finetune_instruct_pix2pix.py [1047:1078]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            progress_bar.set_postfix(**logs)

            if global_step >= args.max_train_steps:
                break

        if accelerator.is_main_process:
            if (
                (args.val_image_url is not None)
                and (args.validation_prompt is not None)
                and (epoch % args.validation_epochs == 0)
            ):
                logger.info(
                    f"Running validation... \n Generating {args.num_validation_images} images with prompt:"
                    f" {args.validation_prompt}."
                )
                # create pipeline
                if args.use_ema:
                    # Store the UNet parameters temporarily and load the EMA parameters to perform inference.
                    ema_unet.store(unet.parameters())
                    ema_unet.copy_to(unet.parameters())
                pipeline = StableDiffusionInstructPix2PixPipeline.from_pretrained(
                    args.pretrained_model_name_or_path,
                    unet=unet,
                    revision=args.revision,
                    torch_dtype=weight_dtype,
                )
                pipeline = pipeline.to(accelerator.device)
                pipeline.set_progress_bar_config(disable=True)

                # run inference
                original_image = download_image(args.val_image_url)
                edited_images = []
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



train_instruct_pix2pix.py [895:926]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            progress_bar.set_postfix(**logs)

            if global_step >= args.max_train_steps:
                break

        if accelerator.is_main_process:
            if (
                (args.val_image_url is not None)
                and (args.validation_prompt is not None)
                and (epoch % args.validation_epochs == 0)
            ):
                logger.info(
                    f"Running validation... \n Generating {args.num_validation_images} images with prompt:"
                    f" {args.validation_prompt}."
                )
                # create pipeline
                if args.use_ema:
                    # Store the UNet parameters temporarily and load the EMA parameters to perform inference.
                    ema_unet.store(unet.parameters())
                    ema_unet.copy_to(unet.parameters())
                pipeline = StableDiffusionInstructPix2PixPipeline.from_pretrained(
                    args.pretrained_model_name_or_path,
                    unet=unet,
                    revision=args.revision,
                    torch_dtype=weight_dtype,
                )
                pipeline = pipeline.to(accelerator.device)
                pipeline.set_progress_bar_config(disable=True)

                # run inference
                original_image = download_image(args.val_image_url)
                edited_images = []
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -