Improve docstrings and type hints in scheduling_ddim_parallel.py (#13023)

* docs: improve docstring scheduling_ddim_parallel.py

* docs: improve docstring scheduling_ddim_parallel.py

* Update src/diffusers/schedulers/scheduling_ddim_parallel.py

Co-authored-by: Steven Liu <[email protected]>

* Update src/diffusers/schedulers/scheduling_ddim_parallel.py

Co-authored-by: Steven Liu <[email protected]>

* Update src/diffusers/schedulers/scheduling_ddim_parallel.py

Co-authored-by: Steven Liu <[email protected]>

* Update src/diffusers/schedulers/scheduling_ddim_parallel.py

Co-authored-by: Steven Liu <[email protected]>

* fix style

---------

Co-authored-by: Steven Liu <[email protected]>

Author: delmalih

src/diffusers/schedulers/scheduling_ddim_parallel.py

@@ -101,7 +101,7 @@ def alpha_bar_fn(t):
 
 
 # Copied from diffusers.schedulers.scheduling_ddim.rescale_zero_terminal_snr
-def rescale_zero_terminal_snr(betas):
+def rescale_zero_terminal_snr(betas: torch.Tensor) -> torch.Tensor:
     """
     Rescales betas to have zero terminal SNR Based on https://huggingface.co/papers/2305.08891 (Algorithm 1)
 
@@ -266,7 +266,7 @@ def scale_model_input(self, sample: torch.Tensor, timestep: Optional[int] = None
         """
         return sample
 
-    def _get_variance(self, timestep, prev_timestep=None):
+    def _get_variance(self, timestep: int, prev_timestep: Optional[int] = None) -> torch.Tensor:
         if prev_timestep is None:
             prev_timestep = timestep - self.config.num_train_timesteps // self.num_inference_steps
 
@@ -279,7 +279,7 @@ def _get_variance(self, timestep, prev_timestep=None):
 
         return variance
 
-    def _batch_get_variance(self, t, prev_t):
+    def _batch_get_variance(self, t: torch.Tensor, prev_t: torch.Tensor) -> torch.Tensor:
         alpha_prod_t = self.alphas_cumprod[t]
         alpha_prod_t_prev = self.alphas_cumprod[torch.clip(prev_t, min=0)]
         alpha_prod_t_prev[prev_t < 0] = torch.tensor(1.0)
@@ -335,7 +335,7 @@ def _threshold_sample(self, sample: torch.Tensor) -> torch.Tensor:
         return sample
 
     # Copied from diffusers.schedulers.scheduling_ddim.DDIMScheduler.set_timesteps
-    def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None):
+    def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.device] = None) -> None:
         """
         Sets the discrete timesteps used for the diffusion chain (to be run before inference).
 
@@ -392,7 +392,7 @@ def step(
         sample: torch.Tensor,
         eta: float = 0.0,
         use_clipped_model_output: bool = False,
-        generator=None,
+        generator: Optional[torch.Generator] = None,
         variance_noise: Optional[torch.Tensor] = None,
         return_dict: bool = True,
     ) -> Union[DDIMParallelSchedulerOutput, Tuple]:
@@ -406,11 +406,13 @@ def step(
             sample (`torch.Tensor`):
                 current instance of sample being created by diffusion process.
             eta (`float`): weight of noise for added noise in diffusion step.
-            use_clipped_model_output (`bool`): if `True`, compute "corrected" `model_output` from the clipped
-                predicted original sample. Necessary because predicted original sample is clipped to [-1, 1] when
-                `self.config.clip_sample` is `True`. If no clipping has happened, "corrected" `model_output` would
-                coincide with the one provided as input and `use_clipped_model_output` will have not effect.
-            generator: random number generator.
+            use_clipped_model_output (`bool`, defaults to `False`):
+                If `True`, compute "corrected" `model_output` from the clipped predicted original sample. This
+                correction is necessary because the predicted original sample is clipped to [-1, 1] when
+                `self.config.clip_sample` is `True`. If no clipping occurred, the "corrected" `model_output` matches
+                the input and `use_clipped_model_output` has no effect.
+            generator (`torch.Generator`, *optional*):
+                Random number generator.
             variance_noise (`torch.Tensor`): instead of generating noise for the variance using `generator`, we
                 can directly provide the noise for the variance itself. This is useful for methods such as
                 CycleDiffusion. (https://huggingface.co/papers/2210.05559)
@@ -496,7 +498,10 @@ def step(
 
             if variance_noise is None:
                 variance_noise = randn_tensor(
-                    model_output.shape, generator=generator, device=model_output.device, dtype=model_output.dtype
+                    model_output.shape,
+                    generator=generator,
+                    device=model_output.device,
+                    dtype=model_output.dtype,
                 )
             variance = std_dev_t * variance_noise
 
@@ -513,7 +518,7 @@ def step(
     def batch_step_no_noise(
         self,
         model_output: torch.Tensor,
-        timesteps: List[int],
+        timesteps: torch.Tensor,
         sample: torch.Tensor,
         eta: float = 0.0,
         use_clipped_model_output: bool = False,
@@ -528,7 +533,7 @@ def batch_step_no_noise(
 
         Args:
             model_output (`torch.Tensor`): direct output from learned diffusion model.
-            timesteps (`List[int]`):
+            timesteps (`torch.Tensor`):
                 current discrete timesteps in the diffusion chain. This is now a list of integers.
             sample (`torch.Tensor`):
                 current instance of sample being created by diffusion process.
@@ -696,5 +701,5 @@ def get_velocity(self, sample: torch.Tensor, noise: torch.Tensor, timesteps: tor
         velocity = sqrt_alpha_prod * noise - sqrt_one_minus_alpha_prod * sample
         return velocity
 
-    def __len__(self):
+    def __len__(self) -> int:
         return self.config.num_train_timesteps