diffusers 0.27.0__py3-none-any.whl → 0.32.2__py3-none-any.whl

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)
@@ -645,16 +643,12 @@ class LCMScheduler(SchedulerMixin, ConfigMixin):
 
     # Copied from diffusers.schedulers.scheduling_ddpm.DDPMScheduler.previous_timestep
     def previous_timestep(self, timestep):
-        if self.custom_timesteps:
+        if self.custom_timesteps or self.num_inference_steps:
             index = (self.timesteps == timestep).nonzero(as_tuple=True)[0][0]
             if index == self.timesteps.shape[0] - 1:
                 prev_t = torch.tensor(-1)
             else:
                 prev_t = self.timesteps[index + 1]
         else:
-            num_inference_steps = (
-                self.num_inference_steps if self.num_inference_steps else self.config.num_train_timesteps
-            )
-            prev_t = timestep - self.config.num_train_timesteps // num_inference_steps
-
+            prev_t = timestep - 1
         return prev_t

diffusers/schedulers/scheduling_lms_discrete.py

@@ -17,6 +17,7 @@ from dataclasses import dataclass
 from typing import List, Optional, Tuple, Union
 
 import numpy as np
+import scipy.stats
 import torch
 from scipy import integrate
 
@@ -32,16 +33,16 @@ class LMSDiscreteSchedulerOutput(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
-    pred_original_sample: Optional[torch.FloatTensor] = None
+    prev_sample: torch.Tensor
+    pred_original_sample: Optional[torch.Tensor] = None
 
 
 # Copied from diffusers.schedulers.scheduling_ddpm.betas_for_alpha_bar
@@ -79,7 +80,7 @@ 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):
@@ -111,6 +112,11 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         use_karras_sigmas (`bool`, *optional*, defaults to `False`):
             Whether to use Karras sigmas for step sizes in the noise schedule during the sampling process. If `True`,
             the sigmas are determined according to a sequence of noise levels {σi}.
+        use_exponential_sigmas (`bool`, *optional*, defaults to `False`):
+            Whether to use exponential sigmas for step sizes in the noise schedule during the sampling process.
+        use_beta_sigmas (`bool`, *optional*, defaults to `False`):
+            Whether to use beta sigmas for step sizes in the noise schedule during the sampling process. Refer to [Beta
+            Sampling is All You Need](https://huggingface.co/papers/2407.12173) for more information.
         prediction_type (`str`, defaults to `epsilon`, *optional*):
             Prediction type of the scheduler function; can be `epsilon` (predicts the noise of the diffusion process),
             `sample` (directly predicts the noisy sample`) or `v_prediction` (see section 2.4 of [Imagen
@@ -134,10 +140,16 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         beta_schedule: str = "linear",
         trained_betas: Optional[Union[np.ndarray, List[float]]] = None,
         use_karras_sigmas: Optional[bool] = False,
+        use_exponential_sigmas: Optional[bool] = False,
+        use_beta_sigmas: Optional[bool] = False,
         prediction_type: str = "epsilon",
         timestep_spacing: str = "linspace",
         steps_offset: int = 0,
     ):
+        if sum([self.config.use_beta_sigmas, self.config.use_exponential_sigmas, self.config.use_karras_sigmas]) > 1:
+            raise ValueError(
+                "Only one of `config.use_beta_sigmas`, `config.use_exponential_sigmas`, `config.use_karras_sigmas` can be used."
+            )
         if trained_betas is not None:
             self.betas = torch.tensor(trained_betas, dtype=torch.float32)
         elif beta_schedule == "linear":
@@ -149,7 +161,7 @@ class LMSDiscreteScheduler(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)
@@ -180,7 +192,7 @@ class LMSDiscreteScheduler(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
 
@@ -202,21 +214,19 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         """
         self._begin_index = begin_index
 
-    def scale_model_input(
-        self, sample: torch.FloatTensor, timestep: Union[float, torch.FloatTensor]
-    ) -> torch.FloatTensor:
+    def scale_model_input(self, 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 (`float` or `torch.FloatTensor`):
+            timestep (`float` or `torch.Tensor`):
                 The current timestep in the diffusion chain.
 
         Returns:
-            `torch.FloatTensor`:
+            `torch.Tensor`:
                 A scaled input sample.
         """
 
@@ -288,9 +298,15 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         log_sigmas = np.log(sigmas)
         sigmas = np.interp(timesteps, np.arange(0, len(sigmas)), sigmas)
 
-        if self.use_karras_sigmas:
+        if self.config.use_karras_sigmas:
             sigmas = self._convert_to_karras(in_sigmas=sigmas)
             timesteps = np.array([self._sigma_to_t(sigma, log_sigmas) for sigma in sigmas])
+        elif self.config.use_exponential_sigmas:
+            sigmas = self._convert_to_exponential(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
+            timesteps = np.array([self._sigma_to_t(sigma, log_sigmas) for sigma in sigmas])
+        elif self.config.use_beta_sigmas:
+            sigmas = self._convert_to_beta(in_sigmas=sigmas, num_inference_steps=num_inference_steps)
+            timesteps = np.array([self._sigma_to_t(sigma, log_sigmas) for sigma in sigmas])
 
         sigmas = np.concatenate([sigmas, [0.0]]).astype(np.float32)
 
@@ -326,7 +342,7 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         else:
             self._step_index = self._begin_index
 
-    # copied from diffusers.schedulers.scheduling_euler_discrete._sigma_to_t
+    # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._sigma_to_t
     def _sigma_to_t(self, sigma, log_sigmas):
         # get log sigma
         log_sigma = np.log(np.maximum(sigma, 1e-10))
@@ -350,8 +366,8 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         t = t.reshape(sigma.shape)
         return t
 
-    # copied from diffusers.schedulers.scheduling_euler_discrete._convert_to_karras
-    def _convert_to_karras(self, in_sigmas: torch.FloatTensor) -> torch.FloatTensor:
+    # copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._convert_to_karras
+    def _convert_to_karras(self, in_sigmas: torch.Tensor) -> torch.Tensor:
         """Constructs the noise schedule of Karras et al. (2022)."""
 
         sigma_min: float = in_sigmas[-1].item()
@@ -364,11 +380,65 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         sigmas = (max_inv_rho + ramp * (min_inv_rho - max_inv_rho)) ** rho
         return sigmas
 
+    # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._convert_to_exponential
+    def _convert_to_exponential(self, in_sigmas: torch.Tensor, num_inference_steps: int) -> torch.Tensor:
+        """Constructs an exponential noise schedule."""
+
+        # Hack to make sure that other schedulers which copy this function don't break
+        # TODO: Add this logic to the other schedulers
+        if hasattr(self.config, "sigma_min"):
+            sigma_min = self.config.sigma_min
+        else:
+            sigma_min = None
+
+        if hasattr(self.config, "sigma_max"):
+            sigma_max = self.config.sigma_max
+        else:
+            sigma_max = None
+
+        sigma_min = sigma_min if sigma_min is not None else in_sigmas[-1].item()
+        sigma_max = sigma_max if sigma_max is not None else in_sigmas[0].item()
+
+        sigmas = np.exp(np.linspace(math.log(sigma_max), math.log(sigma_min), num_inference_steps))
+        return sigmas
+
+    # Copied from diffusers.schedulers.scheduling_euler_discrete.EulerDiscreteScheduler._convert_to_beta
+    def _convert_to_beta(
+        self, in_sigmas: torch.Tensor, num_inference_steps: int, alpha: float = 0.6, beta: float = 0.6
+    ) -> torch.Tensor:
+        """From "Beta Sampling is All You Need" [arXiv:2407.12173] (Lee et. al, 2024)"""
+
+        # Hack to make sure that other schedulers which copy this function don't break
+        # TODO: Add this logic to the other schedulers
+        if hasattr(self.config, "sigma_min"):
+            sigma_min = self.config.sigma_min
+        else:
+            sigma_min = None
+
+        if hasattr(self.config, "sigma_max"):
+            sigma_max = self.config.sigma_max
+        else:
+            sigma_max = None
+
+        sigma_min = sigma_min if sigma_min is not None else in_sigmas[-1].item()
+        sigma_max = sigma_max if sigma_max is not None else in_sigmas[0].item()
+
+        sigmas = np.array(
+            [
+                sigma_min + (ppf * (sigma_max - sigma_min))
+                for ppf in [
+                    scipy.stats.beta.ppf(timestep, alpha, beta)
+                    for timestep in 1 - np.linspace(0, 1, num_inference_steps)
+                ]
+            ]
+        )
+        return sigmas
+
     def step(
         self,
-        model_output: torch.FloatTensor,
-        timestep: Union[float, torch.FloatTensor],
-        sample: torch.FloatTensor,
+        model_output: torch.Tensor,
+        timestep: Union[float, torch.Tensor],
+        sample: torch.Tensor,
         order: int = 4,
         return_dict: bool = True,
     ) -> Union[LMSDiscreteSchedulerOutput, Tuple]:
@@ -377,11 +447,11 @@ class LMSDiscreteScheduler(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` or `torch.FloatTensor`):
+            timestep (`float` or `torch.Tensor`):
                 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.
             order (`int`, defaults to 4):
                 The order of the linear multistep method.
@@ -437,17 +507,20 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         self._step_index += 1
 
         if not return_dict:
-            return (prev_sample,)
+            return (
+                prev_sample,
+                pred_original_sample,
+            )
 
         return LMSDiscreteSchedulerOutput(prev_sample=prev_sample, pred_original_sample=pred_original_sample)
 
     # 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):
@@ -461,7 +534,11 @@ class LMSDiscreteScheduler(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_pndm.py

@@ -59,7 +59,7 @@ 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 PNDMScheduler(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)
@@ -225,9 +225,9 @@ class PNDMScheduler(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]:
         """
@@ -236,11 +236,11 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
         or [`~PNDMScheduler.step_plms`] depending on the internal variable `counter`.
 
         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`.
@@ -258,9 +258,9 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
 
     def step_prk(
         self,
-        model_output: torch.FloatTensor,
+        model_output: torch.Tensor,
         timestep: int,
-        sample: torch.FloatTensor,
+        sample: torch.Tensor,
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
@@ -269,11 +269,11 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
         equation.
 
         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.
@@ -318,9 +318,9 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
 
     def step_plms(
         self,
-        model_output: torch.FloatTensor,
+        model_output: torch.Tensor,
         timestep: int,
-        sample: torch.FloatTensor,
+        sample: torch.Tensor,
         return_dict: bool = True,
     ) -> Union[SchedulerOutput, Tuple]:
         """
@@ -328,11 +328,11 @@ class PNDMScheduler(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.
@@ -387,17 +387,17 @@ class PNDMScheduler(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
@@ -448,10 +448,10 @@ class PNDMScheduler(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

diffusers/schedulers/scheduling_repaint.py

@@ -31,16 +31,16 @@ class RePaintSchedulerOutput(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
-    pred_original_sample: torch.FloatTensor
+    prev_sample: torch.Tensor
+    pred_original_sample: torch.Tensor
 
 
 # Copied from diffusers.schedulers.scheduling_ddpm.betas_for_alpha_bar
@@ -78,7 +78,7 @@ 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):
@@ -143,7 +143,7 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
             betas = torch.linspace(-6, 6, num_train_timesteps)
             self.betas = torch.sigmoid(betas) * (beta_end - beta_start) + beta_start
         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)
@@ -160,19 +160,19 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
 
         self.eta = eta
 
-    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
@@ -245,11 +245,11 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
 
     def step(
         self,
-        model_output: torch.FloatTensor,
+        model_output: torch.Tensor,
         timestep: int,
-        sample: torch.FloatTensor,
-        original_image: torch.FloatTensor,
-        mask: torch.FloatTensor,
+        sample: torch.Tensor,
+        original_image: torch.Tensor,
+        mask: torch.Tensor,
         generator: Optional[torch.Generator] = None,
         return_dict: bool = True,
     ) -> Union[RePaintSchedulerOutput, Tuple]:
@@ -258,15 +258,15 @@ class RePaintScheduler(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 (`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.
-            original_image (`torch.FloatTensor`):
+            original_image (`torch.Tensor`):
                 The original image to inpaint on.
-            mask (`torch.FloatTensor`):
+            mask (`torch.Tensor`):
                 The mask where a value of 0.0 indicates which part of the original image to inpaint.
             generator (`torch.Generator`, *optional*):
                 A random number generator.
@@ -319,7 +319,7 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
         prev_unknown_part = alpha_prod_t_prev**0.5 * pred_original_sample + pred_sample_direction + variance
 
         # 8. Algorithm 1 Line 5 https://arxiv.org/pdf/2201.09865.pdf
-        prev_known_part = (alpha_prod_t_prev**0.5) * original_image + ((1 - alpha_prod_t_prev) ** 0.5) * noise
+        prev_known_part = (alpha_prod_t_prev**0.5) * original_image + (1 - alpha_prod_t_prev) * noise
 
         # 9. Algorithm 1 Line 8 https://arxiv.org/pdf/2201.09865.pdf
         pred_prev_sample = mask * prev_known_part + (1.0 - mask) * prev_unknown_part
@@ -351,10 +351,10 @@ class RePaintScheduler(SchedulerMixin, ConfigMixin):
 
     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:
         raise NotImplementedError("Use `DDPMScheduler.add_noise()` to train for sampling with RePaint.")
 
     def __len__(self):