[Issue]: Rendering 512x768 with 2x upscale creates 1024x1538 images instead of 1024x1536 images.

Issue Description

Rendering 512x768 with 2x upscale creates 1024x1538 images instead of 1024x1536 images.
Reproduce:
SD 1.5 image with 512x768
Set upscale to x2
Render image
Inspect the rendered image, it is 512x769 ratio and resulting image 2 pixels too high
This basically invalidates all my image for future use in SDNext where you need images whose ratio needs to be divisible by 64/128/256/whatever.
Version Platform Description

WSL-2, Win11, SDNext 1b6ebd9
Relevant log output

11:02:11-394647 TRACE    Control exec pipeline: task=DiffusersTaskType.TEXT_2_IMAGE class=<class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'>
11:02:11-395343 TRACE    Process images: {'outpath_samples': '/home/tillerz/images', 'outpath_grids': '/home/tillerz/images', 'prompt': 'steampunk girl, portrait by ross tran and jeremy
                         mann 4 k artstation trending dramatic lighting modernism photo realistic hd painting in the style of alexander mcqueen, dark and moody, foggy background with
                         lightning storm and rain. unreal engine 5 highly rendered render vfx, cinema4 d cinematic octane rendered scene illustration, sharp focus, masterpiece, global
                         illumination ray tracing shadows and smoke out at a window looking in the distance on the city below is 8 0 mm realistic film still from blade runner 2 0 9 7 9 1
                         6 sitting deep focus, fantasy character photography movie still frame, intricate details, extremely detailed, 8 k resolution, digital painting - n 3 - i robot
                         android walking in cyberpunk 20 <lora:watercolorV1:0.4>', 'prompt_for_display': None, 'negative_prompt': 'child, loli, anime, manga, necklace, disney, unreal
                         engine, octane render', 'styles': [], 'seed': -1.0, 'subseed': -1.0, 'subseed_strength': 0, 'seed_resize_from_h': 0, 'seed_resize_from_w': 0, 'sampler_name':
                         'DPM++ 2M', 'hr_sampler_name': 'Same as primary', 'batch_size': 1, 'n_iter': 1, 'steps': 30, 'hr_second_pass_steps': 20, 'cfg_scale': 3.5, 'scale_by': 1,
                         'image_cfg_scale': 3, 'diffusers_guidance_rescale': 0.7, 'pag_scale': 0, 'pag_adaptive': 0.5, 'cfg_end': 1, 'width': 512, 'height': 768, 'full_quality': True,
                         'restore_faces': False, 'tiling': False, 'hidiffusion': True, 'do_not_save_samples': False, 'do_not_save_grid': False, 'extra_generation_params': {},
                         'overlay_images': None, 'eta': None, 'do_not_reload_embeddings': False, 'paste_to': None, 'color_corrections': None, 'denoising_strength': 0.8,
                         'override_settings': {}, 'override_settings_restore_afterwards': True, 'is_using_inpainting_conditioning': False, 'disable_extra_networks': False,
                         'per_script_args': {}, 'all_prompts': None, 'all_negative_prompts': None, 'all_seeds': None, 'all_subseeds': None, 'clip_skip': 1, 'iteration': 0, 'is_control':
                         False, 'is_hr_pass': False, 'is_refiner_pass': False, 'hr_force': True, 'enable_hr': True, 'hr_scale': 2, 'hr_upscaler': 'ESRGAN 4x Remacri', 'hr_resize_x': 0,
                         'hr_resize_y': 0, 'hr_upscale_to_x': 1024, 'hr_upscale_to_y': 1536, 'truncate_x': 0, 'truncate_y': 0, 'applied_old_hires_behavior_to': None, 'refiner_steps': 10,
                         'refiner_start': 0, 'refiner_prompt': '', 'refiner_negative': '', 'ops': [], 'resize_mode': 1, 'resize_name': 'ESRGAN 4x Remacri', 'ddim_discretize': 'uniform',
                         's_min_uncond': 0.0, 's_churn': 0.0, 's_noise': 1.0, 's_min': 0.0, 's_max': 0.0, 's_tmin': 0.0, 's_tmax': inf, 'task_args': {}, 'batch_index': 0,
                         'refiner_switch_at': 0, 'hr_prompt': '', 'all_hr_prompts': [], 'hr_negative_prompt': '', 'all_hr_negative_prompts': [], 'comments': {}, 'is_api': False,
                         'scripts_value': <modules.scripts.ScriptRunner object at 0x7f0ff6b6a200>, 'script_args_value': (0, 1, 'None', 'None', 'None', 'None', 0.5, 0.5, 0.5, 0.5, None,
                         None, None, None, False, False, False, False, 0, 0, 0, 0, 1, 1, 1, 1, None, None, None, None, False, '', 'None', 16, 'None', 1, True, 'None', 2, True, 1, 0,
                         True, 'none', 3, 4, 0.25, 0.25, False, False, {'ad_model': 'face_yolov8n.pt', 'ad_model_classes': '', 'ad_tab_enable': True, 'ad_prompt': '',
                         'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0.0, 'ad_mask_max_ratio': 1.0, 'ad_x_offset': 0, 'ad_y_offset': 0,
                         'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True,
                         'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps':
                         28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7.0, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same
                         VAE', 'ad_use_sampler': False, 'ad_sampler': 'Default', 'ad_scheduler': 'Use same scheduler', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1.0,
                         'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight':
                         1.0, 'ad_controlnet_guidance_start': 0.0, 'ad_controlnet_guidance_end': 1.0}, {'ad_model': 'None', 'ad_model_classes': '', 'ad_tab_enable': True, 'ad_prompt':
                         '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0.0, 'ad_mask_max_ratio': 1.0, 'ad_x_offset': 0, 'ad_y_offset':
                         0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True,
                         'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps':
                         28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7.0, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same
                         VAE', 'ad_use_sampler': False, 'ad_sampler': 'Default', 'ad_scheduler': 'Use same scheduler', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1.0,
                         'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'None', 'ad_controlnet_weight':
                         1.0, 'ad_controlnet_guidance_start': 0.0, 'ad_controlnet_guidance_end': 1.0}, '', '', 0.5, 3, 1, 1, 0.8, 8, 64, True, True, 1, False, 'None', None, 'None', 16,
                         'None', 2, True, 1, 0, 'none', 3, 4, 0.25, 0.25, 0.5, 0.5, True, 0.5, 600.0, 1.0, 0.1, 1, True, '', 0.5, 0.9, '', 0.5, 0.9, 4, 0.5, 'Linear', 'None', 1, 1, 0.5,
                         0.5, 'OpenGVLab/InternVL-14B-224px', False, False, 'positive', 'comma', 0, False, False, '', 'None', '', 1, '', 'None', 1, '<span>&nbsp SD Upscale</span><br>',
                         64, 0, 2, 'SVD 1.0', 14, True, 1, 3, 6, 0.5, 0.1, 'None', 2, True, 1, 0, True, 10, 'None', True, 0, 'None', 2, True, 1, 0, 0, '', [], 0, '', [], 0, '', [],
                         False, True, False, False, False, False, 0, 'None', [], 'FaceID Base', True, True, 1, 1, 1, 0.5, True, 'person', 1, 0.5, True), 'scripts_setup_complete':
                         Field(name=None,type=None,default=False,default_factory=<dataclasses._MISSING_TYPE object at
                         0x7f1129b5a230>,init=False,repr=True,hash=None,compare=True,metadata=mappingproxy({}),kw_only=<dataclasses._MISSING_TYPE object at
                         0x7f1129b5a230>,_field_type=None), 'ip_adapter_names': [], 'ip_adapter_scales': [0.0], 'ip_adapter_images': [], 'ip_adapter_starts': [0.0], 'ip_adapter_ends':
                         [1.0], 'ip_adapter_crops': [], 'hdr_mode': 0, 'hdr_brightness': 0, 'hdr_color': 0, 'hdr_sharpen': 0, 'hdr_clamp': False, 'hdr_boundary': 4, 'hdr_threshold':
                         0.95, 'hdr_maximize': False, 'hdr_max_center': 0.6, 'hdr_max_boundry': 1, 'hdr_color_picker': '#000000', 'hdr_tint_ratio': 0, 'scheduled_prompt': False,
                         'prompt_embeds': [], 'positive_pooleds': [], 'negative_embeds': [], 'negative_pooleds': [], 'hr_denoising_strength': 0.3, 'init_latent': None, 'image_mask':
                         None, 'latent_mask': None, 'mask_for_overlay': None, 'mask_blur_x': 4, 'mask_blur_y': 4, 'mask_blur': 4, 'inpainting_fill': 1, 'inpaint_full_res': False,
                         'inpaint_full_res_padding': 0, 'inpainting_mask_invert': 0, 'initial_noise_multiplier': 1.0, 'mask': None, 'nmask': None, 'image_conditioning': None, 'is_batch':
                         False, 'sampler': None, 'strength': 1.0, 'adapter_conditioning_scale': None, 'adapter_conditioning_factor': 1.0, 'guess_mode': None,
                         'controlnet_conditioning_scale': None, 'control_guidance_start': None, 'control_guidance_end': None, 'reference_attn': None, 'reference_adain': None,
                         'attention_auto_machine_weight': None, 'gn_auto_machine_weight': None, 'style_fidelity': None, 'ref_image': None, 'image': None, 'query_weight': None,
                         'adain_weight': None, 'attention': 'Attention', 'fidelity': 0.5, 'mask_image': None, 'override': None, 'resize_mode_before': 1, 'resize_name_before': 'ESRGAN 4x
                         Remacri', 'width_before': 512, 'height_before': 768, 'scale_by_before': 1, 'selected_scale_tab_before': 0, 'resize_mode_after': 1, 'resize_name_after': 'ESRGAN
                         4x Remacri', 'width_after': 1024, 'height_after': 1538, 'scale_by_after': 1, 'selected_scale_tab_after': 0, 'resize_mode_mask': 1, 'resize_name_mask': 'ESRGAN 4x
                         Remacri', 'width_mask': 1024, 'height_mask': 1538, 'scale_by_mask': 1, 'selected_scale_tab_mask': 0}
11:02:11-407452 INFO     Applying ToDo: ratio=0.5
11:02:11-408344 INFO     Applying free-u: b1=1.2 b2=1.4 s1=0.9 s2=0.2
11:02:11-409324 TRACE    Processing inner: args={'outpath_samples': '/home/tillerz/images', 'outpath_grids': '/home/tillerz/images', 'prompt': 'steampunk girl, portrait by ross tran and
                         jeremy mann 4 k artstation trending dramatic lighting modernism photo realistic hd painting in the style of alexander mcqueen, dark and moody, foggy background
                         with lightning storm and rain. unreal engine 5 highly rendered render vfx, cinema4 d cinematic octane rendered scene illustration, sharp focus, masterpiece,
                         global illumination ray tracing shadows and smoke out at a window looking in the distance on the city below is 8 0 mm realistic film still from blade runner 2 0
                         9 7 9 1 6 sitting deep focus, fantasy character photography movie still frame, intricate details, extremely detailed, 8 k resolution, digital painting - n 3 - i
                         robot android walking in cyberpunk 20 <lora:watercolorV1:0.4>', 'prompt_for_display': None, 'negative_prompt': 'child, loli, anime, manga, necklace, disney,
                         unreal engine, octane render', 'styles': [], 'seed': -1.0, 'subseed': -1.0, 'subseed_strength': 0, 'seed_resize_from_h': 0, 'seed_resize_from_w': 0,
                         'sampler_name': 'DPM++ 2M', 'hr_sampler_name': 'Same as primary', 'batch_size': 1, 'n_iter': 1, 'steps': 30, 'hr_second_pass_steps': 20, 'cfg_scale': 3.5,
                         'scale_by': 1, 'image_cfg_scale': 3, 'diffusers_guidance_rescale': 0.7, 'pag_scale': 0, 'pag_adaptive': 0.5, 'cfg_end': 1, 'width': 512, 'height': 768,
                         'full_quality': True, 'restore_faces': False, 'tiling': False, 'hidiffusion': True, 'do_not_save_samples': False, 'do_not_save_grid': False,
                         'extra_generation_params': {'FreeU': 'b1=1.2 b2=1.4 s1=0.9 s2=0.2'}, 'overlay_images': None, 'eta': None, 'do_not_reload_embeddings': False, 'paste_to': None,
                         'color_corrections': [], 'denoising_strength': 0.8, 'override_settings': {}, 'override_settings_restore_afterwards': True, 'is_using_inpainting_conditioning':
                         False, 'disable_extra_networks': False, 'per_script_args': {}, 'all_prompts': ['steampunk girl, portrait by ross tran and jeremy mann 4 k artstation trending
                         dramatic lighting modernism photo realistic hd painting in the style of alexander mcqueen, dark and moody, foggy background with lightning storm and rain. unreal
                         engine 5 highly rendered render vfx, cinema4 d cinematic octane rendered scene illustration, sharp focus, masterpiece, global illumination ray tracing shadows
                         and smoke out at a window looking in the distance on the city below is 8 0 mm realistic film still from blade runner 2 0 9 7 9 1 6 sitting deep focus, fantasy
                         character photography movie still frame, intricate details, extremely detailed, 8 k resolution, digital painting - n 3 - i robot android walking in cyberpunk 20
                         <lora:watercolorV1:0.4>'], 'all_negative_prompts': ['child, loli, anime, manga, necklace, disney, unreal engine, octane render'], 'all_seeds': [3026283561],
                         'all_subseeds': [2179265473], 'clip_skip': 1, 'iteration': 0, 'is_control': False, 'is_hr_pass': False, 'is_refiner_pass': False, 'hr_force': True, 'enable_hr':
                         True, 'hr_scale': 2, 'hr_upscaler': 'ESRGAN 4x Remacri', 'hr_resize_x': 0, 'hr_resize_y': 0, 'hr_upscale_to_x': 1024, 'hr_upscale_to_y': 1536, 'truncate_x': 0,
                         'truncate_y': 0, 'applied_old_hires_behavior_to': None, 'refiner_steps': 10, 'refiner_start': 0, 'refiner_prompt': '', 'refiner_negative': '', 'ops': [],
                         'resize_mode': 1, 'resize_name': 'ESRGAN 4x Remacri', 'ddim_discretize': 'uniform', 's_min_uncond': 0.0, 's_churn': 0.0, 's_noise': 1.0, 's_min': 0.0, 's_max':
                         0.0, 's_tmin': 0.0, 's_tmax': inf, 'task_args': {}, 'batch_index': 0, 'refiner_switch_at': 0, 'hr_prompt': '', 'all_hr_prompts': [], 'hr_negative_prompt': '',
                         'all_hr_negative_prompts': [], 'comments': {}, 'is_api': False, 'scripts_value': <modules.scripts.ScriptRunner object at 0x7f0ff6b6a200>, 'script_args_value':
                         (0, 1, 'None', 'None', 'None', 'None', 0.5, 0.5, 0.5, 0.5, None, None, None, None, False, False, False, False, 0, 0, 0, 0, 1, 1, 1, 1, None, None, None, None,
                         False, '', 'None', 16, 'None', 1, True, 'None', 2, True, 1, 0, True, 'none', 3, 4, 0.25, 0.25, False, False, {'ad_model': 'face_yolov8n.pt', 'ad_model_classes':
                         '', 'ad_tab_enable': True, 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0.0,
                         'ad_mask_max_ratio': 1.0, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength':
                         0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height':
                         512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7.0, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint',
                         'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'Default', 'ad_scheduler': 'Use same scheduler', 'ad_use_noise_multiplier':
                         False, 'ad_noise_multiplier': 1.0, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module':
                         'None', 'ad_controlnet_weight': 1.0, 'ad_controlnet_guidance_start': 0.0, 'ad_controlnet_guidance_end': 1.0}, {'ad_model': 'None', 'ad_model_classes': '',
                         'ad_tab_enable': True, 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0.0, 'ad_mask_max_ratio':
                         1.0, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4,
                         'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512,
                         'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7.0, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint',
                         'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'Default', 'ad_scheduler': 'Use same scheduler', 'ad_use_noise_multiplier':
                         False, 'ad_noise_multiplier': 1.0, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module':
                         'None', 'ad_controlnet_weight': 1.0, 'ad_controlnet_guidance_start': 0.0, 'ad_controlnet_guidance_end': 1.0}, '', '', 0.5, 3, 1, 1, 0.8, 8, 64, True, True, 1,
                         False, 'None', None, 'None', 16, 'None', 2, True, 1, 0, 'none', 3, 4, 0.25, 0.25, 0.5, 0.5, True, 0.5, 600.0, 1.0, 0.1, 1, True, '', 0.5, 0.9, '', 0.5, 0.9, 4,
                         0.5, 'Linear', 'None', 1, 1, 0.5, 0.5, 'OpenGVLab/InternVL-14B-224px', False, False, 'positive', 'comma', 0, False, False, '', 'None', '', 1, '', 'None', 1,
                         '<span>&nbsp SD Upscale</span><br>', 64, 0, 2, 'SVD 1.0', 14, True, 1, 3, 6, 0.5, 0.1, 'None', 2, True, 1, 0, True, 10, 'None', True, 0, 'None', 2, True, 1, 0,
                         0, '', [], 0, '', [], 0, '', [], False, True, False, False, False, False, 0, 'None', [], 'FaceID Base', True, True, 1, 1, 1, 0.5, True, 'person', 1, 0.5, True),
                         'scripts_setup_complete': Field(name=None,type=None,default=False,default_factory=<dataclasses._MISSING_TYPE object at
                         0x7f1129b5a230>,init=False,repr=True,hash=None,compare=True,metadata=mappingproxy({}),kw_only=<dataclasses._MISSING_TYPE object at
                         0x7f1129b5a230>,_field_type=None), 'ip_adapter_names': ['None'], 'ip_adapter_scales': [0.5], 'ip_adapter_images': [None], 'ip_adapter_starts': [0],
                         'ip_adapter_ends': [1], 'ip_adapter_crops': [False], 'hdr_mode': 0, 'hdr_brightness': 0, 'hdr_color': 0, 'hdr_sharpen': 0, 'hdr_clamp': False, 'hdr_boundary': 4,
                         'hdr_threshold': 0.95, 'hdr_maximize': False, 'hdr_max_center': 0.6, 'hdr_max_boundry': 1, 'hdr_color_picker': '#000000', 'hdr_tint_ratio': 0,
                         'scheduled_prompt': False, 'prompt_embeds': [], 'positive_pooleds': [], 'negative_embeds': [], 'negative_pooleds': [], 'hr_denoising_strength': 0.3,
                         'init_latent': None, 'image_mask': None, 'latent_mask': None, 'mask_for_overlay': None, 'mask_blur_x': 4, 'mask_blur_y': 4, 'mask_blur': 4, 'inpainting_fill': 1,
                         'inpaint_full_res': False, 'inpaint_full_res_padding': 0, 'inpainting_mask_invert': 0, 'initial_noise_multiplier': 1.0, 'mask': None, 'nmask': None,
                         'image_conditioning': None, 'is_batch': False, 'sampler': None, 'strength': 1.0, 'adapter_conditioning_scale': None, 'adapter_conditioning_factor': 1.0,
                         'guess_mode': None, 'controlnet_conditioning_scale': None, 'control_guidance_start': None, 'control_guidance_end': None, 'reference_attn': None,
                         'reference_adain': None, 'attention_auto_machine_weight': None, 'gn_auto_machine_weight': None, 'style_fidelity': None, 'ref_image': None, 'image': None,
                         'query_weight': None, 'adain_weight': None, 'attention': 'Attention', 'fidelity': 0.5, 'mask_image': None, 'override': None, 'resize_mode_before': 1,
                         'resize_name_before': 'ESRGAN 4x Remacri', 'width_before': 512, 'height_before': 768, 'scale_by_before': 1, 'selected_scale_tab_before': 0, 'resize_mode_after':
                         1, 'resize_name_after': 'ESRGAN 4x Remacri', 'width_after': 1024, 'height_after': 1538, 'scale_by_after': 1, 'selected_scale_tab_after': 0, 'resize_mode_mask':
                         1, 'resize_name_mask': 'ESRGAN 4x Remacri', 'width_mask': 1024, 'height_mask': 1538, 'scale_by_mask': 1, 'selected_scale_tab_mask': 0, 'ip_adapter_masks': [],
                         '_ad_disabled': True}
11:02:11-419407 TRACE    Processing inner: iteration=1/1
Loading model: /home/tillerz/models/Lora/FAVES/watercolorV1.safetensors ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/151.1 MB -:--:--
11:02:12-320966 INFO     LoRA apply: ['watercolorV1'] patch=0.00 load=0.90
11:02:12-325839 INFO     Base: class=StableDiffusionPipeline
11:02:12-327140 DEBUG    Sampler: sampler="DPM++ 2M" config={'num_train_timesteps': 1000, 'beta_start': 0.00085, 'beta_end': 0.012, 'beta_schedule': 'scaled_linear', 'prediction_type':
                         'epsilon', 'thresholding': False, 'sample_max_value': 1.0, 'algorithm_type': 'sde-dpmsolver++', 'solver_type': 'midpoint', 'lower_order_final': True,
                         'use_karras_sigmas': False, 'final_sigmas_type': 'zero', 'timestep_spacing': 'leading', 'solver_order': 2}
11:02:12-328472 DEBUG    Sampler: steps=10 timesteps=[999, 850, 736, 645, 545, 455, 343, 233, 124, 24]
11:02:12-591129 DEBUG    Torch generator: device=cuda seeds=[3026283561]
11:02:12-592002 DEBUG    Diffuser pipeline: StableDiffusionPipeline task=DiffusersTaskType.TEXT_2_IMAGE batch=1/1x1 set={'timesteps': [999, 850, 736, 645, 545, 455, 343, 233, 124, 24],
                         'prompt_embeds': torch.Size([1, 154, 768]), 'negative_prompt_embeds': torch.Size([1, 154, 768]), 'guidance_scale': 3.5, 'num_inference_steps': 30, 'eta': 1.0,
                         'guidance_rescale': 0.7, 'output_type': 'latent', 'width': 512, 'height': 768, 'parser': 'Full parser'}
11:02:12-623740 DEBUG    HiDiffusion apply: raunet=True attn=True aggressive=True:8 t1=0.2 t2=0.1 time=0.00 type=sd width=512 height=768
Progress  1.58it/s ██████▊                             20% 2/10 00:01 00:05 Base11:02:14-210866 DEBUG    VAE load: type=taesd model=/home/tillerz/models/TAESD/taesd_decoder.pth

Progress  4.18it/s █████████████████████████████████ 100% 10/10 00:02 00:00 Base
11:02:15-402808 DEBUG    Control hires: upscaler="ESRGAN 4x Remacri" upscale=2 size=1024x1536
11:02:15-404082 INFO     Upscale: upscaler="ESRGAN 4x Remacri" resize=0x0 upscale=1024x1536
11:02:17-688023 INFO     Upscaler loaded: type=ESRGAN model=/home/tillerz/models/ESRGAN/ESRGAN-Remacri-4x.pth
Upscaling ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00 0:00:01
11:02:19-647317 DEBUG    Pipeline class change: original=StableDiffusionPipeline target=StableDiffusionImg2ImgPipeline device=cuda:0 fn=process_diffusers
11:02:19-648218 INFO     HiRes: class=StableDiffusionImg2ImgPipeline sampler="Same as primary"
11:02:19-650431 DEBUG    Sampler: steps=10 timesteps=[999, 850, 736, 645, 545, 455, 343, 233, 124, 24]
11:02:19-651309 DEBUG    Torch generator: device=cuda seeds=[3026283561]
11:02:19-651884 DEBUG    Diffuser pipeline: StableDiffusionImg2ImgPipeline task=DiffusersTaskType.IMAGE_2_IMAGE batch=1/1x1 set={'timesteps': [999, 850, 736, 645, 545, 455, 343, 233,
                         124, 24], 'prompt_embeds': torch.Size([1, 154, 768]), 'negative_prompt_embeds': torch.Size([1, 154, 768]), 'guidance_scale': 3, 'num_inference_steps': 67, 'eta':
                         1.0, 'output_type': 'latent', 'image': [<PIL.Image.Image image mode=RGB size=1024x1536 at 0x7F0FCDB543D0>], 'strength': 0.3, 'parser': 'Full parser'}
Progress  1.86it/s ██████████████████████████████████ 100% 3/3 00:01 00:00 Hires
11:02:24-674338 TRACE    Processing result: index=1/1 iteration=1/1
11:02:24-697172 INFO     Processed: images=1 time=13.29 its=0.75 memory={'ram': {'used': 4.09, 'total': 39.18}, 'gpu': {'used': 4.59, 'total': 23.99}, 'retries': 0, 'oom': 0}
11:02:24-709013 DEBUG    LoRA unload
11:02:24-711472 TRACE    Control resize: op=after image=<PIL.Image.Image image mode=RGB size=1024x1536 at 0x7F0FE4157C10> width=1024 height=1538 mode=1 name=ESRGAN 4x Remacri
11:02:24-714616 DEBUG    Upscaler cached: type=ESRGAN model=/home/tillerz/models/ESRGAN/ESRGAN-Remacri-4x.pth
Upscaling ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:00 0:00:02
11:02:27-738403 TRACE    Control received: type=<class 'tuple'> (<PIL.Image.Image image mode=RGB size=1024x1538 at 0x7F0FE79FCBE0>, None, 'Control output | 1 of 1 | Image 1024x1538')
11:02:28-523416 DEBUG    Save temp: image="/home/tillerz/images_temp/tmp_xye_f2v.png" resolution=1024x1538 size=1766972
11:02:28-596480 INFO     Control: pipeline units=0 process=0 time=13.33 init=0.01 proc=0.00 ctrl=13.32 outputs=1
11:02:28-601503 TRACE    Ready: | Time 17.22s | Images 1 | Size 1024x1538
11:02:28-602310 TRACE    Control received: type=<class 'tuple'> ([<PIL.Image.Image image mode=RGB size=1024x1538 at 0x7F0FE79FCBE0>], None, '<p>Ready | Time 17.22s | Images 1 | Size
                         1024x1538</p><p><b>Prompt:</b> steampunk girl, portrait by ross tran and jeremy mann 4 k artstation trending dramatic lighting modernism photo realistic hd
                         painting in the style of alexander mcqueen, dark and moody, foggy background with lightning storm and rain. unreal engine 5 highly rendered render vfx, cinema4 d
                         cinematic octane rendered scene illustration, sharp focus, masterpiece, global illumination ray tracing shadows and smoke out at a window looking in the distance
                         on the city below is 8 0 mm realistic film still from blade runner 2 0 9 7 9 1 6 sitting deep focus, fantasy character photography movie still frame, intricate
                         details, extremely detailed, 8 k resolution, digital painting - n 3 - i robot android walking in cyberpunk 20
                         &lt;lora:watercolorV1:0.4&gt;</p><p><b>Negative:</b> child, loli, anime, manga, necklace, disney, unreal engine, octane render</p><p><b>Parameters:</b> Steps:
                         10| Seed: 3026283561| Sampler: DPM++ 2M| CFG scale: 3.5| Size: 512x768| Parser: Full parser| Model: zo4-ra-art-if-noo-fcb3-rcr-rpg-ssae-lyrae| Model hash:
                         d371182084| Backend: Diffusers| App: SD.Next| Version: 1b6ebd9| Operations: upscale; hires; txt2img| Pipeline: StableDiffusionPipeline| T5: T5 FP16| Second pass:
                         True| Hires force: True| Hires steps: 20| Hires upscaler: ESRGAN 4x Remacri| Hires upscale: 2| Hires size: 1024x1536| Denoising strength: 0.8| Hires sampler:
                         Same as primary| Image CFG scale: 3| CFG rescale: 0.7| Size before: 512x768| Size mode before: 1| Size scale before: 1| Size name before: ESRGAN 4x Remacri| Size
                         after: 1024x1538| Size mode after: 1| Size scale after: 1| Size name after: ESRGAN 4x Remacri| Size mask: 1024x1538| Size mode mask: 1| Size scale mask: 1| Size
                         name mask: ESRGAN 4x Remacri| ToDo: 0.5| FreeU: b1=1.2 b2=1.4 s1=0.9 s2=0.2| Lora hashes: watercolorV1: 04e3354d| Sampler options: sde-dpmsolver++/order 2/low
                         order| HiDiffusion Ratios: 0.2/0.1| HiDiffusion: True/True/True:8| Size-1: 512| Size-2: 768| Hires size-1: 1024| Hires size-2: 1536| Size before-1: 512| Size
                         before-2: 768| Size after-1: 1024| Size after-2: 1538| Size mask-1: 1024| Size mask-2: 1538</p>', None)
Backend

Diffusers
UI

ModernUI
Branch

Dev
Model

StableDiffusion 1.5
Acknowledgements

[X] I have read the above and searched for existing issues
[X] I confirm that this is classified correctly and its not an extension issue
vladmandic / automatic

[Issue]: Rendering 512x768 with 2x upscale creates 1024x1538 images instead of 1024x1536 images. #3387
