Apply suggestions from code review

Co-authored-by: Aryan <[email protected]>

Author: yiyixuxu

src/diffusers/models/transformers/sana_transformer.py

@@ -97,12 +97,6 @@ def forward(
 
 
 class SanaCombinedTimestepGuidanceEmbeddings(nn.Module):
-    """
-    For Sana.
-
-    Reference:
-    """
-
     def __init__(self, embedding_dim):
         super().__init__()
         self.time_proj = Timesteps(num_channels=256, flip_sin_to_cos=True, downscale_freq_shift=0)

src/diffusers/pipelines/sana/pipeline_sana_sprint.py

@@ -394,24 +394,6 @@ def encode_prompt(
 
         return prompt_embeds, prompt_attention_mask
 
-    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
-    def prepare_extra_step_kwargs(self, generator, eta):
-        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
-        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
-        # and should be between [0, 1]
-
-        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        extra_step_kwargs = {}
-        if accepts_eta:
-            extra_step_kwargs["eta"] = eta
-
-        # check if the scheduler accepts generator
-        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
-        if accepts_generator:
-            extra_step_kwargs["generator"] = generator
-        return extra_step_kwargs
-
     def check_inputs(
         self,
         prompt,
@@ -853,9 +835,6 @@ def __call__(
         guidance = guidance.expand(latents.shape[0]).to(prompt_embeds.dtype)
         guidance = guidance * self.transformer.config.guidance_embeds_scale
 
-        # 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
-        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
-
         # YiYi TODO: refactor this
         timesteps = timesteps[:-1]
 

src/diffusers/schedulers/scheduling_scm.py

@@ -59,10 +59,6 @@ class SCMScheduler(SchedulerMixin, ConfigMixin):
             The number of diffusion steps to train the model.
         prediction_type (`str`, defaults to `trigflow`):
             Prediction type of the scheduler function. Currently only supports "trigflow".
-        max_timesteps (`float`, defaults to 1.57080):
-            The maximum timestep value used in the diffusion process.
-        intermediate_timesteps (`float`, *optional*, defaults to 1.3):
-            The intermediate timestep value used when num_inference_steps=2.
         sigma_data (`float`, defaults to 0.5):
             The standard deviation of the noise added during multi-step inference.
     """
@@ -220,9 +216,7 @@ def step(
             sample (`torch.FloatTensor`):
                 A current instance of a sample created by the diffusion process.
             return_dict (`bool`, *optional*, defaults to `True`):
-                itself. Useful for methods such as [`CycleDiffusion`].
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`~schedulers.scheduling_lcm.LCMSchedulerOutput`] or `tuple`.
+                Whether or not to return a [`~schedulers.scheduling_scm.SCMSchedulerOutput`] or `tuple`.
         Returns:
             [`~schedulers.scheduling_utils.SCMSchedulerOutput`] or `tuple`:
                 If return_dict is `True`, [`~schedulers.scheduling_scm.SCMSchedulerOutput`] is returned, otherwise a