huggingface
diff --git a/‎src/diffusers/schedulers/scheduling_ddim.py
Lines changed: 17 additions & 12 deletions b/‎src/diffusers/schedulers/scheduling_ddim.py
Lines changed: 17 additions & 12 deletions
@@ -16,7 +16,7 @@
 # and https://github.com/hojonathanho/diffusion
 
 import math
-from typing import Union
+from typing import Optional, Union
 
 import numpy as np
 import torch
@@ -73,15 +73,15 @@ class DDIMScheduler(SchedulerMixin, ConfigMixin):
     @register_to_config
     def __init__(
         self,
-        num_train_timesteps=1000,
-        beta_start=0.0001,
-        beta_end=0.02,
-        beta_schedule="linear",
-        trained_betas=None,
-        timestep_values=None,
-        clip_sample=True,
-        set_alpha_to_one=True,
-        tensor_format="pt",
+        num_train_timesteps: int = 1000,
+        beta_start: float = 0.0001,
+        beta_end: float = 0.02,
+        beta_schedule: str = "linear",
+        trained_betas: Optional[np.ndarray] = None,
+        timestep_values: Optional[np.ndarray] = None,
+        clip_sample: bool = True,
+        set_alpha_to_one: bool = True,
+        tensor_format: str = "pt",
     ):
         if trained_betas is not None:
             self.betas = np.asarray(trained_betas)
@@ -122,7 +122,7 @@ def _get_variance(self, timestep, prev_timestep):
 
         return variance
 
-    def set_timesteps(self, num_inference_steps, offset=0):
+    def set_timesteps(self, num_inference_steps: int, offset: int = 0):
         self.num_inference_steps = num_inference_steps
         self.timesteps = np.arange(
             0, self.config.num_train_timesteps, self.config.num_train_timesteps // self.num_inference_steps
@@ -198,7 +198,12 @@ def step(
 
         return {"prev_sample": prev_sample}
 
-    def add_noise(self, original_samples, noise, timesteps):
+    def add_noise(
+        self,
+        original_samples: Union[torch.FloatTensor, np.ndarray],
+        noise: Union[torch.FloatTensor, np.ndarray],
+        timesteps: Union[torch.IntTensor, np.ndarray],
+    ) -> Union[torch.FloatTensor, np.ndarray]:
         sqrt_alpha_prod = self.alphas_cumprod[timesteps] ** 0.5
         sqrt_alpha_prod = self.match_shape(sqrt_alpha_prod, original_samples)
         sqrt_one_minus_alpha_prod = (1 - self.alphas_cumprod[timesteps]) ** 0.5