optimum/habana/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py [613:673]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                start_time_after_warmup=t1,
            )
            logger.info(f"Speed metrics: {speed_measures}")

            # Remove dummy generations if needed
            if num_dummy_samples > 0:
                outputs["images"][-1] = outputs["images"][-1][:-num_dummy_samples]

            # Process generated images
            for i, image in enumerate(outputs["images"][:]):
                if i == 0:
                    outputs["images"].clear()

                if output_type == "latent":
                    has_nsfw_concept = None
                else:
                    image, has_nsfw_concept = self.run_safety_checker(image, device, prompt_embeds.dtype)

                if has_nsfw_concept is None:
                    do_denormalize = [True] * image.shape[0]
                else:
                    do_denormalize = [not has_nsfw for has_nsfw in has_nsfw_concept]

                image = self.image_processor.postprocess(image, output_type=output_type, do_denormalize=do_denormalize)

                if output_type == "pil" and isinstance(image, list):
                    outputs["images"] += image
                elif output_type in ["np", "numpy"] and isinstance(image, np.ndarray):
                    if len(outputs["images"]) == 0:
                        outputs["images"] = image
                    else:
                        outputs["images"] = np.concatenate((outputs["images"], image), axis=0)
                else:
                    if len(outputs["images"]) == 0:
                        outputs["images"] = image
                    else:
                        outputs["images"] = torch.cat((outputs["images"], image), 0)

                if has_nsfw_concept is not None:
                    outputs["has_nsfw_concept"] += has_nsfw_concept
                else:
                    outputs["has_nsfw_concept"] = None

            # Offload all models
            self.maybe_free_model_hooks()

            if not return_dict:
                return (outputs["images"], outputs["has_nsfw_concept"])

            return GaudiStableDiffusionPipelineOutput(
                images=outputs["images"],
                nsfw_content_detected=outputs["has_nsfw_concept"],
                throughput=speed_measures[f"{speed_metrics_prefix}_samples_per_second"],
            )

    @torch.no_grad()
    def unet_hpu(
        self,
        latent_model_input,
        timestep,
        encoder_hidden_states,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/habana/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_instruct_pix2pix.py [503:561]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                start_time_after_warmup=t1,
            )
            logger.info(f"Speed metrics: {speed_measures}")
            # Remove dummy generations if needed
            if num_dummy_samples > 0:
                outputs["images"][-1] = outputs["images"][-1][:-num_dummy_samples]

            # Process generated images
            for i, image in enumerate(outputs["images"][:]):
                if i == 0:
                    outputs["images"].clear()

                if output_type == "latent":
                    has_nsfw_concept = None
                else:
                    image, has_nsfw_concept = self.run_safety_checker(image, device, prompt_embeds.dtype)

                if has_nsfw_concept is None:
                    do_denormalize = [True] * image.shape[0]
                else:
                    do_denormalize = [not has_nsfw for has_nsfw in has_nsfw_concept]

                image = self.image_processor.postprocess(image, output_type=output_type, do_denormalize=do_denormalize)

                if output_type == "pil" and isinstance(image, list):
                    outputs["images"] += image
                elif output_type in ["np", "numpy"] and isinstance(image, np.ndarray):
                    if len(outputs["images"]) == 0:
                        outputs["images"] = image
                    else:
                        outputs["images"] = np.concatenate((outputs["images"], image), axis=0)
                else:
                    if len(outputs["images"]) == 0:
                        outputs["images"] = image
                    else:
                        outputs["images"] = torch.cat((outputs["images"], image), 0)

                if has_nsfw_concept is not None:
                    outputs["has_nsfw_concept"] += has_nsfw_concept
                else:
                    outputs["has_nsfw_concept"] = None

            self.maybe_free_model_hooks()

            if not return_dict:
                return (outputs["images"], outputs["has_nsfw_concept"])

            return GaudiStableDiffusionPipelineOutput(
                images=outputs["images"],
                nsfw_content_detected=outputs["has_nsfw_concept"],
                throughput=speed_measures[f"{speed_metrics_prefix}_samples_per_second"],
            )

    @torch.no_grad()
    def unet_hpu(
        self,
        latent_model_input,
        timestep,
        encoder_hidden_states,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -