Change step_offset scheduler docstrings (huggingface#7128)

* Change step_offset scheduler docstrings

* Mention it may be needed by some models

* More docstrings

These ones failed literal S&R because I performed it case-sensitive
which is fun.

---------

Co-authored-by: Sayak Paul <[email protected]>

Author: Beinsezii

examples/community/latent_consistency_img2img.py

@@ -513,9 +513,7 @@ class LCMSchedulerWithTimestamp(SchedulerMixin, ConfigMixin):
             there is no previous alpha. When this option is `True` the previous alpha product is fixed to `1`,
             otherwise it uses the alpha value at step 0.
         steps_offset (`int`, defaults to 0):
-            An offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
-            Diffusion.
+            An offset added to the inference steps, as required by some model families.
         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

examples/community/latent_consistency_txt2img.py

@@ -418,9 +418,7 @@ class LCMScheduler(SchedulerMixin, ConfigMixin):
             there is no previous alpha. When this option is `True` the previous alpha product is fixed to `1`,
             otherwise it uses the alpha value at step 0.
         steps_offset (`int`, defaults to 0):
-            An offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
-            Diffusion.
+            An offset added to the inference steps, as required by some model families.
         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

examples/community/scheduling_ufogen.py

@@ -171,9 +171,7 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
             The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
             Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
         steps_offset (`int`, defaults to 0):
-            An offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
-            Diffusion.
+            An offset added to the inference steps, as required by some model families.
         rescale_betas_zero_snr (`bool`, defaults to `False`):
             Whether to rescale the betas to have zero terminal SNR. This enables the model to generate very bright and
             dark samples instead of limiting it to samples with medium brightness. Loosely related to

src/diffusers/schedulers/scheduling_ddim.py

@@ -157,9 +157,7 @@ class DDIMScheduler(SchedulerMixin, ConfigMixin):
             there is no previous alpha. When this option is `True` the previous alpha product is fixed to `1`,
             otherwise it uses the alpha value at step 0.
         steps_offset (`int`, defaults to 0):
-            An offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
-            Diffusion.
+            An offset added to the inference steps, as required by some model families.
         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

src/diffusers/schedulers/scheduling_ddim_flax.py

@@ -93,9 +93,7 @@ class FlaxDDIMScheduler(FlaxSchedulerMixin, ConfigMixin):
             step there is no previous alpha. When this option is `True` the previous alpha product is fixed to `1`,
             otherwise it uses the value of alpha at step 0.
         steps_offset (`int`, default `0`):
-            an offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False`, to make the last step use step 0 for the previous alpha product, as done in
-            stable diffusion.
+            An offset added to the inference steps, as required by some model families.
         prediction_type (`str`, default `epsilon`):
             indicates whether the model predicts the noise (epsilon), or the samples. One of `epsilon`, `sample`.
             `v-prediction` is not supported for this scheduler.

src/diffusers/schedulers/scheduling_ddim_inverse.py

@@ -155,9 +155,7 @@ class DDIMInverseScheduler(SchedulerMixin, ConfigMixin):
             there is no previous alpha. When this option is `True` the previous alpha product is fixed to 0, otherwise
             it uses the alpha value at step `num_train_timesteps - 1`.
         steps_offset (`int`, defaults to 0):
-            An offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False` to make the last step use `num_train_timesteps - 1` for the previous alpha
-            product.
+            An offset added to the inference steps, as required by some model families.
         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

src/diffusers/schedulers/scheduling_ddim_parallel.py

@@ -159,9 +159,7 @@ class DDIMParallelScheduler(SchedulerMixin, ConfigMixin):
             step there is no previous alpha. When this option is `True` the previous alpha product is fixed to `1`,
             otherwise it uses the value of alpha at step 0.
         steps_offset (`int`, default `0`):
-            an offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False`, to make the last step use step 0 for the previous alpha product, as done in
-            stable diffusion.
+            An offset added to the inference steps, as required by some model families.
         prediction_type (`str`, default `epsilon`, optional):
             prediction type of the scheduler function, one of `epsilon` (predicting the noise of the diffusion
             process), `sample` (directly predicting the noisy sample`) or `v_prediction` (see section 2.4

src/diffusers/schedulers/scheduling_ddpm.py

@@ -167,9 +167,7 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
             The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
             Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
         steps_offset (`int`, defaults to 0):
-            An offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
-            Diffusion.
+            An offset added to the inference steps, as required by some model families.
         rescale_betas_zero_snr (`bool`, defaults to `False`):
             Whether to rescale the betas to have zero terminal SNR. This enables the model to generate very bright and
             dark samples instead of limiting it to samples with medium brightness. Loosely related to

src/diffusers/schedulers/scheduling_ddpm_parallel.py

@@ -173,9 +173,7 @@ class DDPMParallelScheduler(SchedulerMixin, ConfigMixin):
             The way the timesteps should be scaled. Refer to Table 2. of [Common Diffusion Noise Schedules and Sample
             Steps are Flawed](https://arxiv.org/abs/2305.08891) for more information.
         steps_offset (`int`, default `0`):
-            an offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False`, to make the last step use step 0 for the previous alpha product, as done in
-            stable diffusion.
+            An offset added to the inference steps, as required by some model families.
         rescale_betas_zero_snr (`bool`, defaults to `False`):
             Whether to rescale the betas to have zero terminal SNR. This enables the model to generate very bright and
             dark samples instead of limiting it to samples with medium brightness. Loosely related to

src/diffusers/schedulers/scheduling_deis_multistep.py

@@ -115,9 +115,7 @@ class DEISMultistepScheduler(SchedulerMixin, ConfigMixin):
             The way the timesteps should be scaled. Refer to Table 2 of the [Common Diffusion Noise Schedules and
             Sample Steps are Flawed](https://huggingface.co/papers/2305.08891) for more information.
         steps_offset (`int`, defaults to 0):
-            An offset added to the inference steps. You can use a combination of `offset=1` and
-            `set_alpha_to_one=False` to make the last step use step 0 for the previous alpha product like in Stable
-            Diffusion.
+            An offset added to the inference steps, as required by some model families.
     """
 
     _compatibles = [e.name for e in KarrasDiffusionSchedulers]