Gourieff / sd-webui-reactor

Fast and Simple Face Swap Extension for StableDiffusion WebUI (A1111 SD WebUI, SD WebUI Forge, SD.Next, Cagliostro)
GNU Affero General Public License v3.0
2.3k stars 246 forks source link

VRAM leak issue #307

Open Woisek opened 6 months ago

Woisek commented 6 months ago

First, confirm

What happened?

I just realized, that after using ReActor for the first time, all generations afterward are considerably slowed down. I render a SDXL image 720x1024 in about 1min. with ReActor enabled. After this first generation, all following generations are about 10 times slower. First generation (note the times on each image): Zwischenablagebild

Second generation: Zwischenablagebild (1)

Any ideas what happened here? πŸ€”

Steps to reproduce the problem

  1. Go to ....
  2. Press ....
  3. ...

Sysinfo

{ "Platform": "Windows-10-10.0.19044-SP0", "Python": "3.10.6", "Version": "v1.7.0", "Commit": "cf2772fab0af5573da775e7437e6acdca424f26e", "Script path": "V:\AI_programms\stable-diffusion-webui", "Data path": "V:\AI_programms\stable-diffusion-webui", "Extensions dir": "V:\AI_programms\stable-diffusion-webui\extensions", "Checksum": "82d9dad70b091876c6d37ef368d635c46e8df066deadb05f3741ae06e3428b86", "Commandline": [ "launch.py", "--no-half-vae", "--medvram-sdxl", "--medvram", "--xformers", "--api", "--theme=dark", "--port", "7861" ], "Torch env info": { "torch_version": "2.0.1+cu118", "is_debug_build": "False", "cuda_compiled_version": "11.8", "gcc_version": null, "clang_version": null, "cmake_version": null, "os": "Microsoft Windows 10 Pro", "libc_version": "N/A", "python_version": "3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] (64-bit runtime)", "python_platform": "Windows-10-10.0.19044-SP0", "is_cuda_available": "True", "cuda_runtime_version": null, "cuda_module_loading": "LAZY", "nvidia_driver_version": "537.42", "nvidia_gpu_models": "GPU 0: NVIDIA GeForce RTX 2070 SUPER", "cudnn_version": null, "pip_version": "pip3", "pip_packages": [ "numpy==1.23.5", "open-clip-torch==2.20.0", "pytorch-lightning==1.9.4", "torch==2.0.1+cu118", "torchdiffeq==0.2.3", "torchmetrics==1.2.1", "torchsde==0.2.6", "torchvision==0.15.2+cu118" ], "conda_packages": "", "hip_compiled_version": "N/A", "hip_runtime_version": "N/A", "miopen_runtime_version": "N/A", "caching_allocator_config": "", "is_xnnpack_available": "True", "cpu_info": [ "Architecture=9", "CurrentClockSpeed=3600", "DeviceID=CPU0", "Family=207", "L2CacheSize=2048", "L2CacheSpeed=", "Manufacturer=GenuineIntel", "MaxClockSpeed=3600", "Name=Intel(R) Core(TM) i9-9900K CPU @ 3.60GHz", "ProcessorType=3", "Revision=" ] }, "Exceptions": [], "CPU": { "model": "Intel64 Family 6 Model 158 Stepping 13, GenuineIntel", "count logical": 16, "count physical": 8 }, "RAM": { "total": "64GB", "used": "32GB", "free": "32GB" }, "Extensions": [ { "name": "--sd-webui-ar-plus", "path": "V:\AI_programms\stable-diffusion-webui\extensions\--sd-webui-ar-plus", "version": "cbb397e7", "branch": "main", "remote": "https://github.com/LEv145/--sd-webui-ar-plus" }, { "name": "OneButtonPrompt", "path": "V:\AI_programms\stable-diffusion-webui\extensions\OneButtonPrompt", "version": "356a1b53", "branch": "main", "remote": "https://github.com/AIrjen/OneButtonPrompt" }, { "name": "a1111-sd-webui-tagcomplete", "path": "V:\AI_programms\stable-diffusion-webui\extensions\a1111-sd-webui-tagcomplete", "version": "c659ed21", "branch": "main", "remote": "https://github.com/DominikDoom/a1111-sd-webui-tagcomplete.git" }, { "name": "adetailer", "path": "V:\AI_programms\stable-diffusion-webui\extensions\adetailer", "version": "f1dfb34e", "branch": "main", "remote": "https://github.com/Bing-su/adetailer.git" }, { "name": "canvas-zoom", "path": "V:\AI_programms\stable-diffusion-webui\extensions\canvas-zoom", "version": "26450143", "branch": "main", "remote": "https://github.com/richrobber2/canvas-zoom.git" }, { "name": "clip-interrogator-ext", "path": "V:\AI_programms\stable-diffusion-webui\extensions\clip-interrogator-ext", "version": "0f1a4591", "branch": "main", "remote": "https://github.com/pharmapsychotic/clip-interrogator-ext.git" }, { "name": "sd-dynamic-prompts", "path": "V:\AI_programms\stable-diffusion-webui\extensions\sd-dynamic-prompts", "version": "284d3ef3", "branch": "main", "remote": "https://github.com/adieyal/sd-dynamic-prompts.git" }, { "name": "sd-model-preview-xd", "path": "V:\AI_programms\stable-diffusion-webui\extensions\sd-model-preview-xd", "version": "42fa267d", "branch": "main", "remote": "https://github.com/CurtisDS/sd-model-preview-xd" }, { "name": "sd-webui-controlnet", "path": "V:\AI_programms\stable-diffusion-webui\extensions\sd-webui-controlnet", "version": "4cf15d1c", "branch": "main", "remote": "https://github.com/Mikubill/sd-webui-controlnet.git" }, { "name": "sd-webui-fabric", "path": "V:\AI_programms\stable-diffusion-webui\extensions\sd-webui-fabric", "version": "5a247c9d", "branch": "main", "remote": "https://github.com/dvruette/sd-webui-fabric.git" }, { "name": "sd-webui-openpose-editor", "path": "V:\AI_programms\stable-diffusion-webui\extensions\sd-webui-openpose-editor", "version": "cebe13e0", "branch": "main", "remote": "https://github.com/huchenlei/sd-webui-openpose-editor.git" }, { "name": "sd-webui-reactor", "path": "V:\AI_programms\stable-diffusion-webui\extensions\sd-webui-reactor", "version": "805a0cae", "branch": "main", "remote": "https://github.com/Gourieff/sd-webui-reactor.git" }, { "name": "sd_extension-prompt_formatter", "path": "V:\AI_programms\stable-diffusion-webui\extensions\sd_extension-prompt_formatter", "version": "06f2572e", "branch": "main", "remote": "https://github.com/uwidev/sd_extension-prompt_formatter.git" }, { "name": "stable-diffusion-webui-promptgen", "path": "V:\AI_programms\stable-diffusion-webui\extensions\stable-diffusion-webui-promptgen", "version": "84e58b5d", "branch": "master", "remote": "https://github.com/AUTOMATIC1111/stable-diffusion-webui-promptgen.git" }, { "name": "stable-diffusion-webui-wildcards", "path": "V:\AI_programms\stable-diffusion-webui\extensions\stable-diffusion-webui-wildcards", "version": "c7d49e18", "branch": "master", "remote": "https://github.com/AUTOMATIC1111/stable-diffusion-webui-wildcards.git" }, { "name": "ultimate-upscale-for-automatic1111", "path": "V:\AI_programms\stable-diffusion-webui\extensions\ultimate-upscale-for-automatic1111", "version": "728ffcec", "branch": "master", "remote": "https://github.com/Coyote-A/ultimate-upscale-for-automatic1111.git" } ], "Inactive extensions": [], "Environment": { "COMMANDLINE_ARGS": "--no-half-vae --medvram-sdxl --medvram --xformers --api --theme=dark --port 7861", "GRADIO_ANALYTICS_ENABLED": "False" }, "Config": { "samples_save": true, "samples_format": "png", "samples_filename_pattern": "S=[seed]-St=[steps]-Sa=[sampler]-Cfg=[cfg]", "save_images_add_number": true, "save_images_replace_action": "Add number suffix", "grid_save": true, "grid_format": "png", "grid_extended_filename": false, "grid_only_if_multiple": true, "grid_prevent_empty_spots": false, "grid_zip_filename_pattern": "", "n_rows": -1, "font": "", "grid_text_active_color": "#000000", "grid_text_inactive_color": "#999999", "grid_background_color": "#ffffff", "save_images_before_face_restoration": false, "save_images_before_highres_fix": false, "save_images_before_color_correction": false, "save_mask": false, "save_mask_composite": false, "jpeg_quality": 80, "webp_lossless": false, "export_for_4chan": false, "img_downscale_threshold": 4.0, "target_side_length": 4000, "img_max_size_mp": 200, "use_original_name_batch": true, "use_upscaler_name_as_suffix": false, "save_selected_only": true, "save_init_img": false, "temp_dir": "T:\systemp\sd-temp-files\", "clean_temp_dir_at_start": true, "save_incomplete_images": false, "notification_audio": true, "notification_volume": 100, "outdir_samples": "", "outdir_txt2img_samples": "outputs/txt2img-images", "outdir_img2img_samples": "outputs/img2img-images", "outdir_extras_samples": "outputs/extras-images", "outdir_grids": "", "outdir_txt2img_grids": "outputs/txt2img-grids", "outdir_img2img_grids": "outputs/img2img-grids", "outdir_save": "log/images", "outdir_init_images": "outputs/init-images", "save_to_dirs": true, "grid_save_to_dirs": false, "use_save_to_dirs_for_ui": true, "directories_filename_pattern": "test/[prompt_words]/[model_name]/", "directories_max_prompt_words": 2, "ESRGAN_tile": 192, "ESRGAN_tile_overlap": 8, "realesrgan_enabled_models": [ "R-ESRGAN 4x+", "R-ESRGAN 4x+ Anime6B" ], "upscaler_for_img2img": null, "face_restoration": true, "face_restoration_model": "CodeFormer", "code_former_weight": 0, "face_restoration_unload": true, "auto_launch_browser": "Disable", "enable_console_prompts": false, "show_warnings": true, "show_gradio_deprecation_warnings": true, "memmon_poll_rate": 8, "samples_log_stdout": false, "multiple_tqdm": true, "print_hypernet_extra": false, "list_hidden_files": true, "disable_mmap_load_safetensors": false, "hide_ldm_prints": true, "dump_stacks_on_signal": false, "api_enable_requests": true, "api_forbid_local_requests": true, "api_useragent": "", "unload_models_when_training": false, "pin_memory": false, "save_optimizer_state": false, "save_training_settings_to_txt": true, "dataset_filename_word_regex": "", "dataset_filename_join_string": " ", "training_image_repeats_per_epoch": 1, "training_write_csv_every": 500, "training_xattention_optimizations": false, "training_enable_tensorboard": false, "training_tensorboard_save_images": false, "training_tensorboard_flush_every": 120, "sd_model_checkpoint": "ProtoVision XL\ProtoVision XL_v0.6.2.0_VAE_SDXL1.0.safetensors [dd6c6f3f83]", "sd_checkpoints_limit": 1, "sd_checkpoints_keep_in_cpu": true, "sd_checkpoint_cache": 0, "sd_unet": "None", "enable_quantization": true, "enable_emphasis": true, "enable_batch_seeds": true, "comma_padding_backtrack": 23, "CLIP_stop_at_last_layers": 1, "upcast_attn": false, "randn_source": "GPU", "tiling": false, "hires_fix_refiner_pass": "second pass", "sdxl_crop_top": 0, "sdxl_crop_left": 0, "sdxl_refiner_low_aesthetic_score": 2.5, "sdxl_refiner_high_aesthetic_score": 6.0, "sd_vae_checkpoint_cache": 0, "sd_vae": "sdxl_vae.safetensors", "sd_vae_overrides_per_model_preferences": true, "auto_vae_precision": true, "sd_vae_encode_method": "Full", "sd_vae_decode_method": "Full", "inpainting_mask_weight": 1.0, "initial_noise_multiplier": 1.0, "img2img_extra_noise": 0.0, "img2img_color_correction": false, "img2img_fix_steps": false, "img2img_background_color": "#000000", "img2img_editor_height": 720, "img2img_sketch_default_brush_color": "#ffffff", "img2img_inpaint_mask_brush_color": "#ffffff", "img2img_inpaint_sketch_default_brush_color": "#ffffff", "return_mask": false, "return_mask_composite": false, "img2img_batch_show_results_limit": 32, "cross_attention_optimization": "sdp - scaled dot product", "s_min_uncond": 0.0, "token_merging_ratio": 0.0, "token_merging_ratio_img2img": 0.0, "token_merging_ratio_hr": 0.0, "pad_cond_uncond": false, "persistent_cond_cache": true, "batch_cond_uncond": true, "use_old_emphasis_implementation": false, "use_old_karras_scheduler_sigmas": false, "no_dpmpp_sde_batch_determinism": false, "use_old_hires_fix_width_height": false, "dont_fix_second_order_samplers_schedule": false, "hires_fix_use_firstpass_conds": false, "use_old_scheduling": false, "interrogate_keep_models_in_memory": false, "interrogate_return_ranks": false, "interrogate_clip_num_beams": 4, "interrogate_clip_min_length": 10, "interrogate_clip_max_length": 48, "interrogate_clip_dict_limit": 1500, "interrogate_clip_skip_categories": [], "interrogate_deepbooru_score_threshold": 0.5, "deepbooru_sort_alpha": true, "deepbooru_use_spaces": true, "deepbooru_escape": false, "deepbooru_filter_tags": "", "extra_networks_show_hidden_directories": true, "extra_networks_dir_button_function": false, "extra_networks_hidden_models": "When searched", "extra_networks_default_multiplier": 1.0, "extra_networks_card_width": 0, "extra_networks_card_height": 0, "extra_networks_card_text_scale": 1.0, "extra_networks_card_show_desc": true, "extra_networks_card_order_field": "Name", "extra_networks_card_order": "Ascending", "extra_networks_add_text_separator": " ", "ui_extra_networks_tab_reorder": "Checkpoints, Lora, Textual Inversion, Hypernetworks", "textual_inversion_print_at_load": false, "textual_inversion_add_hashes_to_infotext": true, "sd_hypernetwork": "None", "keyedit_precision_attention": 0.1, "keyedit_precision_extra": 0.05, "keyedit_delimiters": ".,\/!?%^*;:{}=`~() ", "keyedit_delimiters_whitespace": [ "Tab", "Carriage Return", "Line Feed" ], "keyedit_move": true, "disable_token_counters": false, "return_grid": true, "do_not_show_images": false, "js_modal_lightbox": true, "js_modal_lightbox_initially_zoomed": true, "js_modal_lightbox_gamepad": false, "js_modal_lightbox_gamepad_repeat": 250, "gallery_height": "", "compact_prompt_box": false, "samplers_in_dropdown": true, "dimensions_and_batch_together": true, "sd_checkpoint_dropdown_use_short": true, "hires_fix_show_sampler": false, "hires_fix_show_prompts": false, "txt2img_settings_accordion": false, "img2img_settings_accordion": false, "localization": "None", "quicksettings_list": [ "sd_model_checkpoint", "sd_vae", "directories_filename_pattern", "directories_max_prompt_words", "CLIP_stop_at_last_layers", "face_restoration" ], "ui_tab_order": [], "hidden_tabs": [], "ui_reorder_list": [], "gradio_theme": "remilia/Ghostly", "gradio_themes_cache": true, "show_progress_in_title": true, "send_seed": true, "send_size": true, "enable_pnginfo": true, "save_txt": false, "add_model_name_to_info": true, "add_model_hash_to_info": true, "add_vae_name_to_info": true, "add_vae_hash_to_info": true, "add_user_name_to_info": false, "add_version_to_infotext": true, "disable_weights_auto_swap": true, "infotext_skip_pasting": [], "infotext_styles": "Apply if any", "show_progressbar": true, "live_previews_enable": false, "live_previews_image_format": "png", "show_progress_grid": true, "show_progress_every_n_steps": 0, "show_progress_type": "Full", "live_preview_allow_lowvram_full": false, "live_preview_content": "Prompt", "live_preview_refresh_period": 100.0, "live_preview_fast_interrupt": false, "js_live_preview_in_modal_lightbox": false, "hide_samplers": [ "UniPC" ], "eta_ddim": 0.0, "eta_ancestral": 1.0, "ddim_discretize": "uniform", "s_churn": 0.3, "s_tmin": 0.0, "s_tmax": 0.0, "s_noise": 1.0, "k_sched_type": "Automatic", "sigma_min": 0.0, "sigma_max": 0.0, "rho": 0.0, "eta_noise_seed_delta": 0, "always_discard_next_to_last_sigma": false, "sgm_noise_multiplier": false, "uni_pc_variant": "bh1", "uni_pc_skip_type": "time_uniform", "uni_pc_order": 3, "uni_pc_lower_order_final": true, "postprocessing_enable_in_main_ui": [], "postprocessing_operation_order": [], "upscaling_max_images_in_cache": 5, "postprocessing_existing_caption_action": "Ignore", "disabled_extensions": [], "disable_all_extensions": "none", "restore_config_state_file": "", "sd_checkpoint_hash": "8d0ce6c016004cbdacd50f937dad381d8c396628d621a7f97191470532780164", "ldsr_steps": 100, "ldsr_cached": false, "SCUNET_tile": 256, "SCUNET_tile_overlap": 8, "SWIN_tile": 192, "SWIN_tile_overlap": 8, "hypertile_enable_unet": false, "hypertile_enable_unet_secondpass": false, "hypertile_max_depth_unet": 3, "hypertile_max_tile_unet": 256, "hypertile_swap_size_unet": 3, "hypertile_enable_vae": false, "hypertile_max_depth_vae": 3, "hypertile_max_tile_vae": 128, "hypertile_swap_size_vae": 3, "lora_functional": false, "sd_lora": "None", "lora_preferred_name": "Alias from file", "lora_add_hashes_to_infotext": true, "lora_show_all": false, "lora_hide_unknown_for_versions": [], "lora_in_memory_limit": 0, "extra_options_txt2img": [], "extra_options_img2img": [], "extra_options_cols": 1, "extra_options_accordion": false, "canvas_hotkey_zoom": "Alt", "canvas_hotkey_adjust": "Ctrl", "canvas_hotkey_move": "F", "canvas_hotkey_fullscreen": "S", "canvas_hotkey_reset": "R", "canvas_hotkey_overlap": "O", "canvas_show_tooltip": true, "canvas_auto_expand": true, "canvas_blur_prompt": false, "canvas_disabled_functions": [ "Overlap" ], "ad_max_models": 2, "ad_extra_models_dir": "", "ad_save_previews": false, "ad_save_images_before": false, "ad_only_seleted_scripts": true, "ad_script_names": "dynamic_prompting,dynamic_thresholding,wildcard_recursive,wildcards,lora_block_weight,negpip", "ad_bbox_sortby": "None", "ad_same_seed_for_each_tap": false, "model_preview_xd_name_matching": "Index", "model_preview_xd_limit_sizing": true, "model_preview_xd_column_view": true, "control_net_detectedmap_dir": "detected_maps", "control_net_models_path": "", "control_net_modules_path": "", "control_net_unit_count": 3, "control_net_model_cache_size": 2, "control_net_inpaint_blur_sigma": 7, "control_net_no_high_res_fix": false, "control_net_no_detectmap": false, "control_net_detectmap_autosaving": false, "control_net_allow_script_control": false, "control_net_sync_field_args": true, "controlnet_show_batch_images_in_ui": false, "controlnet_increment_seed_during_batch": false, "controlnet_disable_openpose_edit": false, "controlnet_ignore_noninpaint_mask": false, "controlnet_crop_upscale_script_only": false, "pformat_space_commas": true, "pfromat_bracket2weight": true, "pfromat_space2underscore": false, "promptgen_names": "AUTOMATIC/promptgen-lexart", "promptgen_device": "gpu", "wildcards_same_seed": false, "dp_ignore_whitespace": true, "dp_write_raw_template": true, "dp_write_prompts_to_file": false, "dp_parser_variant_start": "{", "dp_parser_variant_end": "}", "dp_parser_wildcard_wrap": "__", "dp_limit_jinja_prompts": false, "dp_auto_purge_cache": false, "dp_wildcard_manager_no_dedupe": false, "dp_wildcard_manager_no_sort": false, "dp_wildcard_manager_shuffle": false, "dp_magicprompt_default_model": "Gustavosta/MagicPrompt-Stable-Diffusion", "dp_magicprompt_batch_size": 1, "canvas_zoom_undo_extra_key": "Ctrl", "canvas_zoom_hotkey_undo": "Z", "canvas_zoom_inc_brush_size": "]", "canvas_zoom_dec_brush_size": "[", "canvas_zoom_hotkey_open_colorpanel": "Q", "canvas_zoom_hotkey_pin_colorpanel": "T", "canvas_zoom_hotkey_dropper": "A", "canvas_zoom_hotkey_fill": "X", "canvas_zoom_hotkey_transparency": "C", "canvas_zoom_hide_btn": true, "canvas_zoom_mask_clear": true, "canvas_zoom_enable_integration": true, "canvas_zoom_brush_size": 200, "canvas_zoom_brush_size_change": 5, "canvas_zoom_transparency_level": 70, "canvas_zoom_brush_opacity": false, "canvas_zoom_inpaint_label": true, "canvas_zoom_inpaint_warning": true, "canvas_zoom_inpaint_change_btn_color": false, "canvas_zoom_inpaint_btn_color": "#C33227", "canvas_zoom_brush_outline": false, "canvas_zoom_add_buttons": false, "canvas_zoom_draw_staight_lines": false, "canvas_zoom_inpaint_brushcolor": "#000000", "canvas_zoom_disabled_functions": [ "Overlap" ], "tac_tagFile": "danbooru.csv", "tac_active": true, "tac_activeIn.txt2img": true, "tac_activeIn.img2img": true, "tac_activeIn.negativePrompts": true, "tac_activeIn.thirdParty": true, "tac_activeIn.modelList": "", "tac_activeIn.modelListMode": "Blacklist", "tac_slidingPopup": true, "tac_maxResults": 5, "tac_showAllResults": false, "tac_resultStepLength": 100, "tac_delayTime": 100, "tac_useWildcards": true, "tac_sortWildcardResults": true, "tac_wildcardExclusionList": "", "tac_skipWildcardRefresh": false, "tac_useEmbeddings": true, "tac_includeEmbeddingsInNormalResults": false, "tac_useHypernetworks": true, "tac_useLoras": true, "tac_useLycos": true, "tac_useLoraPrefixForLycos": true, "tac_showWikiLinks": false, "tac_showExtraNetworkPreviews": true, "tac_modelSortOrder": "Name", "tac_replaceUnderscores": true, "tac_escapeParentheses": true, "tac_appendComma": true, "tac_appendSpace": true, "tac_alwaysSpaceAtEnd": true, "tac_modelKeywordCompletion": "Never", "tac_modelKeywordLocation": "Start of prompt", "tac_wildcardCompletionMode": "To next folder level", "tac_alias.searchByAlias": true, "tac_alias.onlyShowAlias": false, "tac_translation.translationFile": "None", "tac_translation.oldFormat": false, "tac_translation.searchByTranslation": true, "tac_translation.liveTranslation": false, "tac_extra.extraFile": "extra-quality-tags.csv", "tac_extra.addMode": "Insert before", "tac_chantFile": "demo-chants.json", "tac_keymap": "{\n \"MoveUp\": \"ArrowUp\",\n \"MoveDown\": \"ArrowDown\",\n \"JumpUp\": \"PageUp\",\n \"JumpDown\": \"PageDown\",\n \"JumpToStart\": \"Home\",\n \"JumpToEnd\": \"End\",\n \"ChooseSelected\": \"Enter\",\n \"ChooseFirstOrSelected\": \"Tab\",\n \"Close\": \"Escape\"\n}", "tac_colormap": "{\n \"danbooru\": {\n \"-1\": [\"red\", \"maroon\"],\n \"0\": [\"lightblue\", \"dodgerblue\"],\n \"1\": [\"indianred\", \"firebrick\"],\n \"3\": [\"violet\", \"darkorchid\"],\n \"4\": [\"lightgreen\", \"darkgreen\"],\n \"5\": [\"orange\", \"darkorange\"]\n },\n \"e621\": {\n \"-1\": [\"red\", \"maroon\"],\n \"0\": [\"lightblue\", \"dodgerblue\"],\n \"1\": [\"gold\", \"goldenrod\"],\n \"3\": [\"violet\", \"darkorchid\"],\n \"4\": [\"lightgreen\", \"darkgreen\"],\n \"5\": [\"tomato\", \"darksalmon\"],\n \"6\": [\"red\", \"maroon\"],\n \"7\": [\"whitesmoke\", \"black\"],\n \"8\": [\"seagreen\", \"darkseagreen\"]\n }\n}", "tac_refreshTempFiles": "Refresh TAC temp files", "controlnet_disable_photopea_edit": false }, "Startup": { "total": 51.43554186820984, "records": { "initial startup": 0.09474730491638184, "prepare environment/checks": 0.022961139678955078, "prepare environment/git version info": 0.5799798965454102, "prepare environment/torch GPU test": 5.410948038101196, "prepare environment/clone repositores": 0.21796870231628418, "prepare environment/run extensions installers/--sd-webui-ar-plus": 0.0, "prepare environment/run extensions installers/a1111-sd-webui-tagcomplete": 0.0, "prepare environment/run extensions installers/adetailer": 0.33149242401123047, "prepare environment/run extensions installers/canvas-zoom": 9.906271934509277, "prepare environment/run extensions installers/clip-interrogator-ext": 4.526882171630859, "prepare environment/run extensions installers/OneButtonPrompt": 0.0, "prepare environment/run extensions installers/sd-dynamic-prompts": 0.2885909080505371, "prepare environment/run extensions installers/sd-model-preview-xd": 0.001028299331665039, "prepare environment/run extensions installers/sd-webui-controlnet": 0.38493990898132324, "prepare environment/run extensions installers/sd-webui-fabric": 0.0, "prepare environment/run extensions installers/sd-webui-openpose-editor": 0.0, "prepare environment/run extensions installers/sd-webui-reactor": 1.9760572910308838, "prepare environment/run extensions installers/sd_extension-prompt_formatter": 0.18855023384094238, "prepare environment/run extensions installers/stable-diffusion-webui-promptgen": 0.0, "prepare environment/run extensions installers/stable-diffusion-webui-wildcards": 0.0, "prepare environment/run extensions installers/ultimate-upscale-for-automatic1111": 0.0, "prepare environment/run extensions installers": 17.60381317138672, "prepare environment": 24.10330843925476, "launcher": 0.06196141242980957, "import torch": 3.5810585021972656, "import gradio": 0.9066042900085449, "setup paths": 2.135143995285034, "import ldm": 0.011996030807495117, "import sgm": 0.0, "initialize shared": 0.3964264392852783, "other imports": 2.514179229736328, "opts onchange": 0.0019621849060058594, "setup SD model": 0.0060176849365234375, "setup codeformer": 0.47025346755981445, "setup gfpgan": 0.06183457374572754, "set samplers": 0.0, "list extensions": 0.004001617431640625, "restore config state file": 0.0, "list SD models": 2.651313304901123, "list localizations": 0.0008969306945800781, "load scripts/custom_code.py": 0.017318010330200195, "load scripts/detect_extension.py": 0.009969472885131836, "load scripts/img2imgalt.py": 0.0009744167327880859, "load scripts/loopback.py": 0.003989219665527344, "load scripts/loopback_scaler.py": 0.008975744247436523, "load scripts/outpainting_mk_2.py": 0.0020194053649902344, "load scripts/poor_mans_outpainting.py": 0.000972747802734375, "load scripts/postprocessing_caption.py": 0.000997304916381836, "load scripts/postprocessing_codeformer.py": 0.0010194778442382812, "load scripts/postprocessing_create_flipped_copies.py": 0.0, "load scripts/postprocessing_focal_crop.py": 0.009951114654541016, "load scripts/postprocessing_gfpgan.py": 0.0009975433349609375, "load scripts/postprocessing_split_oversized.py": 0.0, "load scripts/postprocessing_upscale.py": 0.0019941329956054688, "load scripts/processing_autosized_crop.py": 0.0, "load scripts/prompt_matrix.py": 0.0009975433349609375, "load scripts/prompts_from_file.py": 0.0019943714141845703, "load scripts/run_n_times.py": 0.0, "load scripts/sd_upscale.py": 0.000997781753540039, "load scripts/xyz_grid.py": 0.003989696502685547, "load scripts/ldsr_model.py": 0.8560492992401123, "load scripts/lora_script.py": 0.1775684356689453, "load scripts/scunet_model.py": 0.04041147232055664, "load scripts/swinir_model.py": 0.027924776077270508, "load scripts/hotkey_config.py": 0.0009703636169433594, "load scripts/extra_options_section.py": 0.0009975433349609375, "load scripts/hypertile_script.py": 0.045876502990722656, "load scripts/hypertile_xyz.py": 0.0, "load scripts/sd-webui-ar.py": 0.010338306427001953, "load scripts/api.py": 0.6507046222686768, "load scripts/onebuttonprompt.py": 0.020973920822143555, "load scripts/model_keyword_support.py": 0.008133172988891602, "load scripts/shared_paths.py": 0.0009982585906982422, "load scripts/tag_autocomplete_helper.py": 0.23255276679992676, "load scripts/!adetailer.py": 1.2668414115905762, "load scripts/config.py": 0.0010211467742919922, "load scripts/clip_interrogator_ext.py": 0.06682419776916504, "load scripts/dynamic_prompting.py": 0.145310640335083, "load scripts/modelpreview.py": 0.06682181358337402, "load scripts/adapter.py": 0.0020132064819335938, "load scripts/batch_hijack.py": 0.0020008087158203125, "load scripts/cldm.py": 0.0009937286376953125, "load scripts/controlmodel_ipadapter.py": 0.0019943714141845703, "load scripts/controlnet.py": 0.4470045566558838, "load scripts/controlnet_diffusers.py": 0.0, "load scripts/controlnet_lllite.py": 0.0, "load scripts/controlnet_lora.py": 0.0, "load scripts/controlnet_model_guess.py": 0.0009968280792236328, "load scripts/controlnet_version.py": 0.0, "load scripts/enums.py": 0.000997304916381836, "load scripts/external_code.py": 0.0, "load scripts/global_state.py": 0.0, "load scripts/hook.py": 0.0009970664978027344, "load scripts/infotext.py": 0.0, "load scripts/logging.py": 0.0, "load scripts/lvminthin.py": 0.0009951591491699219, "load scripts/movie2movie.py": 0.0009837150573730469, "load scripts/processor.py": 0.0010137557983398438, "load scripts/utils.py": 0.0, "load scripts/xyz_grid_support.py": 0.0029942989349365234, "load scripts/fabric.py": 0.06747794151306152, "load scripts/fabric_utils.py": 0.0009996891021728516, "load scripts/marking.py": 0.0, "load scripts/merging.py": 0.0, "load scripts/patching.py": 0.0, "load scripts/weighted_attention.py": 0.0039865970611572266, "load scripts/openpose_editor.py": 0.030052661895751953, "load scripts/console_log_patch.py": 1.2225821018218994, "load scripts/reactor_api.py": 0.10910797119140625, "load scripts/reactor_faceswap.py": 0.013360738754272461, "load scripts/reactor_globals.py": 0.0, "load scripts/reactor_helpers.py": 0.0009987354278564453, "load scripts/reactor_logger.py": 0.0, "load scripts/reactor_swapper.py": 0.0009963512420654297, "load scripts/reactor_version.py": 0.0, "load scripts/format_ui.py": 0.04789161682128906, "load scripts/promptgen.py": 0.06499004364013672, "load scripts/wildcards.py": 0.021936416625976562, "load scripts/ultimate-upscale.py": 0.002970457077026367, "load scripts/refiner.py": 0.0010197162628173828, "load scripts/seed.py": 0.0009937286376953125, "load scripts": 5.739826202392578, "load upscalers": 0.00499725341796875, "refresh VAE": 0.025901079177856445, "refresh textual inversion templates": 0.0, "scripts list_optimizers": 0.0009975433349609375, "scripts list_unets": 0.0, "reload hypernetworks": 0.009999990463256836, "initialize extra networks": 0.03191328048706055, "cleanup temp dir": 0.0, "scripts before_ui_callback": 0.001993894577026367, "create ui": 8.548667907714844, "gradio launch": 0.22140860557556152, "add APIs": 0.09482407569885254, "app_started_callback/lora_script.py": 0.0, "app_started_callback/api.py": 0.004987478256225586, "app_started_callback/tag_autocomplete_helper.py": 0.0019936561584472656, "app_started_callback/clip_interrogator_ext.py": 0.0, "app_started_callback/openpose_editor.py": 0.01196908950805664, "app_started_callback/reactor_api.py": 0.001993894577026367, "app_started_callback": 0.02094411849975586 } }, "Packages": [ "-rotobuf==3.20.0", "absl-py==2.0.0", "accelerate==0.21.0", "addict==2.4.0", "aenum==3.1.15", "aiofiles==23.2.1", "aiohttp==3.9.1", "aiosignal==1.3.1", "albumentations==1.3.1", "altair==5.2.0", "antlr4-python3-runtime==4.9.3", "anyio==3.7.1", "async-timeout==4.0.3", "attrs==23.1.0", "basicsr==1.4.2", "beautifulsoup4==4.12.2", "blendmodes==2022", "cachetools==5.3.2", "certifi==2023.11.17", "cffi==1.16.0", "chardet==5.2.0", "charset-normalizer==3.3.2", "clean-fid==0.1.35", "click==8.1.7", "clip-interrogator==0.6.0", "clip==1.0", "colorama==0.4.6", "coloredlogs==15.0.1", "contourpy==1.2.0", "cssselect2==0.7.0", "cycler==0.12.1", "cython==3.0.7", "deprecation==2.1.0", "dynamicprompts==0.30.4", "easydict==1.11", "einops==0.4.1", "exceptiongroup==1.2.0", "facexlib==0.3.0", "fastapi==0.94.0", "ffmpy==0.3.1", "filelock==3.13.1", "filterpy==1.4.5", "flatbuffers==23.5.26", "fonttools==4.47.0", "frozenlist==1.4.1", "fsspec==2023.12.2", "ftfy==6.1.3", "future==0.18.3", "fvcore==0.1.5.post20221221", "gdown==4.7.1", "gfpgan==1.3.8", "gitdb==4.0.11", "gitpython==3.1.32", "google-auth-oauthlib==1.2.0", "google-auth==2.25.2", "gradio-client==0.5.0", "gradio==3.41.2", "grpcio==1.60.0", "h11==0.12.0", "httpcore==0.15.0", "httpx==0.24.1", "huggingface-hub==0.20.1", "humanfriendly==10.0", "idna==3.6", "imageio==2.33.1", "importlib-metadata==7.0.1", "importlib-resources==6.1.1", "inflection==0.5.1", "insightface==0.7.3", "iopath==0.1.9", "jinja2==3.1.2", "joblib==1.3.2", "jsonmerge==1.8.0", "jsonschema-specifications==2023.12.1", "jsonschema==4.20.0", "kiwisolver==1.4.5", "kornia==0.6.7", "lark==1.1.2", "lazy-loader==0.3", "lightning-utilities==0.10.0", "llvmlite==0.41.1", "lmdb==1.4.1", "lpips==0.1.4", "lxml==5.0.0", "markdown-it-py==3.0.0", "markdown==3.5.1", "markupsafe==2.1.3", "matplotlib==3.8.2", "mdurl==0.1.2", "mediapipe==0.10.9", "mpmath==1.3.0", "multidict==6.0.4", "networkx==3.2.1", "numba==0.58.1", "numpy==1.23.5", "oauthlib==3.2.2", "omegaconf==2.2.3", "onnx==1.15.0", "onnxruntime-gpu==1.16.3", "open-clip-torch==2.20.0", "opencv-contrib-python==4.8.1.78", "opencv-python-headless==4.8.1.78", "opencv-python==4.8.1.78", "orjson==3.9.10", "packaging==23.2", "pandas==2.1.4", "piexif==1.1.3", "pillow==9.5.0", "pip==23.3.2", "platformdirs==4.1.0", "portalocker==2.8.2", "prettytable==3.9.0", "protobuf==3.20.3", "psutil==5.9.5", "py-cpuinfo==9.0.0", "pyasn1-modules==0.3.0", "pyasn1==0.5.1", "pycparser==2.21", "pydantic==1.10.13", "pydub==0.25.1", "pygments==2.17.2", "pyparsing==3.1.1", "pyreadline3==3.4.1", "pysocks==1.7.1", "python-dateutil==2.8.2", "python-multipart==0.0.6", "pytorch-lightning==1.9.4", "pytz==2023.3.post1", "pywavelets==1.5.0", "pywin32==306", "pyyaml==6.0.1", "qudida==0.0.4", "realesrgan==0.3.0", "referencing==0.32.0", "regex==2023.12.25", "reportlab==4.0.8", "requests-oauthlib==1.3.1", "requests==2.31.0", "resize-right==0.0.2", "rich==13.7.0", "rpds-py==0.16.2", "rsa==4.9", "safetensors==0.3.1", "scikit-image==0.21.0", "scikit-learn==1.3.2", "scipy==1.11.4", "seaborn==0.13.0", "semantic-version==2.10.0", "send2trash==1.8.2", "sentencepiece==0.1.99", "setuptools==63.2.0", "six==1.16.0", "smmap==5.0.1", "sniffio==1.3.0", "sounddevice==0.4.6", "soupsieve==2.5", "starlette==0.26.1", "svglib==1.5.1", "sympy==1.12", "tabulate==0.9.0", "tb-nightly==2.16.0a20231230", "tensorboard-data-server==0.7.2", "termcolor==2.4.0", "tf-keras-nightly==2.16.0.dev2023123010", "thop==0.1.1.post2209072238", "threadpoolctl==3.2.0", "tifffile==2023.12.9", "timm==0.9.2", "tinycss2==1.2.1", "tokenizers==0.13.3", "tomesd==0.1.3", "tomli==2.0.1", "toolz==0.12.0", "torch==2.0.1+cu118", "torchdiffeq==0.2.3", "torchmetrics==1.2.1", "torchsde==0.2.6", "torchvision==0.15.2+cu118", "tqdm==4.66.1", "trampoline==0.1.2", "transformers==4.30.2", "typing-extensions==4.9.0", "tzdata==2023.4", "ultralytics==8.0.231", "urllib3==2.1.0", "uvicorn==0.25.0", "wcwidth==0.2.12", "webencodings==0.5.1", "websockets==11.0.3", "werkzeug==3.0.1", "xformers==0.0.20", "yacs==0.1.8", "yapf==0.40.2", "yarl==1.9.4", "zipp==3.17.0" ] }

Relevant console log

remote: Enumerating objects: 17, done.
remote: Counting objects: 100% (17/17), done.
remote: Compressing objects: 100% (11/11), done.
remote: Total 17 (delta 9), reused 12 (delta 6), pack-reused 0
Unpacking objects: 100% (17/17), 9.21 KiB | 12.00 KiB/s, done.
From https://github.com/AUTOMATIC1111/stable-diffusion-webui
   e4dcdcc9..04a005f0  dev        -> origin/dev
 * [new branch]        paste-infotext-cast-int-as-float -> origin/paste-infotext-cast-int-as-float
Already up to date.
venv "V:\AI_programms\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.7.0
Commit hash: cf2772fab0af5573da775e7437e6acdca424f26e
ReActor preheating... Device: CUDA
Launching Web UI with arguments: --no-half-vae --medvram-sdxl --medvram --xformers --api --theme=dark --port 7861
Style database not found: V:\AI_programms\stable-diffusion-webui\styles.csv
Tag Autocomplete: Could not locate model-keyword extension, Lora trigger word completion will be limited to those added through the extra networks menu.
[-] ADetailer initialized. version: 23.12.0, num models: 10
ControlNet preprocessor location: V:\AI_programms\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads
2024-01-03 20:35:47,197 - ControlNet - INFO - ControlNet v1.1.426
2024-01-03 20:35:47,620 - ControlNet - INFO - ControlNet v1.1.426
Loading FABRIC v0.6.3
20:35:49 - ReActor - STATUS - Running v0.6.0-a4
Loading weights [dd6c6f3f83] from V:\AI_programms\stable-diffusion-webui\models\Stable-diffusion\ProtoVision XL\ProtoVision XL_v0.6.2.0_VAE_SDXL1.0.safetensors
Creating model from config: V:\AI_programms\stable-diffusion-webui\repositories\generative-models\configs\inference\sd_xl_base.yaml
Loading VAE weights specified in settings: V:\AI_programms\stable-diffusion-webui\models\VAE\sdxl_vae.safetensors
Applying attention optimization: sdp... done.
Model loaded in 7.9s (load weights from disk: 1.5s, create model: 0.5s, apply weights to model: 1.2s, load VAE: 0.1s, calculate empty prompt: 4.5s).
Running on local URL:  http://127.0.0.1:7861

To create a public link, set `share=True` in `launch()`.
Startup time: 51.4s (prepare environment: 24.1s, import torch: 3.6s, import gradio: 0.9s, setup paths: 2.1s, initialize shared: 0.4s, other imports: 2.5s, setup codeformer: 0.5s, list SD models: 2.7s, load scripts: 5.7s, create ui: 8.5s, gradio launch: 0.2s).
 69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰                          | 24/35 [00:25<00:09,  1.14it/s]Reusing loaded model ProtoVision XL\ProtoVision XL_v0.6.2.0_VAE_SDXL1.0.safetensors [dd6c6f3f83] to load SDXL\SDXL_v1.0_refiner_0.9vae.safetensors [8d0ce6c016]
Loading weights [8d0ce6c016] from V:\AI_programms\stable-diffusion-webui\models\Stable-diffusion\SDXL\SDXL_v1.0_refiner_0.9vae.safetensors
Creating model from config: V:\AI_programms\stable-diffusion-webui\repositories\generative-models\configs\inference\sd_xl_refiner.yaml
Loading VAE weights specified in settings: V:\AI_programms\stable-diffusion-webui\models\VAE\sdxl_vae.safetensors
Applying attention optimization: sdp... done.
Model loaded in 2.4s (create model: 0.2s, apply weights to model: 1.5s, load VAE: 0.1s, calculate empty prompt: 0.5s).
100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 35/35 [00:41<00:00,  1.20s/it]
20:39:07 - ReActor - STATUS - Working: source face index [0], target face index [0]β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 35/35 [00:36<00:00,  1.01it/s]
20:39:07 - ReActor - STATUS - Using Loaded Source Face Model...
20:39:07 - ReActor - STATUS - Analyzing Target Image...
20:39:09 - ReActor - STATUS - Detecting Source Face, Index = 0
20:39:09 - ReActor - STATUS - Detected: -29- y.o. Female
20:39:10 - ReActor - STATUS - Detecting Target Face, Index = 0
20:39:10 - ReActor - STATUS - Detected: -24- y.o. Female
20:39:10 - ReActor - STATUS - Swapping Source into Target
20:39:11 - ReActor - STATUS - Restoring the face with CodeFormer
Total progress: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 35/35 [00:53<00:00,  1.53s/it]
Reusing loaded model SDXL\SDXL_v1.0_refiner_0.9vae.safetensors [8d0ce6c016] to load ProtoVision XL\ProtoVision XL_v0.6.2.0_VAE_SDXL1.0.safetensors [dd6c6f3f83]
Loading weights [dd6c6f3f83] from V:\AI_programms\stable-diffusion-webui\models\Stable-diffusion\ProtoVision XL\ProtoVision XL_v0.6.2.0_VAE_SDXL1.0.safetensors
Creating model from config: V:\AI_programms\stable-diffusion-webui\repositories\generative-models\configs\inference\sd_xl_base.yaml
Loading VAE weights specified in settings: V:\AI_programms\stable-diffusion-webui\models\VAE\sdxl_vae.safetensors
Applying attention optimization: sdp... done.
Model loaded in 3.7s (create model: 1.1s, apply weights to model: 1.3s, load VAE: 0.1s, calculate empty prompt: 0.9s).
 69%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰                          | 24/35 [08:31<03:52, 21.11s/it]Reusing loaded model ProtoVision XL\ProtoVision XL_v0.6.2.0_VAE_SDXL1.0.safetensors [dd6c6f3f83] to load SDXL\SDXL_v1.0_refiner_0.9vae.safetensors [8d0ce6c016]
Loading weights [8d0ce6c016] from V:\AI_programms\stable-diffusion-webui\models\Stable-diffusion\SDXL\SDXL_v1.0_refiner_0.9vae.safetensors
Creating model from config: V:\AI_programms\stable-diffusion-webui\repositories\generative-models\configs\inference\sd_xl_refiner.yaml
Loading VAE weights specified in settings: V:\AI_programms\stable-diffusion-webui\models\VAE\sdxl_vae.safetensors
Applying attention optimization: sdp... done.
Model loaded in 2.6s (create model: 0.2s, apply weights to model: 1.5s, load VAE: 0.1s, calculate empty prompt: 0.6s).
100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 35/35 [11:51<00:00, 20.32s/it]
20:54:02 - ReActor - STATUS - Working: source face index [0], target face index [0]β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 35/35 [11:35<00:00, 18.34s/it]
20:54:02 - ReActor - STATUS - Using Loaded Source Face Model...
20:54:02 - ReActor - STATUS - Analyzing Target Image...
20:54:03 - ReActor - STATUS - Detecting Source Face, Index = 0
20:54:03 - ReActor - STATUS - Detected: -29- y.o. Female
20:54:03 - ReActor - STATUS - Detecting Target Face, Index = 0
20:54:03 - ReActor - STATUS - Detected: -26- y.o. Female
20:54:03 - ReActor - STATUS - Swapping Source into Target
20:54:03 - ReActor - STATUS - Restoring the face with CodeFormer
Total progress: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 35/35 [11:51<00:00, 20.32s/it]
Total progress: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 35/35 [11:51<00:00, 18.34s/it]

Additional information

No response

Gourieff commented 6 months ago

According to your log you use SDXL + VAE + Refiner To make the generation process comfortable with such workflow you should have 12Gb of VRAM and higher ReActor with CUDA EP can eat about ~0.9Gb of VRAM maximum (this is ~8 times less than can be used by SDXL model loaded into VRAM) If you lack of VRAM and 900Mb make sense - you can switch ReActor to use CPU EP instead of CUDA

Woisek commented 6 months ago

Thanks for this suggestion. And how is it explained, that the first generation is done at a "normal speed" and this "lag" occurs then from the second generation on? Also, this slow down stays, even if ReActor is not used for the next generations. Only a restart of the WebUI solves this problem.

Gourieff commented 6 months ago

Thanks for this suggestion. And how is it explained, that the first generation is done at a "normal speed" and this "lag" occurs then from the second generation on? Also, this slow down stays, even if ReActor is not used for the next generations. Only a restart of the WebUI solves this problem.

A1111 forcefully goes to the lowram mode if you lack of VRAM, otherwise you hardly generate anything after the first attempt This is the feature of the newest NVIDIA drivers (shared memory fallback) You can try to set --medvram-sdxl in the command line arguments of A1111 And also you can try to do this https://nvidia.custhelp.com/app/answers/detail/a_id/5490 - it will increase the performance but will reduce the stability when VRAM is lacked

Most of the newest SDXL models don't need Refiner, you can use them without it and this will save a lot of VRAM during the generation process I usually test ReActor on 6Gb 3060 laptop with SD15 and SDXL models - and yes, every additional extension (you apply to your workflow) can reduce the generation speed, this is common situation if you have not so much of VRAM, but this also depends on how you set your A1111/SD.Next enclosure, what GPU driver you use, how you rate your GPU power (to be sufficient to work with heavy models + additional extensions) and etc... A lot of people asked to make ReActor work on CUDA, I made it, but this costs of VRAM - and that's why I made it switchable Switch to CPU - and ReActor won't reduce your VRAM

Woisek commented 6 months ago

Thanks for this more information.

You can try to set --medvram-sdxl in the command line arguments of A1111

That's already enabled.

And also you can try to do this https://nvidia.custhelp.com/app/answers/detail/a_id/5490 - it will increase the performance but will reduce the stability when VRAM is lacked

Will look into it.

Most of the newest SDXL models don't need Refiner, you can use them without it and it will save a lot of VRAM during the generation process

Yes, but depending on the motif, the added details are worth it. But it's an option.

I usually test ReActor on 6Gb 3060 laptop with SD15 and SDXL models - and yes, every additional extension (you apply to your workflow) can reduce the generation speed, this is common situation if you have not so much of VRAM, but this also depends on how you set your A1111/SD.Next enclosure, what GPU driver you use, how you rate your GPU power (to be sufficient to work with heavy models + additional extensions) and etc...

I just wonder, how much ReActor really adds to the VRAM given the fact, that without ReActor I can generate images in under a minute, no matter how much I generate. And still it doesn't explain why the first use of ReActor is fast, but not after that. According to your explanation, the first generation should already be slow, but this is not the case.

A lot of people asked to make ReActor work on CUDA, I made it, but this costs of VRAM - and that's why I made it switchable Switch to CPU - and ReActor won't reduce your VRAM

How can we switch that to test this? I haven't found such an option in the settings ... ?

Thanks again for this great tool. πŸ‘

Gourieff commented 6 months ago

How can we switch that to test this? I haven't found such an option in the settings ... ?

ΠΈΠ·ΠΎΠ±Ρ€Π°ΠΆΠ΅Π½ΠΈΠ΅

I just wonder, how much ReActor really adds to the VRAM

Theoretically about 0.8-1Gb, but as I've just investigated there's some issue with python's implementation of the ORT-GPU library, and ORT session can eat additional VRAM and it doesn't release VRAM until Exit is initialized https://github.com/microsoft/onnxruntime/issues/9509#issuecomment-951546580 We can try to completely delete the opened session (as an object) after the postprocessing ends πŸ€”, but ReActor will work super slow (each run as like the first run) and all the advantages of using CUDA will disappear And I think in this case we probably have to inject the most part of the code of the Insightface library into ReActor and refactor it to implement this (because every new session opens "inside" the Insightface code)

So, the only applicable solution at the moment is to use CPU Execution Provider if you encounter any VRAM-lack issues because of using ReActor in your workflows

Woisek commented 6 months ago

AH, the settings of ReActor itself ... I was looking in the A1111 settings ... πŸ€ͺ Thanks for that.

Theoretically about 0.8-1Gb, but as I've just investigated there's some issue with python's implementation of the ORT-GPU library, and ORT session can eat additional VRAM and it doesn't release VRAM until Exit is initialized

Okay, so there is an issue. And I'm happy you see a potential solution. πŸ‘

I may add, using the Tiled Diffusion extension which has the possibility to "Free GPU", I experienced the following: Generating images 720x1024 with SDXL takes about 1min. Pressing "Free GPU" frees down to about 2GB of my 8. I did this several times. After I generate an image with ReActor and then pressing "Free GPU", it only frees down to 4GB of 8 and the slowdown kicks in. So, I assume, something stays in VRAM after ReActor has run once.

I don't know, but maybe this helps as information.

Usser2023 commented 1 month ago

Hello, this just happened to me today 1st: I recommend you to not use the the refiner because by experience is not worth It and for any defect the image you generated has you can just change It with inpaint only masked, and takes less than changing models, 2nd: I have i5 11, 8vram gpu, 16gb ram, I generate 720x1024 images in 12 secs with Forge or Comfy UI, (16 secs. with automatic11),If you can I recommend you install Forge since is the same as automatic but faster (It doesn't have the deforum extension available) 3rd: To avoid the ReActor issue what I do is generate a good quantity (If you want) of good images and then apply the face of the person you want so I won't be changing back and forth Hope this helps, have a nice day everyone