optimum/habana/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py [345:395]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            )

            self._guidance_scale = guidance_scale
            self._guidance_rescale = guidance_rescale
            self._clip_skip = clip_skip
            self._cross_attention_kwargs = cross_attention_kwargs
            self._denoising_end = denoising_end
            self._denoising_start = denoising_start
            self._interrupt = False

            # 2. Define call parameters
            if prompt is not None and isinstance(prompt, str):
                num_prompts = 1
            elif prompt is not None and isinstance(prompt, list):
                num_prompts = len(prompt)
            else:
                num_prompts = prompt_embeds.shape[0]
            num_batches = ceil((num_images_per_prompt * num_prompts) / batch_size)
            logger.info(
                f"{num_prompts} prompt(s) received, {num_images_per_prompt} generation(s) per prompt,"
                f" {batch_size} sample(s) per batch, {num_batches} total batch(es)."
            )
            if num_batches < 3:
                logger.warning("The first two iterations are slower so it is recommended to feed more batches.")

            device = self._execution_device

            # 3. Encode input prompt
            text_encoder_lora_scale = (
                self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
            )
            (
                prompt_embeds,
                negative_prompt_embeds,
                pooled_prompt_embeds,
                negative_pooled_prompt_embeds,
            ) = self.encode_prompt(
                prompt=prompt,
                prompt_2=prompt_2,
                device=device,
                num_images_per_prompt=num_images_per_prompt,
                do_classifier_free_guidance=self.do_classifier_free_guidance,
                negative_prompt=negative_prompt,
                negative_prompt_2=negative_prompt_2,
                prompt_embeds=prompt_embeds,
                negative_prompt_embeds=negative_prompt_embeds,
                pooled_prompt_embeds=pooled_prompt_embeds,
                negative_pooled_prompt_embeds=negative_pooled_prompt_embeds,
                lora_scale=text_encoder_lora_scale,
                clip_skip=self.clip_skip,
            )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



optimum/habana/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_inpaint.py [489:541]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            )

            self._guidance_scale = guidance_scale
            self._guidance_rescale = guidance_rescale
            self._clip_skip = clip_skip
            self._cross_attention_kwargs = cross_attention_kwargs
            self._denoising_end = denoising_end
            self._denoising_start = denoising_start
            self._interrupt = False

            # 2. Define call parameters
            if prompt is not None and isinstance(prompt, str):
                num_prompts = 1
            elif prompt is not None and isinstance(prompt, list):
                num_prompts = len(prompt)
            else:
                num_prompts = prompt_embeds.shape[0]

            num_batches = ceil((num_images_per_prompt * num_prompts) / batch_size)

            logger.info(
                f"{num_prompts} prompt(s) received, {num_images_per_prompt} generation(s) per prompt,"
                f" {batch_size} sample(s) per batch, {num_batches} total batch(es)."
            )
            if num_batches < 3:
                logger.warning("The first two iterations are slower so it is recommended to feed more batches.")

            device = self._execution_device
            # 3. Encode input prompt
            text_encoder_lora_scale = (
                self.cross_attention_kwargs.get("scale", None) if self.cross_attention_kwargs is not None else None
            )

            (
                prompt_embeds,
                negative_prompt_embeds,
                pooled_prompt_embeds,
                negative_pooled_prompt_embeds,
            ) = self.encode_prompt(
                prompt=prompt,
                prompt_2=prompt_2,
                device=device,
                num_images_per_prompt=num_images_per_prompt,
                do_classifier_free_guidance=self.do_classifier_free_guidance,
                negative_prompt=negative_prompt,
                negative_prompt_2=negative_prompt_2,
                prompt_embeds=prompt_embeds,
                negative_prompt_embeds=negative_prompt_embeds,
                pooled_prompt_embeds=pooled_prompt_embeds,
                negative_pooled_prompt_embeds=negative_pooled_prompt_embeds,
                lora_scale=text_encoder_lora_scale,
                clip_skip=self.clip_skip,
            )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -