Remove the redundant init_timestep parameter that was being passed around. It is simply the first element of the timesteps array.

invokeai/app/invocations/denoise_latents.py

@@ -625,7 +625,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
         t_start_idx *= scheduler.order
         t_end_idx *= scheduler.order
 
-        init_timestep = timesteps[t_start_idx : t_start_idx + 1]
         timesteps = timesteps[t_start_idx : t_start_idx + t_end_idx]
 
         scheduler_step_kwargs: Dict[str, Any] = {}
@@ -648,7 +647,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         if isinstance(scheduler, TCDScheduler):
             scheduler_step_kwargs.update({"eta": 1.0})
 
-        return timesteps, init_timestep, scheduler_step_kwargs
+        return timesteps, scheduler_step_kwargs
 
     def prep_inpaint_mask(
         self, context: InvocationContext, latents: torch.Tensor
@@ -814,7 +813,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 dtype=unet.dtype,
             )
 
-            timesteps, init_timestep, scheduler_step_kwargs = self.init_scheduler(
+            timesteps, scheduler_step_kwargs = self.init_scheduler(
                 scheduler,
                 device=unet.device,
                 steps=self.steps,
@@ -826,7 +825,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
             result_latents = pipeline.latents_from_embeddings(
                 latents=latents,
                 timesteps=timesteps,
-                init_timestep=init_timestep,
                 noise=noise,
                 seed=seed,
                 mask=mask,

invokeai/app/invocations/tiled_multi_diffusion_denoise_latents.py

@@ -234,7 +234,7 @@ class TiledMultiDiffusionDenoiseLatents(BaseInvocation):
                     )
                 )
 
-            timesteps, init_timestep, scheduler_step_kwargs = DenoiseLatentsInvocation.init_scheduler(
+            timesteps, scheduler_step_kwargs = DenoiseLatentsInvocation.init_scheduler(
                 scheduler,
                 device=unet.device,
                 steps=self.steps,
@@ -250,7 +250,6 @@ class TiledMultiDiffusionDenoiseLatents(BaseInvocation):
                 scheduler_step_kwargs=scheduler_step_kwargs,
                 noise=noise,
                 timesteps=timesteps,
-                init_timestep=init_timestep,
                 # TODO(ryand): Add proper callback.
                 callback=lambda x: None,
             )

invokeai/backend/stable_diffusion/diffusers_pipeline.py

@@ -273,7 +273,6 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         noise: Optional[torch.Tensor],
         seed: int,
         timesteps: torch.Tensor,
-        init_timestep: torch.Tensor,
         callback: Callable[[PipelineIntermediateState], None],
         control_data: list[ControlNetData] | None = None,
         ip_adapter_data: Optional[list[IPAdapterData]] = None,
@@ -299,9 +298,6 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
                 HACK(ryand): seed is only used in a particular case when `noise` is None, but we need to re-generate the
                 same noise used earlier in the pipeline. This should really be handled in a clearer way.
             timesteps: The timestep schedule for the denoising process.
-            init_timestep: The first timestep in the schedule.
-                TODO(ryand): I'm pretty sure this should always be the same as timesteps[0:1]. Confirm that that is the
-                case, and remove this duplicate param.
             callback: A callback function that is called to report progress during the denoising process.
             control_data: ControlNet data.
             ip_adapter_data: IP-Adapter data.
@@ -316,18 +312,17 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
                 SD UNet model.
             is_gradient_mask: A flag indicating whether `mask` is a gradient mask or not.
         """
-        # TODO(ryand): Figure out why this condition is necessary, and document it. My guess is that it's to handle
+        if timesteps.shape[0] == 0:
-        # cases where densoisings_start and denoising_end are set such that there are no timesteps.
-        if init_timestep.shape[0] == 0 or timesteps.shape[0] == 0:
             return latents
 
         orig_latents = latents.clone()
-
         batch_size = latents.shape[0]
-        batched_init_timestep = init_timestep.expand(batch_size)
 
         # noise can be None if the latents have already been noised (e.g. when running the SDXL refiner).
         if noise is not None:
+            # batched_init_timestep should have shape (batch_size, 1).
+            batched_init_timestep = timesteps[0:1].expand(batch_size)
+
             # TODO(ryand): I'm pretty sure we should be applying init_noise_sigma in cases where we are starting with
             # full noise. Investigate the history of why this got commented out.
             # latents = noise * self.scheduler.init_noise_sigma # it's like in t2l according to diffusers

invokeai/backend/stable_diffusion/multi_diffusion_pipeline.py

@@ -34,19 +34,18 @@ class MultiDiffusionPipeline(StableDiffusionGeneratorPipeline):
         scheduler_step_kwargs: dict[str, Any],
         noise: Optional[torch.Tensor],
         timesteps: torch.Tensor,
-        init_timestep: torch.Tensor,
         callback: Callable[[PipelineIntermediateState], None],
     ) -> torch.Tensor:
-        # TODO(ryand): Figure out why this condition is necessary, and document it. My guess is that it's to handle
+        if timesteps.shape[0] == 0:
-        # cases where densoisings_start and denoising_end are set such that there are no timesteps.
-        if init_timestep.shape[0] == 0 or timesteps.shape[0] == 0:
             return latents
 
         batch_size, _, latent_height, latent_width = latents.shape
-        batched_init_timestep = init_timestep.expand(batch_size)
 
         # noise can be None if the latents have already been noised (e.g. when running the SDXL refiner).
         if noise is not None:
+            # batched_init_timestep should have shape (batch_size, 1).
+            batched_init_timestep = timesteps[0:1].expand(batch_size)
+
             # TODO(ryand): I'm pretty sure we should be applying init_noise_sigma in cases where we are starting with
             # full noise. Investigate the history of why this got commented out.
             # latents = noise * self.scheduler.init_noise_sigma # it's like in t2l according to diffusers