644
--- a/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py
+++ b/src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py
@@ -302,13 +302,13 @@ class DPMSolverSinglestepScheduler(SchedulerMixin, ConfigMixin):
         https://arxiv.org/abs/2205.11487
         """
         dtype = sample.dtype
-        batch_size, channels, height, width = sample.shape
+        batch_size, channels, *remaining_dims = sample.shape
 
         if dtype not in (torch.float32, torch.float64):
             sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half
 
         # Flatten sample for doing quantile calculation along each image
-        sample = sample.reshape(batch_size, channels * height * width)
+        sample = sample.reshape(batch_size, channels * np.prod(remaining_dims))
 
         abs_sample = sample.abs()  # "a certain percentile absolute pixel value"
 
@@ -316,11 +316,10 @@ class DPMSolverSinglestepScheduler(SchedulerMixin, ConfigMixin):
         s = torch.clamp(
             s, min=1, max=self.config.sample_max_value
         )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
-
         s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
         sample = torch.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"
 
-        sample = sample.reshape(batch_size, channels, height, width)
+        sample = sample.reshape(batch_size, channels, *remaining_dims)
         sample = sample.to(dtype)
 
         return sample
diff --git a/src/diffusers/schedulers/scheduling_unipc_multistep.py b/src/diffusers/schedulers/scheduling_unipc_multistep.py
index 18d95fe514..741b03b6d3 100644
--- a/src/diffusers/schedulers/scheduling_unipc_multistep.py
+++ b/src/diffusers/schedulers/scheduling_unipc_multistep.py
@@ -282,13 +282,13 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
         https://arxiv.org/abs/2205.11487
         """
         dtype = sample.dtype
-        batch_size, channels, height, width = sample.shape
+        batch_size, channels, *remaining_dims = sample.shape
 
         if dtype not in (torch.float32, torch.float64):
             sample = sample.float()  # upcast for quantile calculation, and clamp not implemented for cpu half
 
         # Flatten sample for doing quantile calculation along each image
-        sample = sample.reshape(batch_size, channels * height * width)
+        sample = sample.reshape(batch_size, channels * np.prod(remaining_dims))
 
         abs_sample = sample.abs()  # "a certain percentile absolute pixel value"
 
@@ -296,11 +296,10 @@ class UniPCMultistepScheduler(SchedulerMixin, ConfigMixin):
         s = torch.clamp(
             s, min=1, max=self.config.sample_max_value
         )  # When clamped to min=1, equivalent to standard clipping to [-1, 1]
-
         s = s.unsqueeze(1)  # (batch_size, 1) because clamp will broadcast along dim=0
         sample = torch.clamp(sample, -s, s) / s  # "we threshold xt0 to the range [-s, s] and then divide by s"
 
-        sample = sample.reshape(batch_size, channels, height, width)
+        sample = sample.reshape(batch_size, channels, *remaining_dims)
         sample = sample.to(dtype)
 
         return sample