Scheduler docs update (#464)

* update scheduler docs TODOs, fix typos

* fix another typo

src/diffusers/schedulers/scheduling_ddim.py

@@ -62,7 +62,7 @@ class DDIMScheduler(SchedulerMixin, ConfigMixin):
     [`~ConfigMixin`] takes care of storing all config attributes that are passed in the scheduler's `__init__`
     function, such as `num_train_timesteps`. They can be accessed via `scheduler.config.num_train_timesteps`.
     [`~ConfigMixin`] also provides general loading and saving functionality via the [`~ConfigMixin.save_config`] and
-    [`~ConfigMixin.from_config`] functios.
+    [`~ConfigMixin.from_config`] functions.
 
     For more details, see the original paper: https://arxiv.org/abs/2010.02502
 
@@ -73,8 +73,8 @@ class DDIMScheduler(SchedulerMixin, ConfigMixin):
         beta_schedule (`str`):
             the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
             `linear`, `scaled_linear`, or `squaredcos_cap_v2`.
-        trained_betas (`np.ndarray`, optional): TODO
-        timestep_values (`np.ndarray`, optional): TODO
+        trained_betas (`np.ndarray`, optional):
+            option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
         clip_sample (`bool`, default `True`):
             option to clip predicted sample between -1 and 1 for numerical stability.
         set_alpha_to_one (`bool`, default `True`):
@@ -91,7 +91,6 @@ class DDIMScheduler(SchedulerMixin, ConfigMixin):
         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",
@@ -142,7 +141,8 @@ class DDIMScheduler(SchedulerMixin, ConfigMixin):
         Args:
             num_inference_steps (`int`):
                 the number of diffusion steps used when generating samples with a pre-trained model.
-            offset (`int`): TODO
+            offset (`int`):
+                optional value to shift timestep values up by. A value of 1 is used in stable diffusion for inference.
         """
         self.num_inference_steps = num_inference_steps
         self.timesteps = np.arange(

src/diffusers/schedulers/scheduling_ddpm.py

@@ -61,7 +61,7 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
     [`~ConfigMixin`] takes care of storing all config attributes that are passed in the scheduler's `__init__`
     function, such as `num_train_timesteps`. They can be accessed via `scheduler.config.num_train_timesteps`.
     [`~ConfigMixin`] also provides general loading and saving functionality via the [`~ConfigMixin.save_config`] and
-    [`~ConfigMixin.from_config`] functios.
+    [`~ConfigMixin.from_config`] functions.
 
     For more details, see the original paper: https://arxiv.org/abs/2006.11239
 
@@ -72,7 +72,8 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
         beta_schedule (`str`):
             the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
             `linear`, `scaled_linear`, or `squaredcos_cap_v2`.
-        trained_betas (`np.ndarray`, optional): TODO
+        trained_betas (`np.ndarray`, optional):
+            option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
         variance_type (`str`):
             options to clip the variance used when adding noise to the denoised sample. Choose from `fixed_small`,
             `fixed_small_log`, `fixed_large`, `fixed_large_log`, `learned` or `learned_range`.

src/diffusers/schedulers/scheduling_karras_ve.py

@@ -53,7 +53,7 @@ class KarrasVeScheduler(SchedulerMixin, ConfigMixin):
     [`~ConfigMixin`] takes care of storing all config attributes that are passed in the scheduler's `__init__`
     function, such as `num_train_timesteps`. They can be accessed via `scheduler.config.num_train_timesteps`.
     [`~ConfigMixin`] also provides general loading and saving functionality via the [`~ConfigMixin.save_config`] and
-    [`~ConfigMixin.from_config`] functios.
+    [`~ConfigMixin.from_config`] functions.
 
     For more details on the parameters, see the original paper's Appendix E.: "Elucidating the Design Space of
     Diffusion-Based Generative Models." https://arxiv.org/abs/2206.00364. The grid search values used to find the

src/diffusers/schedulers/scheduling_lms_discrete.py

@@ -32,7 +32,7 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
     [`~ConfigMixin`] takes care of storing all config attributes that are passed in the scheduler's `__init__`
     function, such as `num_train_timesteps`. They can be accessed via `scheduler.config.num_train_timesteps`.
     [`~ConfigMixin`] also provides general loading and saving functionality via the [`~ConfigMixin.save_config`] and
-    [`~ConfigMixin.from_config`] functios.
+    [`~ConfigMixin.from_config`] functions.
 
     Args:
         num_train_timesteps (`int`): number of diffusion steps used to train the model.
@@ -41,10 +41,10 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         beta_schedule (`str`):
             the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
             `linear` or `scaled_linear`.
-        trained_betas (`np.ndarray`, optional): TODO
+        trained_betas (`np.ndarray`, optional):
+            option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
             options to clip the variance used when adding noise to the denoised sample. Choose from `fixed_small`,
             `fixed_small_log`, `fixed_large`, `fixed_large_log`, `learned` or `learned_range`.
-        timestep_values (`np.ndarry`, optional): TODO
         tensor_format (`str`): whether the scheduler expects pytorch or numpy arrays.
 
     """
@@ -57,7 +57,6 @@ class LMSDiscreteScheduler(SchedulerMixin, ConfigMixin):
         beta_end: float = 0.02,
         beta_schedule: str = "linear",
         trained_betas: Optional[np.ndarray] = None,
-        timestep_values: Optional[np.ndarray] = None,
         tensor_format: str = "pt",
     ):
         if trained_betas is not None:

src/diffusers/schedulers/scheduling_pndm.py

@@ -61,7 +61,7 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
     [`~ConfigMixin`] takes care of storing all config attributes that are passed in the scheduler's `__init__`
     function, such as `num_train_timesteps`. They can be accessed via `scheduler.config.num_train_timesteps`.
     [`~ConfigMixin`] also provides general loading and saving functionality via the [`~ConfigMixin.save_config`] and
-    [`~ConfigMixin.from_config`] functios.
+    [`~ConfigMixin.from_config`] functions.
 
     For more details, see the original paper: https://arxiv.org/abs/2202.09778
 
@@ -72,7 +72,8 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
         beta_schedule (`str`):
             the beta schedule, a mapping from a beta range to a sequence of betas for stepping the model. Choose from
             `linear`, `scaled_linear`, or `squaredcos_cap_v2`.
-        trained_betas (`np.ndarray`, optional): TODO
+        trained_betas (`np.ndarray`, optional):
+            option to pass an array of betas directly to the constructor to bypass `beta_start`, `beta_end` etc.
         tensor_format (`str`): whether the scheduler expects pytorch or numpy arrays
         skip_prk_steps (`bool`):
             allows the scheduler to skip the Runge-Kutta steps that are defined in the original paper as being required
@@ -138,7 +139,8 @@ class PNDMScheduler(SchedulerMixin, ConfigMixin):
         Args:
             num_inference_steps (`int`):
                 the number of diffusion steps used when generating samples with a pre-trained model.
-            offset (`int`): TODO
+            offset (`int`):
+                optional value to shift timestep values up by. A value of 1 is used in stable diffusion for inference.
         """
         self.num_inference_steps = num_inference_steps
         self._timesteps = list(

src/diffusers/schedulers/scheduling_sde_ve.py

@@ -52,7 +52,7 @@ class ScoreSdeVeScheduler(SchedulerMixin, ConfigMixin):
     [`~ConfigMixin`] takes care of storing all config attributes that are passed in the scheduler's `__init__`
     function, such as `num_train_timesteps`. They can be accessed via `scheduler.config.num_train_timesteps`.
     [`~ConfigMixin`] also provides general loading and saving functionality via the [`~ConfigMixin.save_config`] and
-    [`~ConfigMixin.from_config`] functios.
+    [`~ConfigMixin.from_config`] functions.
 
     Args:
         snr (`float`):
@@ -61,7 +61,7 @@ class ScoreSdeVeScheduler(SchedulerMixin, ConfigMixin):
                 initial noise scale for sigma sequence in sampling procedure. The minimum sigma should mirror the
                 distribution of the data.
         sigma_max (`float`): maximum value used for the range of continuous timesteps passed into the model.
-        sampling_eps (`float`): the end value of sampling, where timesteps decrease progessively from 1 to
+        sampling_eps (`float`): the end value of sampling, where timesteps decrease progressively from 1 to
         epsilon.
         correct_steps (`int`): number of correction steps performed on a produced sample.
         tensor_format (`str`): "np" or "pt" for the expected format of samples passed to the Scheduler.

src/diffusers/schedulers/scheduling_sde_vp.py

@@ -30,7 +30,7 @@ class ScoreSdeVpScheduler(SchedulerMixin, ConfigMixin):
     [`~ConfigMixin`] takes care of storing all config attributes that are passed in the scheduler's `__init__`
     function, such as `num_train_timesteps`. They can be accessed via `scheduler.config.num_train_timesteps`.
     [`~ConfigMixin`] also provides general loading and saving functionality via the [`~ConfigMixin.save_config`] and
-    [`~ConfigMixin.from_config`] functios.
+    [`~ConfigMixin.from_config`] functions.
 
     For more information, see the original paper: https://arxiv.org/abs/2011.13456