optimum/habana/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py [206:261]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            latents = latents.to(device)

        # scale the initial noise by the standard deviation required by the scheduler
        latents = latents * self.scheduler.init_noise_sigma
        return latents

    @classmethod
    def _split_inputs_into_batches(cls, batch_size, latents, prompt_embeds, negative_prompt_embeds):
        # Use torch.split to generate num_batches batches of size batch_size
        latents_batches = list(torch.split(latents, batch_size))
        prompt_embeds_batches = list(torch.split(prompt_embeds, batch_size))
        if negative_prompt_embeds is not None:
            negative_prompt_embeds_batches = list(torch.split(negative_prompt_embeds, batch_size))

        # If the last batch has less samples than batch_size, pad it with dummy samples
        num_dummy_samples = 0
        if latents_batches[-1].shape[0] < batch_size:
            num_dummy_samples = batch_size - latents_batches[-1].shape[0]
            # Pad latents_batches
            sequence_to_stack = (latents_batches[-1],) + tuple(
                torch.zeros_like(latents_batches[-1][0][None, :]) for _ in range(num_dummy_samples)
            )
            latents_batches[-1] = torch.vstack(sequence_to_stack)
            # Pad prompt_embeds_batches
            sequence_to_stack = (prompt_embeds_batches[-1],) + tuple(
                torch.zeros_like(prompt_embeds_batches[-1][0][None, :]) for _ in range(num_dummy_samples)
            )
            prompt_embeds_batches[-1] = torch.vstack(sequence_to_stack)
            # Pad negative_prompt_embeds_batches if necessary
            if negative_prompt_embeds is not None:
                sequence_to_stack = (negative_prompt_embeds_batches[-1],) + tuple(
                    torch.zeros_like(negative_prompt_embeds_batches[-1][0][None, :]) for _ in range(num_dummy_samples)
                )
                negative_prompt_embeds_batches[-1] = torch.vstack(sequence_to_stack)

        # Stack batches in the same tensor
        latents_batches = torch.stack(latents_batches)
        if negative_prompt_embeds is not None:
            # For classifier free guidance, we need to do two forward passes.
            # Here we concatenate the unconditional and text embeddings into a single batch
            # to avoid doing two forward passes
            for i, (negative_prompt_embeds_batch, prompt_embeds_batch) in enumerate(
                zip(negative_prompt_embeds_batches, prompt_embeds_batches[:])
            ):
                prompt_embeds_batches[i] = torch.cat([negative_prompt_embeds_batch, prompt_embeds_batch])

        prompt_embeds_batches = torch.stack(prompt_embeds_batches)

        return latents_batches, prompt_embeds_batches, num_dummy_samples

    @torch.no_grad()
    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        height: Optional[int] = None,
        width: Optional[int] = None,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/habana/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth.py [137:192]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            latents = latents.to(device)

        # scale the initial noise by the standard deviation required by the scheduler
        latents = latents * self.scheduler.init_noise_sigma
        return latents

    # Copied from optimum.habana.diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.GaudiStableDiffusionPipeline._split_inputs_into_batches
    @classmethod
    def _split_inputs_into_batches(cls, batch_size, latents, prompt_embeds, negative_prompt_embeds):
        # Use torch.split to generate num_batches batches of size batch_size
        latents_batches = list(torch.split(latents, batch_size))
        prompt_embeds_batches = list(torch.split(prompt_embeds, batch_size))
        if negative_prompt_embeds is not None:
            negative_prompt_embeds_batches = list(torch.split(negative_prompt_embeds, batch_size))

        # If the last batch has less samples than batch_size, pad it with dummy samples
        num_dummy_samples = 0
        if latents_batches[-1].shape[0] < batch_size:
            num_dummy_samples = batch_size - latents_batches[-1].shape[0]
            # Pad latents_batches
            sequence_to_stack = (latents_batches[-1],) + tuple(
                torch.zeros_like(latents_batches[-1][0][None, :]) for _ in range(num_dummy_samples)
            )
            latents_batches[-1] = torch.vstack(sequence_to_stack)
            # Pad prompt_embeds_batches
            sequence_to_stack = (prompt_embeds_batches[-1],) + tuple(
                torch.zeros_like(prompt_embeds_batches[-1][0][None, :]) for _ in range(num_dummy_samples)
            )
            prompt_embeds_batches[-1] = torch.vstack(sequence_to_stack)
            # Pad negative_prompt_embeds_batches if necessary
            if negative_prompt_embeds is not None:
                sequence_to_stack = (negative_prompt_embeds_batches[-1],) + tuple(
                    torch.zeros_like(negative_prompt_embeds_batches[-1][0][None, :]) for _ in range(num_dummy_samples)
                )
                negative_prompt_embeds_batches[-1] = torch.vstack(sequence_to_stack)

        # Stack batches in the same tensor
        latents_batches = torch.stack(latents_batches)
        if negative_prompt_embeds is not None:
            # For classifier free guidance, we need to do two forward passes.
            # Here we concatenate the unconditional and text embeddings into a single batch
            # to avoid doing two forward passes
            for i, (negative_prompt_embeds_batch, prompt_embeds_batch) in enumerate(
                zip(negative_prompt_embeds_batches, prompt_embeds_batches[:])
            ):
                prompt_embeds_batches[i] = torch.cat([negative_prompt_embeds_batch, prompt_embeds_batch])
        prompt_embeds_batches = torch.stack(prompt_embeds_batches)

        return latents_batches, prompt_embeds_batches, num_dummy_samples

    @torch.no_grad()
    def __call__(
        self,
        prompt: Union[str, List[str]] = None,
        height: Optional[int] = None,
        width: Optional[int] = None,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -