diffusers 0.27.1__py3-none-any.whl → 0.28.0__py3-none-any.whl

diffusers/schedulers/scheduling_heun_discrete.py

@@ -57,7 +57,7 @@ def betas_for_alpha_bar(
             return math.exp(t * -12.0)
 
     else:
-        raise ValueError(f"Unsupported alpha_tranform_type: {alpha_transform_type}")
+        raise ValueError(f"Unsupported alpha_transform_type: {alpha_transform_type}")
 
     betas = []
     for i in range(num_diffusion_timesteps):
@@ -135,7 +135,7 @@ class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
         elif beta_schedule == "exp":
             self.betas = betas_for_alpha_bar(num_train_timesteps, alpha_transform_type="exp")
         else:
-            raise NotImplementedError(f"{beta_schedule} does is not implemented for {self.__class__}")
+            raise NotImplementedError(f"{beta_schedule} is not implemented for {self.__class__}")
 
         self.alphas = 1.0 - self.betas
         self.alphas_cumprod = torch.cumprod(self.alphas, dim=0)
@@ -174,7 +174,7 @@ class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
     @property
     def step_index(self):
         """
-        The index counter for current timestep. It will increae 1 after each scheduler step.
+        The index counter for current timestep. It will increase 1 after each scheduler step.
         """
         return self._step_index
 
@@ -198,21 +198,21 @@ class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
 
     def scale_model_input(
         self,
-        sample: torch.FloatTensor,
-        timestep: Union[float, torch.FloatTensor],
-    ) -> torch.FloatTensor:
+        sample: torch.Tensor,
+        timestep: Union[float, torch.Tensor],
+    ) -> torch.Tensor:
         """
         Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
         current timestep.
 
         Args:
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 The input sample.
             timestep (`int`, *optional*):
                 The current timestep in the diffusion chain.
 
         Returns:
-            `torch.FloatTensor`:
+            `torch.Tensor`:
                 A scaled input sample.
         """
         if self.step_index is None:
@@ -224,9 +224,10 @@ class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
 
     def set_timesteps(
         self,
-        num_inference_steps: int,
+        num_inference_steps: Optional[int] = None,
         device: Union[str, torch.device] = None,
         num_train_timesteps: Optional[int] = None,
+        timesteps: Optional[List[int]] = None,
     ):
         """
         Sets the discrete timesteps used for the diffusion chain (to be run before inference).
@@ -236,30 +237,47 @@ class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
                 The number of diffusion steps used when generating samples with a pre-trained model.
             device (`str` or `torch.device`, *optional*):
                 The device to which the timesteps should be moved to. If `None`, the timesteps are not moved.
+            num_train_timesteps (`int`, *optional*):
+                The number of diffusion steps used when training the model. If `None`, the default
+                `num_train_timesteps` attribute is used.
+            timesteps (`List[int]`, *optional*):
+                Custom timesteps used to support arbitrary spacing between timesteps. If `None`, timesteps will be
+                generated based on the `timestep_spacing` attribute. If `timesteps` is passed, `num_inference_steps`
+                must be `None`, and `timestep_spacing` attribute will be ignored.
         """
+        if num_inference_steps is None and timesteps is None:
+            raise ValueError("Must pass exactly one of `num_inference_steps` or `custom_timesteps`.")
+        if num_inference_steps is not None and timesteps is not None:
+            raise ValueError("Can only pass one of `num_inference_steps` or `custom_timesteps`.")
+        if timesteps is not None and self.config.use_karras_sigmas:
+            raise ValueError("Cannot use `timesteps` with `config.use_karras_sigmas = True`")
+
+        num_inference_steps = num_inference_steps or len(timesteps)
         self.num_inference_steps = num_inference_steps
-
         num_train_timesteps = num_train_timesteps or self.config.num_train_timesteps
 
-        # "linspace", "leading", "trailing" corresponds to annotation of Table 2. of https://arxiv.org/abs/2305.08891
-        if self.config.timestep_spacing == "linspace":
-            timesteps = np.linspace(0, num_train_timesteps - 1, num_inference_steps, dtype=np.float32)[::-1].copy()
-        elif self.config.timestep_spacing == "leading":
-            step_ratio = num_train_timesteps // self.num_inference_steps
-            # creates integer timesteps by multiplying by ratio
-            # casting to int to avoid issues when num_inference_step is power of 3
-            timesteps = (np.arange(0, num_inference_steps) * step_ratio).round()[::-1].copy().astype(np.float32)
-            timesteps += self.config.steps_offset
-        elif self.config.timestep_spacing == "trailing":
-            step_ratio = num_train_timesteps / self.num_inference_steps
-            # creates integer timesteps by multiplying by ratio
-            # casting to int to avoid issues when num_inference_step is power of 3
-            timesteps = (np.arange(num_train_timesteps, 0, -step_ratio)).round().copy().astype(np.float32)
-            timesteps -= 1
+        if timesteps is not None:
+            timesteps = np.array(timesteps, dtype=np.float32)
         else:
-            raise ValueError(
-                f"{self.config.timestep_spacing} is not supported. Please make sure to choose one of 'linspace', 'leading' or 'trailing'."
-            )
+            # "linspace", "leading", "trailing" corresponds to annotation of Table 2. of https://arxiv.org/abs/2305.08891
+            if self.config.timestep_spacing == "linspace":
+                timesteps = np.linspace(0, num_train_timesteps - 1, num_inference_steps, dtype=np.float32)[::-1].copy()
+            elif self.config.timestep_spacing == "leading":
+                step_ratio = num_train_timesteps // self.num_inference_steps
+                # creates integer timesteps by multiplying by ratio
+                # casting to int to avoid issues when num_inference_step is power of 3
+                timesteps = (np.arange(0, num_inference_steps) * step_ratio).round()[::-1].copy().astype(np.float32)
+                timesteps += self.config.steps_offset
+            elif self.config.timestep_spacing == "trailing":
+                step_ratio = num_train_timesteps / self.num_inference_steps
+                # creates integer timesteps by multiplying by ratio
+                # casting to int to avoid issues when num_inference_step is power of 3
+                timesteps = (np.arange(num_train_timesteps, 0, -step_ratio)).round().copy().astype(np.float32)
+                timesteps -= 1
+            else:
+                raise ValueError(
+                    f"{self.config.timestep_spacing} is not supported. Please make sure to choose one of 'linspace', 'leading' or 'trailing'."
+                )
 
         sigmas = np.array(((1 - self.alphas_cumprod) / self.alphas_cumprod) ** 0.5)
         log_sigmas = np.log(sigmas)
@@ -311,7 +329,7 @@ class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
         return t
 
     # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._convert_to_karras
-    def _convert_to_karras(self, in_sigmas: torch.FloatTensor, num_inference_steps) -> torch.FloatTensor:
+    def _convert_to_karras(self, in_sigmas: torch.Tensor, num_inference_steps) -> torch.Tensor:
         """Constructs the noise schedule of Karras et al. (2022)."""
 
         # Hack to make sure that other schedulers which copy this function don't break
@@ -351,9 +369,9 @@ class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
 
     def step(
         self,
-        model_output: Union[torch.FloatTensor, np.ndarray],
-        timestep: Union[float, torch.FloatTensor],
-        sample: Union[torch.FloatTensor, np.ndarray],
+        model_output: Union[torch.Tensor, np.ndarray],
+        timestep: Union[float, torch.Tensor],
+        sample: Union[torch.Tensor, np.ndarray],
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
@@ -361,11 +379,11 @@ class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
         process from the learned model outputs (most often the predicted noise).
 
         Args:
-            model_output (`torch.FloatTensor`):
+            model_output (`torch.Tensor`):
                 The direct output from learned diffusion model.
             timestep (`float`):
                 The current discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 A current instance of a sample created by the diffusion process.
             return_dict (`bool`):
                 Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or tuple.
@@ -451,10 +469,10 @@ class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
     # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler.add_noise
     def add_noise(
         self,
-        original_samples: torch.FloatTensor,
-        noise: torch.FloatTensor,
-        timesteps: torch.FloatTensor,
-    ) -> torch.FloatTensor:
+        original_samples: torch.Tensor,
+        noise: torch.Tensor,
+        timesteps: torch.Tensor,
+    ) -> torch.Tensor:
         # Make sure sigmas and timesteps have the same device and dtype as original_samples
         sigmas = self.sigmas.to(device=original_samples.device, dtype=original_samples.dtype)
         if original_samples.device.type == "mps" and torch.is_floating_point(timesteps):
@@ -468,7 +486,11 @@ class HeunDiscreteScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called before first denoising step to create initial latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

diffusers/schedulers/scheduling_ipndm.py

@@ -61,7 +61,7 @@ class IPNDMScheduler(SchedulerMixin, ConfigMixin):
     @property
     def step_index(self):
         """
-        The index counter for current timestep. It will increae 1 after each scheduler step.
+        The index counter for current timestep. It will increase 1 after each scheduler step.
         """
         return self._step_index
 
@@ -137,9 +137,9 @@ class IPNDMScheduler(SchedulerMixin, ConfigMixin):
 
     def step(
         self,
-        model_output: torch.FloatTensor,
+        model_output: torch.Tensor,
         timestep: int,
-        sample: torch.FloatTensor,
+        sample: torch.Tensor,
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
@@ -147,11 +147,11 @@ class IPNDMScheduler(SchedulerMixin, ConfigMixin):
         the linear multistep method. It performs one forward pass multiple times to approximate the solution.
 
         Args:
-            model_output (`torch.FloatTensor`):
+            model_output (`torch.Tensor`):
                 The direct output from learned diffusion model.
             timestep (`int`):
                 The current discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 A current instance of a sample created by the diffusion process.
             return_dict (`bool`):
                 Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or tuple.
@@ -193,17 +193,17 @@ class IPNDMScheduler(SchedulerMixin, ConfigMixin):
 
         return SchedulerOutput(prev_sample=prev_sample)
 
-    def scale_model_input(self, sample: torch.FloatTensor, *args, **kwargs) -> torch.FloatTensor:
+    def scale_model_input(self, sample: torch.Tensor, *args, **kwargs) -> torch.Tensor:
         """
         Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
         current timestep.
 
         Args:
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 The input sample.
 
         Returns:
-            `torch.FloatTensor`:
+            `torch.Tensor`:
                 A scaled input sample.
         """
         return sample

diffusers/schedulers/scheduling_k_dpm_2_ancestral_discrete.py

@@ -58,7 +58,7 @@ def betas_for_alpha_bar(
             return math.exp(t * -12.0)
 
     else:
-        raise ValueError(f"Unsupported alpha_tranform_type: {alpha_transform_type}")
+        raise ValueError(f"Unsupported alpha_transform_type: {alpha_transform_type}")
 
     betas = []
     for i in range(num_diffusion_timesteps):
@@ -129,7 +129,7 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
             # Glide cosine schedule
             self.betas = betas_for_alpha_bar(num_train_timesteps)
         else:
-            raise NotImplementedError(f"{beta_schedule} does is not implemented for {self.__class__}")
+            raise NotImplementedError(f"{beta_schedule} is not implemented for {self.__class__}")
 
         self.alphas = 1.0 - self.betas
         self.alphas_cumprod = torch.cumprod(self.alphas, dim=0)
@@ -151,7 +151,7 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
     @property
     def step_index(self):
         """
-        The index counter for current timestep. It will increae 1 after each scheduler step.
+        The index counter for current timestep. It will increase 1 after each scheduler step.
         """
         return self._step_index
 
@@ -175,21 +175,21 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
 
     def scale_model_input(
         self,
-        sample: torch.FloatTensor,
-        timestep: Union[float, torch.FloatTensor],
-    ) -> torch.FloatTensor:
+        sample: torch.Tensor,
+        timestep: Union[float, torch.Tensor],
+    ) -> torch.Tensor:
         """
         Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
         current timestep.
 
         Args:
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 The input sample.
             timestep (`int`, *optional*):
                 The current timestep in the diffusion chain.
 
         Returns:
-            `torch.FloatTensor`:
+            `torch.Tensor`:
                 A scaled input sample.
         """
         if self.step_index is None:
@@ -321,7 +321,7 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
         return t
 
     # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._convert_to_karras
-    def _convert_to_karras(self, in_sigmas: torch.FloatTensor, num_inference_steps) -> torch.FloatTensor:
+    def _convert_to_karras(self, in_sigmas: torch.Tensor, num_inference_steps) -> torch.Tensor:
         """Constructs the noise schedule of Karras et al. (2022)."""
 
         # Hack to make sure that other schedulers which copy this function don't break
@@ -376,9 +376,9 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
 
     def step(
         self,
-        model_output: Union[torch.FloatTensor, np.ndarray],
-        timestep: Union[float, torch.FloatTensor],
-        sample: Union[torch.FloatTensor, np.ndarray],
+        model_output: Union[torch.Tensor, np.ndarray],
+        timestep: Union[float, torch.Tensor],
+        sample: Union[torch.Tensor, np.ndarray],
         generator: Optional[torch.Generator] = None,
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
@@ -387,11 +387,11 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
         process from the learned model outputs (most often the predicted noise).
 
         Args:
-            model_output (`torch.FloatTensor`):
+            model_output (`torch.Tensor`):
                 The direct output from learned diffusion model.
             timestep (`float`):
                 The current discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 A current instance of a sample created by the diffusion process.
             generator (`torch.Generator`, *optional*):
                 A random number generator.
@@ -477,10 +477,10 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
     # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler.add_noise
     def add_noise(
         self,
-        original_samples: torch.FloatTensor,
-        noise: torch.FloatTensor,
-        timesteps: torch.FloatTensor,
-    ) -> torch.FloatTensor:
+        original_samples: torch.Tensor,
+        noise: torch.Tensor,
+        timesteps: torch.Tensor,
+    ) -> torch.Tensor:
         # Make sure sigmas and timesteps have the same device and dtype as original_samples
         sigmas = self.sigmas.to(device=original_samples.device, dtype=original_samples.dtype)
         if original_samples.device.type == "mps" and torch.is_floating_point(timesteps):
@@ -494,7 +494,11 @@ class KDPM2AncestralDiscreteScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called before first denoising step to create initial latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

diffusers/schedulers/scheduling_k_dpm_2_discrete.py

@@ -57,7 +57,7 @@ def betas_for_alpha_bar(
             return math.exp(t * -12.0)
 
     else:
-        raise ValueError(f"Unsupported alpha_tranform_type: {alpha_transform_type}")
+        raise ValueError(f"Unsupported alpha_transform_type: {alpha_transform_type}")
 
     betas = []
     for i in range(num_diffusion_timesteps):
@@ -128,7 +128,7 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
             # Glide cosine schedule
             self.betas = betas_for_alpha_bar(num_train_timesteps)
         else:
-            raise NotImplementedError(f"{beta_schedule} does is not implemented for {self.__class__}")
+            raise NotImplementedError(f"{beta_schedule} is not implemented for {self.__class__}")
 
         self.alphas = 1.0 - self.betas
         self.alphas_cumprod = torch.cumprod(self.alphas, dim=0)
@@ -151,7 +151,7 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
     @property
     def step_index(self):
         """
-        The index counter for current timestep. It will increae 1 after each scheduler step.
+        The index counter for current timestep. It will increase 1 after each scheduler step.
         """
         return self._step_index
 
@@ -175,21 +175,21 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
 
     def scale_model_input(
         self,
-        sample: torch.FloatTensor,
-        timestep: Union[float, torch.FloatTensor],
-    ) -> torch.FloatTensor:
+        sample: torch.Tensor,
+        timestep: Union[float, torch.Tensor],
+    ) -> torch.Tensor:
         """
         Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
         current timestep.
 
         Args:
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 The input sample.
             timestep (`int`, *optional*):
                 The current timestep in the diffusion chain.
 
         Returns:
-            `torch.FloatTensor`:
+            `torch.Tensor`:
                 A scaled input sample.
         """
         if self.step_index is None:
@@ -334,7 +334,7 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
         return t
 
     # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._convert_to_karras
-    def _convert_to_karras(self, in_sigmas: torch.FloatTensor, num_inference_steps) -> torch.FloatTensor:
+    def _convert_to_karras(self, in_sigmas: torch.Tensor, num_inference_steps) -> torch.Tensor:
         """Constructs the noise schedule of Karras et al. (2022)."""
 
         # Hack to make sure that other schedulers which copy this function don't break
@@ -361,9 +361,9 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
 
     def step(
         self,
-        model_output: Union[torch.FloatTensor, np.ndarray],
-        timestep: Union[float, torch.FloatTensor],
-        sample: Union[torch.FloatTensor, np.ndarray],
+        model_output: Union[torch.Tensor, np.ndarray],
+        timestep: Union[float, torch.Tensor],
+        sample: Union[torch.Tensor, np.ndarray],
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
@@ -371,11 +371,11 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
         process from the learned model outputs (most often the predicted noise).
 
         Args:
-            model_output (`torch.FloatTensor`):
+            model_output (`torch.Tensor`):
                 The direct output from learned diffusion model.
             timestep (`float`):
                 The current discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 A current instance of a sample created by the diffusion process.
             return_dict (`bool`):
                 Whether or not to return a [`~schedulers.scheduling_utils.SchedulerOutput`] or tuple.
@@ -452,10 +452,10 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
     # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler.add_noise
     def add_noise(
         self,
-        original_samples: torch.FloatTensor,
-        noise: torch.FloatTensor,
-        timesteps: torch.FloatTensor,
-    ) -> torch.FloatTensor:
+        original_samples: torch.Tensor,
+        noise: torch.Tensor,
+        timesteps: torch.Tensor,
+    ) -> torch.Tensor:
         # Make sure sigmas and timesteps have the same device and dtype as original_samples
         sigmas = self.sigmas.to(device=original_samples.device, dtype=original_samples.dtype)
         if original_samples.device.type == "mps" and torch.is_floating_point(timesteps):
@@ -469,7 +469,11 @@ class KDPM2DiscreteScheduler(SchedulerMixin, ConfigMixin):
         # self.begin_index is None when scheduler is used for training, or pipeline does not implement set_begin_index
         if self.begin_index is None:
             step_indices = [self.index_for_timestep(t, schedule_timesteps) for t in timesteps]
+        elif self.step_index is not None:
+            # add_noise is called after first denoising step (for inpainting)
+            step_indices = [self.step_index] * timesteps.shape[0]
         else:
+            # add noise is called before first denoising step to create initial latent(img2img)
             step_indices = [self.begin_index] * timesteps.shape[0]
 
         sigma = sigmas[step_indices].flatten()

diffusers/schedulers/scheduling_karras_ve_flax.py

@@ -176,10 +176,10 @@ class FlaxKarrasVeScheduler(FlaxSchedulerMixin, ConfigMixin):
 
         Args:
             state (`KarrasVeSchedulerState`): the `FlaxKarrasVeScheduler` state data class.
-            model_output (`torch.FloatTensor` or `np.ndarray`): direct output from learned diffusion model.
+            model_output (`torch.Tensor` or `np.ndarray`): direct output from learned diffusion model.
             sigma_hat (`float`): TODO
             sigma_prev (`float`): TODO
-            sample_hat (`torch.FloatTensor` or `np.ndarray`): TODO
+            sample_hat (`torch.Tensor` or `np.ndarray`): TODO
             return_dict (`bool`): option for returning tuple rather than FlaxKarrasVeOutput class
 
         Returns:
@@ -213,12 +213,12 @@ class FlaxKarrasVeScheduler(FlaxSchedulerMixin, ConfigMixin):
 
         Args:
             state (`KarrasVeSchedulerState`): the `FlaxKarrasVeScheduler` state data class.
-            model_output (`torch.FloatTensor` or `np.ndarray`): direct output from learned diffusion model.
+            model_output (`torch.Tensor` or `np.ndarray`): direct output from learned diffusion model.
             sigma_hat (`float`): TODO
             sigma_prev (`float`): TODO
-            sample_hat (`torch.FloatTensor` or `np.ndarray`): TODO
-            sample_prev (`torch.FloatTensor` or `np.ndarray`): TODO
-            derivative (`torch.FloatTensor` or `np.ndarray`): TODO
+            sample_hat (`torch.Tensor` or `np.ndarray`): TODO
+            sample_prev (`torch.Tensor` or `np.ndarray`): TODO
+            derivative (`torch.Tensor` or `np.ndarray`): TODO
             return_dict (`bool`): option for returning tuple rather than FlaxKarrasVeOutput class
 
         Returns:

diffusers/schedulers/scheduling_lcm.py

@@ -37,16 +37,16 @@ class LCMSchedulerOutput(BaseOutput):
     Output class for the scheduler's `step` function output.
 
     Args:
-        prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
+        prev_sample (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` for images):
             Computed sample `(x_{t-1})` of previous timestep. `prev_sample` should be used as next model input in the
             denoising loop.
-        pred_original_sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` for images):
+        pred_original_sample (`torch.Tensor` of shape `(batch_size, num_channels, height, width)` for images):
             The predicted denoised sample `(x_{0})` based on the model output from the current timestep.
             `pred_original_sample` can be used to preview progress or for guidance.
     """
 
-    prev_sample: torch.FloatTensor
-    denoised: Optional[torch.FloatTensor] = None
+    prev_sample: torch.Tensor
+    denoised: Optional[torch.Tensor] = None
 
 
 # Copied from diffusers.schedulers.scheduling_ddpm.betas_for_alpha_bar
@@ -84,7 +84,7 @@ def betas_for_alpha_bar(
             return math.exp(t * -12.0)
 
     else:
-        raise ValueError(f"Unsupported alpha_tranform_type: {alpha_transform_type}")
+        raise ValueError(f"Unsupported alpha_transform_type: {alpha_transform_type}")
 
     betas = []
     for i in range(num_diffusion_timesteps):
@@ -95,17 +95,17 @@ def betas_for_alpha_bar(
 
 
 # Copied from diffusers.schedulers.scheduling_ddim.rescale_zero_terminal_snr
-def rescale_zero_terminal_snr(betas: torch.FloatTensor) -> torch.FloatTensor:
+def rescale_zero_terminal_snr(betas: torch.Tensor) -> torch.Tensor:
     """
     Rescales betas to have zero terminal SNR Based on https://arxiv.org/pdf/2305.08891.pdf (Algorithm 1)
 
 
     Args:
-        betas (`torch.FloatTensor`):
+        betas (`torch.Tensor`):
             the betas that the scheduler is being initialized with.
 
     Returns:
-        `torch.FloatTensor`: rescaled betas with zero terminal SNR
+        `torch.Tensor`: rescaled betas with zero terminal SNR
     """
     # Convert betas to alphas_bar_sqrt
     alphas = 1.0 - betas
@@ -224,7 +224,7 @@ class LCMScheduler(SchedulerMixin, ConfigMixin):
             # Glide cosine schedule
             self.betas = betas_for_alpha_bar(num_train_timesteps)
         else:
-            raise NotImplementedError(f"{beta_schedule} does is not implemented for {self.__class__}")
+            raise NotImplementedError(f"{beta_schedule} is not implemented for {self.__class__}")
 
         # Rescale for zero SNR
         if rescale_betas_zero_snr:
@@ -296,24 +296,24 @@ class LCMScheduler(SchedulerMixin, ConfigMixin):
         """
         self._begin_index = begin_index
 
-    def scale_model_input(self, sample: torch.FloatTensor, timestep: Optional[int] = None) -> torch.FloatTensor:
+    def scale_model_input(self, sample: torch.Tensor, timestep: Optional[int] = None) -> torch.Tensor:
         """
         Ensures interchangeability with schedulers that need to scale the denoising model input depending on the
         current timestep.
 
         Args:
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 The input sample.
             timestep (`int`, *optional*):
                 The current timestep in the diffusion chain.
         Returns:
-            `torch.FloatTensor`:
+            `torch.Tensor`:
                 A scaled input sample.
         """
         return sample
 
     # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler._threshold_sample
-    def _threshold_sample(self, sample: torch.FloatTensor) -> torch.FloatTensor:
+    def _threshold_sample(self, sample: torch.Tensor) -> torch.Tensor:
         """
         "Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the
         prediction of x_0 at timestep t), and if s > 1, then we threshold xt0 to the range [-s, s] and then divide by
@@ -497,9 +497,9 @@ class LCMScheduler(SchedulerMixin, ConfigMixin):
 
     def step(
         self,
-        model_output: torch.FloatTensor,
+        model_output: torch.Tensor,
         timestep: int,
-        sample: torch.FloatTensor,
+        sample: torch.Tensor,
         generator: Optional[torch.Generator] = None,
         return_dict: bool = True,
     ) -> Union[LCMSchedulerOutput, Tuple]:
@@ -508,11 +508,11 @@ class LCMScheduler(SchedulerMixin, ConfigMixin):
         process from the learned model outputs (most often the predicted noise).
 
         Args:
-            model_output (`torch.FloatTensor`):
+            model_output (`torch.Tensor`):
                 The direct output from learned diffusion model.
             timestep (`float`):
                 The current discrete timestep in the diffusion chain.
-            sample (`torch.FloatTensor`):
+            sample (`torch.Tensor`):
                 A current instance of a sample created by the diffusion process.
             generator (`torch.Generator`, *optional*):
                 A random number generator.
@@ -594,10 +594,10 @@ class LCMScheduler(SchedulerMixin, ConfigMixin):
     # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler.add_noise
     def add_noise(
         self,
-        original_samples: torch.FloatTensor,
-        noise: torch.FloatTensor,
+        original_samples: torch.Tensor,
+        noise: torch.Tensor,
         timesteps: torch.IntTensor,
-    ) -> torch.FloatTensor:
+    ) -> torch.Tensor:
         # Make sure alphas_cumprod and timestep have same device and dtype as original_samples
         # Move the self.alphas_cumprod to device to avoid redundant CPU to GPU data movement
         # for the subsequent add_noise calls
@@ -619,9 +619,7 @@ class LCMScheduler(SchedulerMixin, ConfigMixin):
         return noisy_samples
 
     # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler.get_velocity
-    def get_velocity(
-        self, sample: torch.FloatTensor, noise: torch.FloatTensor, timesteps: torch.IntTensor
-    ) -> torch.FloatTensor:
+    def get_velocity(self, sample: torch.Tensor, noise: torch.Tensor, timesteps: torch.IntTensor) -> torch.Tensor:
         # Make sure alphas_cumprod and timestep have same device and dtype as sample
         self.alphas_cumprod = self.alphas_cumprod.to(device=sample.device)
         alphas_cumprod = self.alphas_cumprod.to(dtype=sample.dtype)