optimum/habana/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py [671:719]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            )

    @torch.no_grad()
    def unet_hpu(
        self,
        latent_model_input,
        timestep,
        encoder_hidden_states,
        timestep_cond,
        cross_attention_kwargs,
        added_cond_kwargs,
    ):
        if self.use_hpu_graphs:
            return self.capture_replay(
                latent_model_input,
                timestep,
                encoder_hidden_states,
                timestep_cond,
                cross_attention_kwargs,
                added_cond_kwargs,
            )
        else:
            return self.unet(
                latent_model_input,
                timestep,
                encoder_hidden_states=encoder_hidden_states,
                timestep_cond=timestep_cond,
                cross_attention_kwargs=cross_attention_kwargs,
                added_cond_kwargs=added_cond_kwargs,
                return_dict=False,
            )[0]

    @torch.no_grad()
    def capture_replay(
        self,
        latent_model_input,
        timestep,
        encoder_hidden_states,
        timestep_cond,
        cross_attention_kwargs,
        added_cond_kwargs,
    ):
        inputs = [
            latent_model_input,
            timestep,
            encoder_hidden_states,
            timestep_cond,
            cross_attention_kwargs,
            added_cond_kwargs,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/habana/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py [722:770]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            )

    @torch.no_grad()
    def unet_hpu(
        self,
        latent_model_input,
        timestep,
        encoder_hidden_states,
        timestep_cond,
        cross_attention_kwargs,
        added_cond_kwargs,
    ):
        if self.use_hpu_graphs:
            return self.capture_replay(
                latent_model_input,
                timestep,
                encoder_hidden_states,
                timestep_cond,
                cross_attention_kwargs,
                added_cond_kwargs,
            )
        else:
            return self.unet(
                latent_model_input,
                timestep,
                encoder_hidden_states=encoder_hidden_states,
                timestep_cond=timestep_cond,
                cross_attention_kwargs=cross_attention_kwargs,
                added_cond_kwargs=added_cond_kwargs,
                return_dict=False,
            )[0]

    @torch.no_grad()
    def capture_replay(
        self,
        latent_model_input,
        timestep,
        encoder_hidden_states,
        timestep_cond,
        cross_attention_kwargs,
        added_cond_kwargs,
    ):
        inputs = [
            latent_model_input,
            timestep,
            encoder_hidden_states,
            timestep_cond,
            cross_attention_kwargs,
            added_cond_kwargs,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -