lshqqytiger / stable-diffusion-webui-amdgpu

Stable Diffusion web UI
GNU Affero General Public License v3.0
1.8k stars 186 forks source link

[Bug]: AssertionError on assert conversion_footprint and optimizer_footprint when optimizing SD 1.5 checkpoint from Olive tab #348

Closed R-N closed 9 months ago

R-N commented 9 months ago

Checklist

What happened?

Can't optimize checkpoint. Assertion error

    Traceback (most recent call last):
      File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 57, in f
        res = list(func(*args, **kwargs))
      File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 36, in f
        res = func(*args, **kwargs)
      File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 1759, in optimize
        return optimize_sd_from_ckpt(
      File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 92, in optimize_sd_from_ckpt
        optimize(
      File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 358, in optimize
        assert conversion_footprint and optimizer_footprint
    AssertionError

Steps to reproduce the problem

  1. Start webui with these flags: --no-half-vae --opt-sdp-attention --skip-torch-cuda-test --no-half --olive --use-directml
  2. Try to optimize a checkpoint using Olive tab. Only fill the checkpoint file name and uncheck half float.
  3. Wait for it to error

What should have happened?

The checkpoint is optimized

What browsers do you use to access the UI ?

Google Chrome

Sysinfo

Sysinfo ``` { "Platform": "Windows-10-10.0.22621-SP0", "Python": "3.10.0", "Version": "1.7.0", "Commit": "cfa6e40e6d7e290b52940253bf705f282477b890", "Script path": "D:\\stable-diffusion\\stable-diffusion-webui-directml", "Data path": "D:\\stable-diffusion\\stable-diffusion-webui-directml", "Extensions dir": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions", "Checksum": "21192891edeb5c286572a538ff2a8c990c8f399347cce88d56503dd735bc1d66", "Commandline": [ "launch.py", "--no-half-vae", "--opt-sdp-attention", "--skip-torch-cuda-test", "--no-half", "--olive", "--use-directml" ], "Torch env info": { "torch_version": "1.13.1+cpu", "is_debug_build": "False", "cuda_compiled_version": null, "gcc_version": null, "clang_version": null, "cmake_version": null, "os": "Microsoft Windows 11 Pro", "libc_version": "N/A", "python_version": "3.10.0 | packaged by conda-forge | (default, Nov 20 2021, 02:18:13) [MSC v.1916 64 bit (AMD64)] (64-bit runtime)", "python_platform": "Windows-10-10.0.22621-SP0", "is_cuda_available": "False", "cuda_runtime_version": null, "cuda_module_loading": "N/A", "nvidia_driver_version": null, "nvidia_gpu_models": null, "cudnn_version": null, "pip_version": "pip3", "pip_packages": [ "numpy==1.23.5", "open-clip-torch==2.20.0", "pytorch-lightning==1.9.4", "torch==1.13.1", "torch-directml==0.1.13.1.dev230413", "torchdiffeq==0.2.3", "torchmetrics==0.10.3", "torchsde==0.2.6", "torchvision==0.14.1" ], "conda_packages": [ "open-clip-torch 2.20.0 pypi_0 pypi", "pytorch-lightning 1.9.4 pypi_0 pypi", "torch 1.13.1 pypi_0 pypi", "torch-directml 0.1.13.1.dev230413 pypi_0 pypi", "torchdiffeq 0.2.3 pypi_0 pypi", "torchmetrics 0.10.3 pypi_0 pypi", "torchsde 0.2.6 pypi_0 pypi", "torchvision 0.14.1 pypi_0 pypi" ], "hip_compiled_version": "N/A", "hip_runtime_version": "N/A", "miopen_runtime_version": "N/A", "caching_allocator_config": "", "is_xnnpack_available": "True" }, "Exceptions": [ { "exception": "", "traceback": [ [ "D:\\stable-diffusion\\stable-diffusion-webui-directml\\modules\\call_queue.py, line 57, f", "res = list(func(*args, **kwargs))" ], [ "D:\\stable-diffusion\\stable-diffusion-webui-directml\\modules\\call_queue.py, line 36, f", "res = func(*args, **kwargs)" ], [ "D:\\stable-diffusion\\stable-diffusion-webui-directml\\modules\\ui.py, line 1759, optimize", "return optimize_sd_from_ckpt(" ], [ "D:\\stable-diffusion\\stable-diffusion-webui-directml\\modules\\sd_olive_ui.py, line 92, optimize_sd_from_ckpt", "optimize(" ], [ "D:\\stable-diffusion\\stable-diffusion-webui-directml\\modules\\sd_olive_ui.py, line 358, optimize", "assert conversion_footprint and optimizer_footprint" ] ] } ], "CPU": { "model": "AMD64 Family 23 Model 96 Stepping 1, AuthenticAMD", "count logical": 6, "count physical": 6 }, "RAM": { "total": "19GB", "used": "14GB", "free": "5GB" }, "GPU": { "model": "AMD Radeon(TM) Graphics", "total_memory": 5656576 }, "Extensions": [ { "name": "DreamArtist-sd-webui-extension", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\DreamArtist-sd-webui-extension", "version": "12f80775", "branch": "master", "remote": "https://github.com/7eu7d7/DreamArtist-sd-webui-extension" }, { "name": "Stable-Diffusion-WebUI-DirectML", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\Stable-Diffusion-WebUI-DirectML", "version": "f293af43", "branch": "main", "remote": "https://github.com/microsoft/Stable-Diffusion-WebUI-DirectML" }, { "name": "Stable-Diffusion-Webui-Civitai-Helper", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\Stable-Diffusion-Webui-Civitai-Helper", "version": "203cd5a1", "branch": "master", "remote": "https://github.com/zixaphir/Stable-Diffusion-Webui-Civitai-Helper" }, { "name": "a1111-sd-webui-haku-img", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\a1111-sd-webui-haku-img", "version": "197daebe", "branch": "main", "remote": "https://github.com/KohakuBlueleaf/a1111-sd-webui-haku-img" }, { "name": "a1111-sd-webui-locon", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\a1111-sd-webui-locon", "version": "b6911354", "branch": "main", "remote": "https://github.com/KohakuBlueleaf/a1111-sd-webui-locon" }, { "name": "a1111-sd-webui-tagcomplete", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\a1111-sd-webui-tagcomplete", "version": "c659ed21", "branch": "main", "remote": "https://github.com/DominikDoom/a1111-sd-webui-tagcomplete" }, { "name": "adetailer", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\adetailer", "version": "f1dfb34e", "branch": "main", "remote": "https://github.com/Bing-su/adetailer" }, { "name": "custom-diffusion-webui", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\custom-diffusion-webui", "version": "006e46f6", "branch": "master", "remote": "https://github.com/guaneec/custom-diffusion-webui" }, { "name": "multidiffusion-upscaler-for-automatic1111", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\multidiffusion-upscaler-for-automatic1111", "version": "fbb24736", "branch": "main", "remote": "https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111" }, { "name": "openpose-editor", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\openpose-editor", "version": "c9357715", "branch": "master", "remote": "https://github.com/fkunn1326/openpose-editor" }, { "name": "posex", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\posex", "version": "292f92d5", "branch": "master", "remote": "https://github.com/hnmr293/posex" }, { "name": "sd-dynamic-prompts", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\sd-dynamic-prompts", "version": "284d3ef3", "branch": "main", "remote": "https://github.com/adieyal/sd-dynamic-prompts" }, { "name": "sd-webui-controlnet", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\sd-webui-controlnet", "version": "73f53197", "branch": "main", "remote": "https://github.com/Mikubill/sd-webui-controlnet" }, { "name": "sd-webui-infinite-image-browsing", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\sd-webui-infinite-image-browsing", "version": "fed7cf41", "branch": "main", "remote": "https://github.com/zanllp/sd-webui-infinite-image-browsing" }, { "name": "sd-webui-llul", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\sd-webui-llul", "version": "6c5ac1b0", "branch": "master", "remote": "https://github.com/hnmr293/sd-webui-llul" }, { "name": "sd-webui-lora-block-weight", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\sd-webui-lora-block-weight", "version": "885db951", "branch": "main", "remote": "https://github.com/hako-mikan/sd-webui-lora-block-weight" }, { "name": "sd-webui-regional-prompter", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\sd-webui-regional-prompter", "version": "3a759b72", "branch": "main", "remote": "https://github.com/hako-mikan/sd-webui-regional-prompter" }, { "name": "sd-webui-supermerger", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\sd-webui-supermerger", "version": "f2be9fa8", "branch": "main", "remote": "https://github.com/hako-mikan/sd-webui-supermerger" }, { "name": "shift-attention", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\shift-attention", "version": "0129f6b9", "branch": "main", "remote": "https://github.com/yownas/shift-attention" }, { "name": "stable-diffusion-webui-aesthetic-gradients", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\stable-diffusion-webui-aesthetic-gradients", "version": "2624e5dd", "branch": "master", "remote": "https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients" }, { "name": "stable-diffusion-webui-anti-burn", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\stable-diffusion-webui-anti-burn", "version": "6f4bf0a7", "branch": "master", "remote": "https://github.com/klimaleksus/stable-diffusion-webui-anti-burn" }, { "name": "stable-diffusion-webui-composable-lora", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\stable-diffusion-webui-composable-lora", "version": "d4963e48", "branch": "main", "remote": "https://github.com/opparco/stable-diffusion-webui-composable-lora" }, { "name": "stable-diffusion-webui-embedding-merge", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\stable-diffusion-webui-embedding-merge", "version": "c3cdd9ac", "branch": "master", "remote": "https://github.com/klimaleksus/stable-diffusion-webui-embedding-merge" }, { "name": "stable-diffusion-webui-sonar", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\stable-diffusion-webui-sonar", "version": "15f92859", "branch": "main", "remote": "https://github.com/Kahsolt/stable-diffusion-webui-sonar" }, { "name": "stable-diffusion-webui-two-shot", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\stable-diffusion-webui-two-shot", "version": "9936c52e", "branch": "main", "remote": "https://github.com/opparco/stable-diffusion-webui-two-shot" }, { "name": "stable-diffusion-webui-wildcards", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\stable-diffusion-webui-wildcards", "version": "c7d49e18", "branch": "master", "remote": "https://github.com/AUTOMATIC1111/stable-diffusion-webui-wildcards" }, { "name": "ultimate-upscale-for-automatic1111", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\ultimate-upscale-for-automatic1111", "version": "728ffcec", "branch": "master", "remote": "https://github.com/Coyote-A/ultimate-upscale-for-automatic1111" } ], "Inactive extensions": [ { "name": "prompt-fusion-extension", "path": "D:\\stable-diffusion\\stable-diffusion-webui-directml\\extensions\\prompt-fusion-extension", "version": "1d86996a", "branch": "main", "remote": "https://github.com/ljleb/prompt-fusion-extension" } ], "Environment": { "COMMANDLINE_ARGS": "--no-half-vae --opt-sdp-attention --skip-torch-cuda-test --no-half --olive --use-directml", "GRADIO_ANALYTICS_ENABLED": "False" }, "Config": { "samples_save": true, "samples_format": "png", "samples_filename_pattern": "[seed]-[model_name]", "grid_save": true, "grid_format": "png", "grid_extended_filename": false, "grid_only_if_multiple": true, "grid_prevent_empty_spots": false, "n_rows": -1, "enable_pnginfo": true, "save_txt": false, "save_images_before_face_restoration": false, "jpeg_quality": 80, "export_for_4chan": true, "use_original_name_batch": false, "save_selected_only": true, "do_not_add_watermark": false, "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", "save_to_dirs": false, "grid_save_to_dirs": false, "use_save_to_dirs_for_ui": false, "directories_filename_pattern": "", "directories_max_prompt_words": 8, "ESRGAN_tile": 192, "ESRGAN_tile_overlap": 8, "realesrgan_enabled_models": [ "R-ESRGAN x4+", "R-ESRGAN x4+ Anime6B" ], "SWIN_tile": 192, "SWIN_tile_overlap": 8, "ldsr_steps": 100, "upscaler_for_img2img": null, "use_scale_latent_for_hires_fix": false, "face_restoration_model": null, "code_former_weight": 0.7, "face_restoration_unload": false, "memmon_poll_rate": 8, "samples_log_stdout": false, "multiple_tqdm": true, "unload_models_when_training": true, "dataset_filename_word_regex": "", "dataset_filename_join_string": " ", "training_image_repeats_per_epoch": 1, "training_write_csv_every": 9.0, "sd_model_checkpoint": "oMix_pruned", "sd_checkpoint_cache": 0, "sd_hypernetwork": "", "sd_hypernetwork_strength": 1, "img2img_color_correction": false, "save_images_before_color_correction": false, "img2img_fix_steps": false, "enable_quantization": false, "enable_emphasis": true, "use_old_emphasis_implementation": false, "enable_batch_seeds": true, "comma_padding_backtrack": 20, "filter_nsfw": false, "CLIP_stop_at_last_layers": 2, "random_artist_categories": [], "interrogate_keep_models_in_memory": false, "interrogate_use_builtin_artists": true, "interrogate_return_ranks": false, "interrogate_clip_num_beams": 1, "interrogate_clip_min_length": 24, "interrogate_clip_max_length": 48, "interrogate_clip_dict_limit": 1500.0, "interrogate_deepbooru_score_threshold": 0.5, "deepbooru_sort_alpha": false, "deepbooru_use_spaces": true, "deepbooru_escape": true, "show_progressbar": true, "show_progress_every_n_steps": 0, "return_grid": true, "do_not_show_images": false, "add_model_hash_to_info": true, "add_model_name_to_info": true, "font": "", "js_modal_lightbox": true, "js_modal_lightbox_initially_zoomed": true, "show_progress_in_title": true, "quicksettings": "sd_model_checkpoint, sd_hypernetwork, sd_hypernetwork_strength, aesthetic_embedding, aesthetic_embedding_steps, training_write_csv_every, sd_vae, sd_lora, extra_networks_default_multiplier", "hide_samplers": [], "eta_ddim": 0.0022321428125, "eta_ancestral": 0.0022321428125, "ddim_discretize": "uniform", "s_churn": 0, "s_tmin": 0, "s_noise": 1, "eta_noise_seed_delta": 31337, "localization": "None", "disable_weights_auto_swap": false, "save_images_add_number": true, "show_progress_grid": true, "sd_vae": "None", "inpainting_mask_weight": 1, "send_seed": true, "training_xattention_optimizations": false, "save_images_before_highres_fix": false, "sd_base_vae_cache": "file", "sd_vae_as_default": false, "embedding_blacklist": [ "senran kagura new-1000.pt", "senran kagura new-1500.pt", "senran kagura new-500.pt", "senran kagura new-2500.pt", "senran kagura new-2000.pt", "senran kagura new-3000.pt", "kokomi_wd.pt" ], "disabled_extensions": [ "prompt-fusion-extension" ], "shuffle_tags": false, "tag_drop_out": 0, "save_optimizer_state": false, "dataset_editor_image_columns": 6.0, "images_history_preload": false, "images_history_page_columns": 6.0, "images_history_page_rows": 6.0, "images_history_pages_perload": 20.0, "pin_memory": false, "temp_dir": "", "clean_temp_dir_at_start": false, "tac_tagFile": "danbooru.csv", "tac_active": true, "tac_activeIn.txt2img": true, "tac_activeIn.img2img": true, "tac_activeIn.negativePrompts": true, "tac_maxResults": 5.0, "tac_showAllResults": false, "tac_resultStepLength": 100.0, "tac_delayTime": 100.0, "tac_useWildcards": true, "tac_useEmbeddings": true, "tac_replaceUnderscores": true, "tac_escapeParentheses": true, "tac_appendComma": true, "tac_alias.searchByAlias": true, "tac_alias.onlyShowAlias": false, "tac_translation.translationFile": "None", "tac_translation.oldFormat": false, "tac_translation.searchByTranslation": true, "tac_extra.extraFile": "None", "tac_extra.onlyAliasExtraFile": false, "booru_prompts_danbooru_username": "", "booru_prompts_danbooru_apikey": "", "booru_prompts_use_safebooru": true, "booru_prompts_namespaces": "character, general", "booru_prompts_use_large_preview": false, "booru_prompts_validate_api_access": true, "sd_checkpoint_hash": "39ee30561fb851b682a081fd8a59a9db71aa33fff3db1d24632d6b68921d2d5b", "use_upscaler_name_as_suffix": false, "ldsr_cached": false, "show_warnings": false, "print_hypernet_extra": false, "save_training_settings_to_txt": true, "training_enable_tensorboard": false, "training_tensorboard_save_images": false, "training_tensorboard_flush_every": 120.0, "sd_vae_checkpoint_cache": 0, "initial_noise_multiplier": 1, "img2img_background_color": "#ffffff", "upcast_attn": false, "use_old_karras_scheduler_sigmas": false, "use_old_hires_fix_width_height": false, "interrogate_clip_skip_categories": [], "deepbooru_filter_tags": "", "extra_networks_default_view": "cards", "extra_networks_default_multiplier": 1, "sd_lora": "", "lora_apply_to_outputs": false, "send_size": true, "samplers_in_dropdown": true, "dimensions_and_batch_together": true, "keyedit_precision_attention": 0.1, "keyedit_precision_extra": 0.05, "ui_reorder": "inpaint, sampler, checkboxes, hires_fix, dimensions, cfg, seed, batch, override_settings, scripts", "ui_extra_networks_tab_reorder": "", "live_previews_enable": true, "show_progress_type": "Approx NN", "live_preview_content": "Prompt", "live_preview_refresh_period": 1000.0, "always_discard_next_to_last_sigma": false, "postprocessing_enable_in_main_ui": [], "postprocessing_operation_order": [], "upscaling_max_images_in_cache": 5, "hakuimg_layer_num": 5.0, "hakuimg_curve_points": 3.0, "tac_activeIn.thirdParty": true, "tac_activeIn.modelList": "", "tac_activeIn.modelListMode": "Blacklist", "tac_useHypernetworks": true, "tac_useLoras": true, "tac_showWikiLinks": false, "tac_extra.addMode": "Insert before", "dp_ignore_whitespace": false, "dp_write_raw_template": false, "dp_write_prompts_to_file": false, "dp_parser_variant_start": "{", "dp_parser_variant_end": "}", "wildcards_same_seed": false, "control_net_model_config": "/content/nai/stable-diffusion-webui/extensions/sd-webui-controlnet/models/cldm_v15.yaml", "control_net_models_path": "", "control_net_control_transfer": false, "control_net_no_detectmap": false, "control_net_only_midctrl_hires": true, "control_net_allow_script_control": false, "restore_config_state_file": "", "sd_vae_overrides_per_model_preferences": true, "quicksettings_list": [ "sd_model_checkpoint", "sd_hypernetwork", "sd_hypernetwork_strength", "aesthetic_embedding", "aesthetic_embedding_steps", "training_write_csv_every", "sd_vae", "sd_lora", "extra_networks_default_multiplier" ], "ui_reorder_list": [ "inpaint", "sampler", "checkboxes", "hires_fix", "dimensions", "cfg", "seed", "batch", "override_settings", "scripts" ], "SCUNET_tile": 256, "SCUNET_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, "directml_static_dims": true, "ch_civiai_api_key": "", "ch_dl_lyco_to_lora": false, "ch_open_url_with_js": true, "ch_hide_buttons": [], "ch_always_display": false, "ch_show_btn_on_thumb": true, "ch_max_size_preview": true, "ch_nsfw_preview_threshold": "Allow All", "ch_dl_webui_metadata": true, "ch_proxy": "", "tac_slidingPopup": true, "tac_sortWildcardResults": true, "tac_wildcardExclusionList": "", "tac_skipWildcardRefresh": false, "tac_includeEmbeddingsInNormalResults": false, "tac_useLycos": true, "tac_useLoraPrefixForLycos": true, "tac_showExtraNetworkPreviews": true, "tac_modelSortOrder": "Name", "tac_appendSpace": true, "tac_alwaysSpaceAtEnd": true, "tac_modelKeywordCompletion": "Never", "tac_modelKeywordLocation": "Start of prompt", "tac_wildcardCompletionMode": "To next folder level", "tac_translation.liveTranslation": false, "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", "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, "control_net_detectedmap_dir": "detected_maps", "control_net_modules_path": "", "control_net_unit_count": 3, "control_net_model_cache_size": 1, "control_net_inpaint_blur_sigma": 7, "control_net_detectmap_autosaving": 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, "regprp_debug": false, "regprp_hidepmask": false, "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, "disable_all_extensions": "all" }, "Startup": { "total": 29.05458354949951, "records": { "initial startup": 0.07833147048950195, "prepare environment/checks": 0.012108087539672852, "prepare environment/git version info": 0.07621240615844727, "prepare environment/clone repositores": 0.23178887367248535, "prepare environment/run extensions installers": 0.018269062042236328, "prepare environment": 0.3898639678955078, "launcher": 0.004682064056396484, "import torch": 5.045473337173462, "import gradio": 3.5322437286376953, "setup paths": 16.084914684295654, "import ldm": 0.010534286499023438, "import sgm": 0.0, "initialize shared": 1.3337302207946777, "other imports": 0.3000617027282715, "opts onchange": 0.0009348392486572266, "setup SD model": 0.0025162696838378906, "setup codeformer": 0.15128827095031738, "setup gfpgan": 0.0405116081237793, "set samplers": 0.0, "list extensions": 0.005427360534667969, "restore config state file": 0.0, "list SD models": 0.001119852066040039, "list localizations": 0.0, "load scripts/custom_code.py": 0.002012968063354492, "load scripts/img2imgalt.py": 0.0013098716735839844, "load scripts/loopback.py": 0.0008676052093505859, "load scripts/outpainting_mk_2.py": 0.0006120204925537109, "load scripts/poor_mans_outpainting.py": 0.0007328987121582031, "load scripts/postprocessing_caption.py": 0.0005593299865722656, "load scripts/postprocessing_codeformer.py": 0.0005240440368652344, "load scripts/postprocessing_create_flipped_copies.py": 0.0006175041198730469, "load scripts/postprocessing_focal_crop.py": 0.0011205673217773438, "load scripts/postprocessing_gfpgan.py": 0.0, "load scripts/postprocessing_split_oversized.py": 0.0010025501251220703, "load scripts/postprocessing_upscale.py": 0.00125885009765625, "load scripts/processing_autosized_crop.py": 0.0008282661437988281, "load scripts/prompt_matrix.py": 0.0003647804260253906, "load scripts/prompts_from_file.py": 0.0, "load scripts/sd_upscale.py": 0.0010614395141601562, "load scripts/xyz_grid.py": 0.0032355785369873047, "load scripts/refiner.py": 0.0010023117065429688, "load scripts/seed.py": 0.0019207000732421875, "load scripts": 0.019031286239624023, "load upscalers": 0.0028150081634521484, "refresh VAE": 0.001003265380859375, "refresh textual inversion templates": 0.0011374950408935547, "scripts list_optimizers": 0.4852755069732666, "scripts list_unets": 0.0, "reload hypernetworks": 0.0010001659393310547, "initialize extra networks": 0.006008148193359375, "scripts before_ui_callback": 0.0, "create ui": 1.3503918647766113, "gradio launch": 0.2568984031677246, "add APIs": 0.010008811950683594, "app_started_callback": 0.0 } }, "Packages": [ "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", "alembic==1.12.0", "altair==5.2.0", "antlr4-python3-runtime==4.9.3", "anyio==3.7.1", "argcomplete==2.0.0", "argon2-cffi-bindings==21.2.0", "argon2-cffi==23.1.0", "arrow==1.3.0", "asttokens==2.4.0", "astunparse==1.6.3", "async-lru==2.0.4", "async-timeout==4.0.3", "atomicwrites==1.4.1", "attrs==23.1.0", "babel==2.12.1", "backcall==0.2.0", "backports.functools-lru-cache==1.6.5", "bagit-profile==1.3.1", "bagit==1.8.1", "basicsr==1.4.2", "bbox-visualizer==0.1.0", "bcrypt==4.1.2", "beanie==1.23.6", "beautifulsoup4==4.12.2", "bleach==6.0.0", "blendmodes==2022", "blinker==1.7.0", "boltons==23.1.1", "bottle==0.12.25", "brotli==1.1.0", "cached-property==1.5.2", "cachetools==5.3.2", "cattrs==23.2.3", "certifi==2023.7.22", "cffi==1.16.0", "chardet==5.2.0", "charset-normalizer==3.2.0", "clean-fid==0.1.35", "click==8.1.3", "clip==1.0", "cmaes==0.10.0", "colorama==0.4.6", "coloredlogs==15.0.1", "colorlog==6.7.0", "comm==0.1.4", "contourpy==1.2.0", "coremltools==7.1", "cssselect2==0.7.0", "cycler==0.12.1", "datasets==2.16.1", "debugpy==1.8.0", "decorator==5.1.1", "defusedxml==0.7.1", "deprecated==1.2.0", "deprecation==2.1.0", "diffusers==0.25.0", "dill==0.3.7", "dinglehopper==0.9.4", "dnspython==2.4.2", "docker==7.0.0", "dynamicprompts==0.30.4", "einops==0.4.1", "entrypoints==0.4", "exceptiongroup==1.1.3", "executing==1.2.0", "facexlib==0.3.0", "fastapi==0.94.0", "fastjsonschema==2.18.1", "ffmpy==0.3.1", "filelock==3.13.1", "filetype==1.2.0", "filterpy==1.4.5", "flask==3.0.0", "flatbuffers==23.5.26", "fonttools==4.45.1", "fqdn==1.5.1", "frozendict==2.3.10", "frozenlist==1.4.1", "fsspec==2023.10.0", "ftfy==6.1.3", "future==0.18.3", "fvcore==0.1.5.post20221221", "gast==0.5.4", "gdown==4.7.1", "gfpgan==1.3.8", "gitdb==4.0.11", "gitpython==3.1.32", "google-auth-oauthlib==1.1.0", "google-auth==2.23.4", "google-pasta==0.2.0", "gradio-client==0.5.0", "gradio==3.41.2", "greenlet==2.0.2", "grpcio==1.59.3", "h11==0.12.0", "h5py==3.10.0", "httpcore==0.15.0", "httpx==0.24.1", "huggingface-hub==0.20.1", "humanfriendly==10.0", "idna==3.4", "imageio-ffmpeg==0.4.9", "imageio==2.33.0", "imgviz==1.7.4", "importlib-metadata==6.8.0", "importlib-resources==6.1.0", "inflection==0.5.1", "invisible-watermark==0.2.0", "iopath==0.1.9", "ipykernel==6.25.2", "ipython-genutils==0.2.0", "ipython==8.16.0", "ipywidgets==8.1.1", "isoduration==20.11.0", "itsdangerous==2.1.2", "jedi==0.19.0", "jinja2==3.1.2", "joblib==1.3.2", "json5==0.9.14", "jsonmerge==1.8.0", "jsonpointer==2.4", "jsonschema-specifications==2023.7.1", "jsonschema==4.19.1", "jupyter-bbox-widget==0.5.0", "jupyter-client==8.3.1", "jupyter-console==6.6.3", "jupyter-contrib-core==0.4.2", "jupyter-core==5.3.2", "jupyter-events==0.7.0", "jupyter-highlight-selected-word==0.2.0", "jupyter-lsp==2.2.0", "jupyter-nbextensions-configurator==0.6.3", "jupyter-server-terminals==0.4.4", "jupyter-server==2.7.3", "jupyter==1.0.0", "jupyterlab-pygments==0.2.2", "jupyterlab-server==2.25.0", "jupyterlab-widgets==3.0.9", "jupyterlab==4.0.6", "kamilib==0.1.13", "keras==2.15.0", "kiwisolver==1.4.5", "kornia==0.6.7", "kraken==4.3.5", "labelme==5.3.1", "lark==1.1.2", "lazy-loader==0.3", "lazy-model==0.2.0", "levenshtein==0.20.9", "libclang==16.0.6", "lightning-utilities==0.10.0", "llvmlite==0.41.1", "lmdb==1.4.1", "lpips==0.1.4", "lxml==4.9.3", "mako==1.2.4", "markdown-it-py==3.0.0", "markdown==3.5.1", "markupsafe==2.1.3", "matplotlib-inline==0.1.6", "matplotlib==3.8.2", "mdurl==0.1.2", "mediapipe==0.10.9", "memory-profiler==0.61.0", "mistune==3.0.1", "ml-dtypes==0.2.0", "motor==3.3.2", "mpmath==1.3.0", "multidict==6.0.4", "multimethod==1.3", "multiprocess==0.70.15", "natsort==8.4.0", "nbclient==0.8.0", "nbconvert==7.8.0", "nbformat==5.9.2", "nest-asyncio==1.5.6", "networkx==3.2.1", "notebook-shim==0.2.3", "notebook==7.0.4", "numba==0.58.1", "numpy==1.23.5", "oauthlib==3.2.2", "ocrd-modelfactory==2.60.1", "ocrd-models==2.60.1", "ocrd-network==2.60.1", "ocrd-utils==2.60.1", "ocrd-validators==2.60.1", "ocrd==2.60.1", "olive-ai==0.4.0", "omegaconf==2.2.3", "onnx==1.15.0", "onnxruntime-directml==1.16.3", "open-clip-torch==2.20.0", "opencv-contrib-python==4.9.0.80", "opencv-python-headless==4.8.1.78", "opencv-python==4.8.1.78", "opt-einsum==3.3.0", "optimum==1.16.1", "optuna-dashboard==0.12.0", "optuna==3.3.0", "orjson==3.9.10", "overrides==7.4.0", "packaging==23.1", "pandas==2.1.3", "pandocfilters==1.5.0", "paramiko==3.4.0", "parso==0.8.3", "patsy==0.5.4", "pickleshare==0.7.5", "piexif==1.1.3", "pika==1.3.2", "pillow==9.5.0", "pip==23.3.1", "pkgutil-resolve-name==1.3.10", "platformdirs==3.10.0", "ply==3.11", "portalocker==2.8.2", "prometheus-client==0.17.1", "prompt-toolkit==3.0.39", "protobuf==3.20.3", "psutil==5.9.5", "pure-eval==0.2.2", "py-cpuinfo==9.0.0", "pyaml==23.9.7", "pyarrow-hotfix==0.6", "pyarrow==14.0.2", "pyasn1-modules==0.3.0", "pyasn1==0.5.1", "pycparser==2.21", "pydantic==1.10.13", "pydub==0.25.1", "pyfunctional==1.4.3", "pygments==2.16.1", "pylabel==0.1.55", "pymongo==4.6.1", "pynacl==1.5.0", "pyparsing==3.1.1", "pyqt5-qt5==5.15.2", "pyqt5-sip==12.13.0", "pyqt5==5.15.10", "pyreadline3==3.4.1", "pysocks==1.7.1", "python-bidi==0.4.2", "python-dateutil==2.8.2", "python-dotenv==1.0.0", "python-json-logger==2.0.7", "python-magic==0.4.27", "python-multipart==0.0.6", "pytorch-lightning==1.9.4", "pytz==2023.3.post1", "pywavelets==1.5.0", "pywin32==306", "pywinpty==2.0.11", "pyyaml==6.0.1", "pyzmq==25.1.1", "qtconsole==5.4.4", "qtpy==2.4.1", "rapidfuzz==2.15.2", "realesrgan==0.3.0", "referencing==0.30.2", "regex==2023.10.3", "reportlab==4.0.8", "requests-oauthlib==1.3.1", "requests-unixsocket==0.3.0", "requests==2.31.0", "resize-right==0.0.2", "rfc3339-validator==0.1.4", "rfc3986-validator==0.1.1", "rich==13.7.0", "rpds-py==0.10.3", "rsa==4.9", "safetensors==0.3.1", "scikit-image==0.21.0", "scikit-learn==1.3.1", "scipy==1.11.3", "seaborn==0.13.0", "semantic-version==2.10.0", "send2trash==1.8.2", "sentencepiece==0.1.99", "setuptools==68.2.2", "shapely==1.8.5", "sip==6.7.11", "six==1.16.0", "smmap==5.0.1", "sniffio==1.3.0", "sounddevice==0.4.6", "soupsieve==2.5", "sparklines==0.4.2", "sqlalchemy==2.0.21", "stack-data==0.6.2", "starlette==0.26.1", "statsmodels==0.14.0", "svglib==1.5.1", "sympy==1.12", "tabulate==0.9.0", "tb-nightly==2.16.0a20240101", "tensorboard-data-server==0.7.2", "tensorboard==2.15.1", "tensorflow-estimator==2.15.0", "tensorflow-intel==2.15.0", "tensorflow-io-gcs-filesystem==0.31.0", "tensorflow==2.15.0", "termcolor==1.1.0", "terminado==0.17.0", "tf-keras-nightly==2.16.0.dev2023123010", "thop==0.1.1.post2209072238", "threadpoolctl==3.2.0", "tifffile==2023.9.26", "timm==0.9.2", "tinycss2==1.2.1", "tokenizers==0.13.3", "tomesd==0.1.3", "toml==0.10.2", "tomli==2.0.1", "toolz==0.12.0", "torch-directml==0.1.13.1.dev230413", "torch==1.13.1", "torchdiffeq==0.2.3", "torchmetrics==0.10.3", "torchsde==0.2.6", "torchvision==0.14.1", "tornado==6.3.3", "tqdm==4.66.1", "traitlets==5.10.1", "trampoline==0.1.2", "transformers==4.30.2", "types-python-dateutil==2.8.19.14", "typing-extensions==4.8.0", "typing-utils==0.1.0", "tzdata==2023.3", "ultralytics==8.0.232", "unidecode==1.3.4", "uniseg==0.7.2", "uri-template==1.3.0", "urllib3==2.0.5", "userpath==1.8.0", "uvicorn==0.24.0.post1", "wcwidth==0.2.12", "webcolors==1.13", "webencodings==0.5.1", "websocket-client==1.6.3", "websockets==11.0.3", "werkzeug==3.0.1", "wheel==0.41.2", "widgetsnbextension==4.0.9", "win-inet-pton==1.1.0", "wrapt==1.14.1", "xgboost==2.0.2", "xxhash==3.4.1", "yacs==0.1.8", "yapf==0.40.2", "yarl==1.9.4", "yolosplitter==0.4.5", "zipp==3.17.0" ] } ```

Console logs

Console logs ``` (sdwebui) D:\stable-diffusion\stable-diffusion-webui-directml>webui-user2 fatal: No names found, cannot describe anything. Python 3.10.0 | packaged by conda-forge | (default, Nov 20 2021, 02:18:13) [MSC v.1916 64 bit (AMD64)] Version: 1.7.0 Commit hash: cfa6e40e6d7e290b52940253bf705f282477b890 Launching Web UI with arguments: --no-half-vae --opt-sdp-attention --skip-torch-cuda-test --no-half --olive --use-directml 2024-01-02 02:51:17.143597: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. WARNING:tensorflow:From C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead. no module 'xformers'. Processing without... No SDP backend available, likely because you are running in pytorch versions < 2.0. In fact, you are using PyTorch 1.13.1+cpu. You might want to consider upgrading. no module 'xformers'. Processing without... --olive was integrated into --onnx. Use --onnx instead. No module 'xformers'. Proceeding without it. ============================================================================== You are running torch 1.13.1+cpu. The program is tested to work with torch 2.0.0. To reinstall the desired version, run with commandline flag --reinstall-torch. Beware that this will cause a lot of large files to be downloaded, as well as there are reports of issues with training tab on the latest version. Use --skip-version-check commandline argument to disable this check. ============================================================================== *** "Disable all extensions" option was set, will not load any extensions *** Model oMix_pruned loaded. Applying attention optimization: InvokeAI... done. D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py:1326: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead. with gr.Row().style(equal_height=False): D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py:1448: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead. with gr.Row().style(equal_height=False): Running on local URL: http://127.0.0.1:7860 To create a public link, set `share=True` in `launch()`. Startup time: 29.1s (prepare environment: 0.4s, import torch: 5.0s, import gradio: 3.5s, setup paths: 16.1s, initialize shared: 1.3s, other imports: 0.3s, setup codeformer: 0.2s, scripts list_optimizers: 0.5s, create ui: 1.4s, gradio launch: 0.3s). C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead. warnings.warn( Optimizing safety_checker [2024-01-02 02:52:38,140] [INFO] [engine.py:179:setup_accelerators] Running workflow on accelerator specs: gpu-dml [2024-01-02 02:52:38,184] [INFO] [engine.py:929:_run_pass] Running pass convert:OnnxConversion C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:284: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if attn_weights.size() != (bsz * self.num_heads, tgt_len, src_len): C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:324: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if attn_output.size() != (bsz * self.num_heads, tgt_len, self.head_dim): [2024-01-02 02:53:04,592] [INFO] [engine.py:929:_run_pass] Running pass optimize:OrtTransformersOptimization [2024-01-02 02:53:43,681] [INFO] [footprint.py:183:create_pareto_frontier] pareto frontier points: 1_OrtTransformersOptimization-0-1f94385ea9940c6a3e4cf02b43af9d6b { "latency-avg": 527.13176 } [2024-01-02 02:53:43,681] [INFO] [engine.py:610:create_pareto_frontier_footprints] Output all 1 models [2024-01-02 02:53:43,682] [INFO] [engine.py:357:run] Run history for gpu-dml: [2024-01-02 02:53:43,691] [INFO] [engine.py:634:dump_run_history] run history: +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ | model_id | parent_model_id | from_pass | duration_sec | metrics | +====================================================================================+====================================================================================+=============================+================+============================+ | 0bc47fe1d38bbc129af422adee1d5d94 | | | | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ | 0_OnnxConversion-0bc47fe1d38bbc129af422adee1d5d94-16f2a37f9cd543024ce55445ffe26e2b | 0bc47fe1d38bbc129af422adee1d5d94 | OnnxConversion | 26.3953 | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ | 1_OrtTransformersOptimization-0-1f94385ea9940c6a3e4cf02b43af9d6b | 0_OnnxConversion-0bc47fe1d38bbc129af422adee1d5d94-16f2a37f9cd543024ce55445ffe26e2b | OrtTransformersOptimization | 19.5134 | { | | | | | | "latency-avg": 527.13176 | | | | | | } | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ [2024-01-02 02:53:43,692] [INFO] [engine.py:372:run] No packaging config provided, skip packaging artifacts Optimized safety_checker Optimizing text_encoder [2024-01-02 02:53:43,715] [INFO] [engine.py:179:setup_accelerators] Running workflow on accelerator specs: gpu-dml [2024-01-02 02:53:43,745] [INFO] [engine.py:929:_run_pass] Running pass convert:OnnxConversion D:\stable-diffusion\stable-diffusion-webui-directml\modules\dml\hijack\transformers.py:13: TracerWarning: torch.tensor results are registered as constants in the trace. You can safely ignore this warning if you use this function to create tensors out of constant variables that would be the same every time you call this function. In any other case, this might cause the trace to be incorrect. min = torch.tensor(torch.finfo(dtype).min, device="cpu") C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:292: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if causal_attention_mask.size() != (bsz, 1, tgt_len, src_len): [2024-01-02 02:53:50,882] [ERROR] [engine.py:1002:_run_pass] Pass run failed. Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\engine\engine.py", line 990, in _run_pass output_model_config = host.run_pass(p, input_model_config, data_root, output_model_path, pass_search_point) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\systems\local.py", line 32, in run_pass output_model = the_pass.run(model, data_root, output_model_path, point) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\olive_pass.py", line 371, in run output_model = self._run_for_config(model, data_root, config, output_model_path) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\onnx\conversion.py", line 121, in _run_for_config return self._convert_model_on_device(model, data_root, config, output_model_path, device, torch_dtype) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\onnx\conversion.py", line 343, in _convert_model_on_device converted_onnx_model = OnnxConversion._export_pytorch_model( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\onnx\conversion.py", line 216, in _export_pytorch_model torch.onnx.export( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 504, in export _export( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 1605, in _export opened_file.write(proto) OSError: [Errno 28] No space left on device [2024-01-02 02:53:50,931] [WARNING] [engine.py:912:_run_passes] Skipping evaluation as model was pruned [2024-01-02 02:53:50,932] [INFO] [engine.py:610:create_pareto_frontier_footprints] Output all 0 models [2024-01-02 02:53:50,934] [INFO] [engine.py:357:run] Run history for gpu-dml: [2024-01-02 02:53:50,934] [INFO] [engine.py:634:dump_run_history] run history: +------------------------------------------------------------------------------------+----------------------------------+----------------+----------------+-----------+ | model_id | parent_model_id | from_pass | duration_sec | metrics | +====================================================================================+==================================+================+================+===========+ | 34c28b143af5f334cba9e8f3bfaf9bc8 | | | | | +------------------------------------------------------------------------------------+----------------------------------+----------------+----------------+-----------+ | 2_OnnxConversion-34c28b143af5f334cba9e8f3bfaf9bc8-16f2a37f9cd543024ce55445ffe26e2b | 34c28b143af5f334cba9e8f3bfaf9bc8 | OnnxConversion | 7.17821 | | +------------------------------------------------------------------------------------+----------------------------------+----------------+----------------+-----------+ [2024-01-02 02:53:50,936] [INFO] [engine.py:372:run] No packaging config provided, skip packaging artifacts *** Error completing request *** Arguments: ('oMix_pruned.safetensors', '', 'vae', 'oMix_pruned', 'oMix_pruned', 'runwayml/stable-diffusion-v1-5', '', 'vae', 'stable-diffusion-v1-5', 'stable-diffusion-v1-5', False, False, False, False, False, True, True, True, True, True, 'euler', False, 512, False, '', '', '') {} Traceback (most recent call last): File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 36, in f res = func(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 1759, in optimize return optimize_sd_from_ckpt( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 92, in optimize_sd_from_ckpt optimize( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 358, in optimize assert conversion_footprint and optimizer_footprint AssertionError --- ```

Additional information

274 is similar but it's SDXL so idk

lshqqytiger commented 9 months ago

OSError: [Errno 28] No space left on device Check your disk space.

R-N commented 9 months ago

OSError: [Errno 28] No space left on device Check your disk space.

Ah sorry, must've been because I tried with other checkpoints too and it got full. Let me try again

R-N commented 9 months ago
Console logs ``` (sdwebui) D:\stable-diffusion\stable-diffusion-webui-directml>webui-user2 fatal: No names found, cannot describe anything. Python 3.10.0 | packaged by conda-forge | (default, Nov 20 2021, 02:18:13) [MSC v.1916 64 bit (AMD64)] Version: 1.7.0 Commit hash: cfa6e40e6d7e290b52940253bf705f282477b890 Launching Web UI with arguments: --no-half-vae --opt-sdp-attention --skip-torch-cuda-test --no-half --olive --use-directml 2024-01-02 12:54:53.626971: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. WARNING:tensorflow:From C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead. no module 'xformers'. Processing without... No SDP backend available, likely because you are running in pytorch versions < 2.0. In fact, you are using PyTorch 1.13.1+cpu. You might want to consider upgrading. no module 'xformers'. Processing without... --olive was integrated into --onnx. Use --onnx instead. No module 'xformers'. Proceeding without it. ============================================================================== You are running torch 1.13.1+cpu. The program is tested to work with torch 2.0.0. To reinstall the desired version, run with commandline flag --reinstall-torch. Beware that this will cause a lot of large files to be downloaded, as well as there are reports of issues with training tab on the latest version. Use --skip-version-check commandline argument to disable this check. ============================================================================== *** "Disable all extensions" option was set, will not load any extensions *** loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 946, in run self._target(*self._args, **self._kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\initialize.py", line 147, in load_model shared.sd_model # noqa: B018 File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load Applying attention optimization: InvokeAI... done. D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py:1326: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead. with gr.Row().style(equal_height=False): D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py:1448: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead. with gr.Row().style(equal_height=False): Running on local URL: http://127.0.0.1:7860 To create a public link, set `share=True` in `launch()`. Startup time: 35.3s (initial startup: 0.1s, prepare environment: 1.5s, import torch: 6.6s, import gradio: 4.7s, setup paths: 18.3s, initialize shared: 1.5s, other imports: 0.3s, setup codeformer: 0.2s, scripts list_optimizers: 0.4s, create ui: 1.3s, gradio launch: 0.3s). loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\anyio\_backends\_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\gradio\utils.py", line 707, in wrapper response = f(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 2393, in visible=shared.sd_model and shared.sd_model.cond_stage_key == "edit" File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\anyio\_backends\_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\gradio\utils.py", line 707, in wrapper response = f(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 36, in f res = func(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 1759, in optimize return optimize_sd_from_ckpt( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 66, in optimize_sd_from_ckpt unoptimized_dir, optimized_dir = ready(unoptimized_dir, optimized_dir) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 34, in ready unload_model_weights(shared.sd_model) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\anyio\_backends\_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\gradio\utils.py", line 707, in wrapper response = f(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 36, in f res = func(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 1759, in optimize return optimize_sd_from_ckpt( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 66, in optimize_sd_from_ckpt unoptimized_dir, optimized_dir = ready(unoptimized_dir, optimized_dir) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 34, in ready unload_model_weights(shared.sd_model) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 882, in unload_model_weights send_model_to_cpu(sd_model or shared.sd_model) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead. warnings.warn( Optimizing safety_checker [2024-01-02 12:56:15,472] [INFO] [engine.py:179:setup_accelerators] Running workflow on accelerator specs: gpu-dml [2024-01-02 12:56:15,505] [INFO] [engine.py:929:_run_pass] Running pass convert:OnnxConversion C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:284: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if attn_weights.size() != (bsz * self.num_heads, tgt_len, src_len): C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:324: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if attn_output.size() != (bsz * self.num_heads, tgt_len, self.head_dim): [2024-01-02 12:56:43,319] [INFO] [engine.py:929:_run_pass] Running pass optimize:OrtTransformersOptimization [2024-01-02 12:57:25,781] [INFO] [footprint.py:183:create_pareto_frontier] pareto frontier points: 1_OrtTransformersOptimization-0-1f94385ea9940c6a3e4cf02b43af9d6b { "latency-avg": 561.96183 } [2024-01-02 12:57:25,781] [INFO] [engine.py:610:create_pareto_frontier_footprints] Output all 1 models [2024-01-02 12:57:25,782] [INFO] [engine.py:357:run] Run history for gpu-dml: [2024-01-02 12:57:25,790] [INFO] [engine.py:634:dump_run_history] run history: +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ | model_id | parent_model_id | from_pass | duration_sec | metrics | +====================================================================================+====================================================================================+=============================+================+============================+ | 0bc47fe1d38bbc129af422adee1d5d94 | | | | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ | 0_OnnxConversion-0bc47fe1d38bbc129af422adee1d5d94-16f2a37f9cd543024ce55445ffe26e2b | 0bc47fe1d38bbc129af422adee1d5d94 | OnnxConversion | 27.8047 | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ | 1_OrtTransformersOptimization-0-1f94385ea9940c6a3e4cf02b43af9d6b | 0_OnnxConversion-0bc47fe1d38bbc129af422adee1d5d94-16f2a37f9cd543024ce55445ffe26e2b | OrtTransformersOptimization | 21.8566 | { | | | | | | "latency-avg": 561.96183 | | | | | | } | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ [2024-01-02 12:57:25,792] [INFO] [engine.py:372:run] No packaging config provided, skip packaging artifacts Optimized safety_checker Optimizing text_encoder [2024-01-02 12:57:25,817] [INFO] [engine.py:179:setup_accelerators] Running workflow on accelerator specs: gpu-dml [2024-01-02 12:57:25,854] [INFO] [engine.py:929:_run_pass] Running pass convert:OnnxConversion D:\stable-diffusion\stable-diffusion-webui-directml\modules\dml\hijack\transformers.py:13: TracerWarning: torch.tensor results are registered as constants in the trace. You can safely ignore this warning if you use this function to create tensors out of constant variables that would be the same every time you call this function. In any other case, this might cause the trace to be incorrect. min = torch.tensor(torch.finfo(dtype).min, device="cpu") C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:292: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if causal_attention_mask.size() != (bsz, 1, tgt_len, src_len): [2024-01-02 12:57:35,576] [INFO] [engine.py:929:_run_pass] Running pass optimize:OrtTransformersOptimization [2024-01-02 12:57:49,323] [INFO] [footprint.py:183:create_pareto_frontier] pareto frontier points: 3_OrtTransformersOptimization-2-4205191dd3b8a5c28264a96ba7dc0dc2 { "latency-avg": 59.53685 } [2024-01-02 12:57:49,323] [INFO] [engine.py:610:create_pareto_frontier_footprints] Output all 1 models [2024-01-02 12:57:49,325] [INFO] [engine.py:357:run] Run history for gpu-dml: [2024-01-02 12:57:49,326] [INFO] [engine.py:634:dump_run_history] run history: +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+---------------------------+ | model_id | parent_model_id | from_pass | duration_sec | metrics | +====================================================================================+====================================================================================+=============================+================+===========================+ | 34c28b143af5f334cba9e8f3bfaf9bc8 | | | | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+---------------------------+ | 2_OnnxConversion-34c28b143af5f334cba9e8f3bfaf9bc8-16f2a37f9cd543024ce55445ffe26e2b | 34c28b143af5f334cba9e8f3bfaf9bc8 | OnnxConversion | 9.71317 | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+---------------------------+ | 3_OrtTransformersOptimization-2-4205191dd3b8a5c28264a96ba7dc0dc2 | 2_OnnxConversion-34c28b143af5f334cba9e8f3bfaf9bc8-16f2a37f9cd543024ce55445ffe26e2b | OrtTransformersOptimization | 9.67545 | { | | | | | | "latency-avg": 59.53685 | | | | | | } | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+---------------------------+ [2024-01-02 12:57:49,327] [INFO] [engine.py:372:run] No packaging config provided, skip packaging artifacts Optimized text_encoder Optimizing unet [2024-01-02 12:57:49,348] [INFO] [engine.py:179:setup_accelerators] Running workflow on accelerator specs: gpu-dml [2024-01-02 12:57:49,379] [INFO] [engine.py:929:_run_pass] Running pass convert:OnnxConversion [2024-01-02 12:58:01,013] [ERROR] [engine.py:1002:_run_pass] Pass run failed. Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\engine\engine.py", line 990, in _run_pass output_model_config = host.run_pass(p, input_model_config, data_root, output_model_path, pass_search_point) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\systems\local.py", line 32, in run_pass output_model = the_pass.run(model, data_root, output_model_path, point) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\olive_pass.py", line 371, in run output_model = self._run_for_config(model, data_root, config, output_model_path) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\onnx\conversion.py", line 121, in _run_for_config return self._convert_model_on_device(model, data_root, config, output_model_path, device, torch_dtype) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\onnx\conversion.py", line 343, in _convert_model_on_device converted_onnx_model = OnnxConversion._export_pytorch_model( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\onnx\conversion.py", line 216, in _export_pytorch_model torch.onnx.export( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 504, in export _export( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 1529, in _export graph, params_dict, torch_out = _model_to_graph( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 1111, in _model_to_graph graph, params, torch_out, module = _create_jit_graph(model, args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 987, in _create_jit_graph graph, torch_out = _trace_and_get_graph_from_model(model, args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 891, in _trace_and_get_graph_from_model trace_graph, torch_out, inputs_states = torch.jit._get_trace_graph( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\jit\_trace.py", line 1184, in _get_trace_graph outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, **kwargs) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\jit\_trace.py", line 127, in forward graph, out = torch._C._create_graph_by_tracing( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\jit\_trace.py", line 114, in wrapper tuple(x.clone(memory_format=torch.preserve_format) for x in args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\jit\_trace.py", line 114, in tuple(x.clone(memory_format=torch.preserve_format) for x in args) RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 14745600 bytes. [2024-01-02 12:58:01,506] [WARNING] [engine.py:912:_run_passes] Skipping evaluation as model was pruned [2024-01-02 12:58:01,509] [INFO] [engine.py:610:create_pareto_frontier_footprints] Output all 0 models [2024-01-02 12:58:01,510] [INFO] [engine.py:357:run] Run history for gpu-dml: [2024-01-02 12:58:01,513] [INFO] [engine.py:634:dump_run_history] run history: +------------------------------------------------------------------------------------+----------------------------------+----------------+----------------+-----------+ | model_id | parent_model_id | from_pass | duration_sec | metrics | +====================================================================================+==================================+================+================+===========+ | 67059446a4f85cf39eb6213217bc76eb | | | | | +------------------------------------------------------------------------------------+----------------------------------+----------------+----------------+-----------+ | 4_OnnxConversion-67059446a4f85cf39eb6213217bc76eb-2c8029b46eea4cc88db3982a7c7e6997 | 67059446a4f85cf39eb6213217bc76eb | OnnxConversion | 12.1141 | | +------------------------------------------------------------------------------------+----------------------------------+----------------+----------------+-----------+ [2024-01-02 12:58:01,514] [INFO] [engine.py:372:run] No packaging config provided, skip packaging artifacts *** Error completing request *** Arguments: ('oMix_pruned.safetensors', '', 'vae', 'oMix_pruned', 'oMix_pruned', 'runwayml/stable-diffusion-v1-5', '', 'vae', 'stable-diffusion-v1-5', 'stable-diffusion-v1-5', True, True, True, True, True, True, True, True, True, True, 'euler', False, 512, False, '', '', '') {} Traceback (most recent call last): File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 36, in f res = func(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 1759, in optimize return optimize_sd_from_ckpt( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 92, in optimize_sd_from_ckpt optimize( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 358, in optimize assert conversion_footprint and optimizer_footprint AssertionError --- ```

RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 14745600 bytes.

How much memory do I need? I'm using integrated GPU, 20GB of RAM, and it's still full. The checkpoint is only 2GB (16 bit, pruned). I'll try with half floats checked. I had to use --no-half because I can't generate any image without it with default settings/args, so I thought half floats on my machine is a no-no.

R-N commented 9 months ago

Still not enough memory. Maybe I'll remove no-half and add lowvram

R-N commented 9 months ago
Console logs ``` (sdwebui) D:\stable-diffusion\stable-diffusion-webui-directml>webui-user2 fatal: No names found, cannot describe anything. Python 3.10.0 | packaged by conda-forge | (default, Nov 20 2021, 02:18:13) [MSC v.1916 64 bit (AMD64)] Version: 1.7.0 Commit hash: cfa6e40e6d7e290b52940253bf705f282477b890 Launching Web UI with arguments: --opt-sdp-attention --skip-torch-cuda-test --olive --use-directml --lowvram 2024-01-02 13:11:13.292964: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. WARNING:tensorflow:From C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead. no module 'xformers'. Processing without... No SDP backend available, likely because you are running in pytorch versions < 2.0. In fact, you are using PyTorch 1.13.1+cpu. You might want to consider upgrading. no module 'xformers'. Processing without... --olive was integrated into --onnx. Use --onnx instead. No module 'xformers'. Proceeding without it. ============================================================================== You are running torch 1.13.1+cpu. The program is tested to work with torch 2.0.0. To reinstall the desired version, run with commandline flag --reinstall-torch. Beware that this will cause a lot of large files to be downloaded, as well as there are reports of issues with training tab on the latest version. Use --skip-version-check commandline argument to disable this check. ============================================================================== *** "Disable all extensions" option was set, will not load any extensions *** loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 946, in run self._target(*self._args, **self._kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\initialize.py", line 147, in load_model shared.sd_model # noqa: B018 File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load Applying attention optimization: InvokeAI... done. D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py:1326: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead. with gr.Row().style(equal_height=False): D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py:1448: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead. with gr.Row().style(equal_height=False): Running on local URL: http://127.0.0.1:7860 To create a public link, set `share=True` in `launch()`. Startup time: 32.1s (prepare environment: 1.3s, import torch: 5.9s, import gradio: 3.6s, setup paths: 16.6s, initialize shared: 1.9s, other imports: 0.3s, setup codeformer: 0.2s, scripts list_optimizers: 0.5s, create ui: 1.4s, gradio launch: 0.3s). loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\anyio\_backends\_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\gradio\utils.py", line 707, in wrapper response = f(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 2393, in visible=shared.sd_model and shared.sd_model.cond_stage_key == "edit" File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\anyio\_backends\_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\gradio\utils.py", line 707, in wrapper response = f(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 36, in f res = func(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 1759, in optimize return optimize_sd_from_ckpt( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 66, in optimize_sd_from_ckpt unoptimized_dir, optimized_dir = ready(unoptimized_dir, optimized_dir) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 34, in ready unload_model_weights(shared.sd_model) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\anyio\_backends\_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\gradio\utils.py", line 707, in wrapper response = f(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 36, in f res = func(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 1759, in optimize return optimize_sd_from_ckpt( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 66, in optimize_sd_from_ckpt unoptimized_dir, optimized_dir = ready(unoptimized_dir, optimized_dir) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 34, in ready unload_model_weights(shared.sd_model) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 882, in unload_model_weights send_model_to_cpu(sd_model or shared.sd_model) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead. warnings.warn( Optimizing safety_checker [2024-01-02 13:12:11,360] [INFO] [engine.py:179:setup_accelerators] Running workflow on accelerator specs: gpu-dml [2024-01-02 13:12:11,403] [INFO] [engine.py:929:_run_pass] Running pass convert:OnnxConversion C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:284: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if attn_weights.size() != (bsz * self.num_heads, tgt_len, src_len): C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:324: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if attn_output.size() != (bsz * self.num_heads, tgt_len, self.head_dim): [2024-01-02 13:12:37,003] [INFO] [engine.py:929:_run_pass] Running pass optimize:OrtTransformersOptimization [2024-01-02 13:13:25,762] [INFO] [footprint.py:183:create_pareto_frontier] pareto frontier points: 1_OrtTransformersOptimization-0-619f2fd5ba69b6cafc9ccf2d841c3b38 { "latency-avg": 443.5449 } [2024-01-02 13:13:25,762] [INFO] [engine.py:610:create_pareto_frontier_footprints] Output all 1 models [2024-01-02 13:13:25,763] [INFO] [engine.py:357:run] Run history for gpu-dml: [2024-01-02 13:13:25,771] [INFO] [engine.py:634:dump_run_history] run history: +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+---------------------------+ | model_id | parent_model_id | from_pass | duration_sec | metrics | +====================================================================================+====================================================================================+=============================+================+===========================+ | 0bc47fe1d38bbc129af422adee1d5d94 | | | | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+---------------------------+ | 0_OnnxConversion-0bc47fe1d38bbc129af422adee1d5d94-16f2a37f9cd543024ce55445ffe26e2b | 0bc47fe1d38bbc129af422adee1d5d94 | OnnxConversion | 25.5918 | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+---------------------------+ | 1_OrtTransformersOptimization-0-619f2fd5ba69b6cafc9ccf2d841c3b38 | 0_OnnxConversion-0bc47fe1d38bbc129af422adee1d5d94-16f2a37f9cd543024ce55445ffe26e2b | OrtTransformersOptimization | 33.1938 | { | | | | | | "latency-avg": 443.5449 | | | | | | } | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+---------------------------+ [2024-01-02 13:13:25,773] [INFO] [engine.py:372:run] No packaging config provided, skip packaging artifacts Optimized safety_checker Optimizing text_encoder [2024-01-02 13:13:25,793] [INFO] [engine.py:179:setup_accelerators] Running workflow on accelerator specs: gpu-dml [2024-01-02 13:13:25,823] [INFO] [engine.py:929:_run_pass] Running pass convert:OnnxConversion D:\stable-diffusion\stable-diffusion-webui-directml\modules\dml\hijack\transformers.py:13: TracerWarning: torch.tensor results are registered as constants in the trace. You can safely ignore this warning if you use this function to create tensors out of constant variables that would be the same every time you call this function. In any other case, this might cause the trace to be incorrect. min = torch.tensor(torch.finfo(dtype).min, device="cpu") C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:292: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if causal_attention_mask.size() != (bsz, 1, tgt_len, src_len): [2024-01-02 13:13:36,181] [INFO] [engine.py:929:_run_pass] Running pass optimize:OrtTransformersOptimization [2024-01-02 13:13:54,481] [INFO] [footprint.py:183:create_pareto_frontier] pareto frontier points: 3_OrtTransformersOptimization-2-62c67214e0d8b2e59c4b857d7f513a48 { "latency-avg": 49.7933 } [2024-01-02 13:13:54,481] [INFO] [engine.py:610:create_pareto_frontier_footprints] Output all 1 models [2024-01-02 13:13:54,482] [INFO] [engine.py:357:run] Run history for gpu-dml: [2024-01-02 13:13:54,483] [INFO] [engine.py:634:dump_run_history] run history: +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+--------------------------+ | model_id | parent_model_id | from_pass | duration_sec | metrics | +====================================================================================+====================================================================================+=============================+================+==========================+ | 34c28b143af5f334cba9e8f3bfaf9bc8 | | | | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+--------------------------+ | 2_OnnxConversion-34c28b143af5f334cba9e8f3bfaf9bc8-16f2a37f9cd543024ce55445ffe26e2b | 34c28b143af5f334cba9e8f3bfaf9bc8 | OnnxConversion | 10.3501 | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+--------------------------+ | 3_OrtTransformersOptimization-2-62c67214e0d8b2e59c4b857d7f513a48 | 2_OnnxConversion-34c28b143af5f334cba9e8f3bfaf9bc8-16f2a37f9cd543024ce55445ffe26e2b | OrtTransformersOptimization | 15.5208 | { | | | | | | "latency-avg": 49.7933 | | | | | | } | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+--------------------------+ [2024-01-02 13:13:54,484] [INFO] [engine.py:372:run] No packaging config provided, skip packaging artifacts Optimized text_encoder Optimizing unet [2024-01-02 13:13:54,505] [INFO] [engine.py:179:setup_accelerators] Running workflow on accelerator specs: gpu-dml [2024-01-02 13:13:54,539] [INFO] [engine.py:929:_run_pass] Running pass convert:OnnxConversion [2024-01-02 13:13:57,080] [ERROR] [engine.py:1002:_run_pass] Pass run failed. Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\engine\engine.py", line 990, in _run_pass output_model_config = host.run_pass(p, input_model_config, data_root, output_model_path, pass_search_point) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\systems\local.py", line 32, in run_pass output_model = the_pass.run(model, data_root, output_model_path, point) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\olive_pass.py", line 371, in run output_model = self._run_for_config(model, data_root, config, output_model_path) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\onnx\conversion.py", line 121, in _run_for_config return self._convert_model_on_device(model, data_root, config, output_model_path, device, torch_dtype) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\onnx\conversion.py", line 343, in _convert_model_on_device converted_onnx_model = OnnxConversion._export_pytorch_model( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\olive\passes\onnx\conversion.py", line 216, in _export_pytorch_model torch.onnx.export( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 504, in export _export( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 1529, in _export graph, params_dict, torch_out = _model_to_graph( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 1111, in _model_to_graph graph, params, torch_out, module = _create_jit_graph(model, args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 987, in _create_jit_graph graph, torch_out = _trace_and_get_graph_from_model(model, args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\onnx\utils.py", line 891, in _trace_and_get_graph_from_model trace_graph, torch_out, inputs_states = torch.jit._get_trace_graph( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\jit\_trace.py", line 1184, in _get_trace_graph outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, **kwargs) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\nn\modules\module.py", line 1194, in _call_impl return forward_call(*input, **kwargs) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\jit\_trace.py", line 127, in forward graph, out = torch._C._create_graph_by_tracing( File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\jit\_trace.py", line 114, in wrapper tuple(x.clone(memory_format=torch.preserve_format) for x in args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\torch\jit\_trace.py", line 114, in tuple(x.clone(memory_format=torch.preserve_format) for x in args) RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 58982400 bytes. [2024-01-02 13:13:57,222] [WARNING] [engine.py:912:_run_passes] Skipping evaluation as model was pruned [2024-01-02 13:13:57,224] [INFO] [engine.py:610:create_pareto_frontier_footprints] Output all 0 models [2024-01-02 13:13:57,226] [INFO] [engine.py:357:run] Run history for gpu-dml: [2024-01-02 13:13:57,227] [INFO] [engine.py:634:dump_run_history] run history: +------------------------------------------------------------------------------------+----------------------------------+----------------+----------------+-----------+ | model_id | parent_model_id | from_pass | duration_sec | metrics | +====================================================================================+==================================+================+================+===========+ | 67059446a4f85cf39eb6213217bc76eb | | | | | +------------------------------------------------------------------------------------+----------------------------------+----------------+----------------+-----------+ | 4_OnnxConversion-67059446a4f85cf39eb6213217bc76eb-2c8029b46eea4cc88db3982a7c7e6997 | 67059446a4f85cf39eb6213217bc76eb | OnnxConversion | 2.67611 | | +------------------------------------------------------------------------------------+----------------------------------+----------------+----------------+-----------+ [2024-01-02 13:13:57,227] [INFO] [engine.py:372:run] No packaging config provided, skip packaging artifacts *** Error completing request *** Arguments: ('oMix_pruned.safetensors', '', 'vae', 'oMix_pruned', 'oMix_pruned', 'runwayml/stable-diffusion-v1-5', '', 'vae', 'stable-diffusion-v1-5', 'stable-diffusion-v1-5', True, True, True, True, True, True, True, True, True, True, 'euler', True, 512, False, '', '', '') {} Traceback (most recent call last): File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 36, in f res = func(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 1759, in optimize return optimize_sd_from_ckpt( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 92, in optimize_sd_from_ckpt optimize( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 358, in optimize assert conversion_footprint and optimizer_footprint AssertionError --- ```

Still can't and this time my C partition gets full although the webui and mamba is in D. I guess it's the pagefile. I'll try freeing up space

lshqqytiger commented 9 months ago

The optimization process requires lots of RAM. You need at least 6GB of VRAM and at least 16GB of RAM, but you're sharing 20GB of RAM with integrated GPU. I recommend using optimized models that can be downloaded from huggingface.

R-N commented 9 months ago

Ok this time it just, idk, crashed? No error or anything. I watched the disk space and I'm sure none were full (lowest were at 5gb free).

Console logs ``` (sdwebui) D:\stable-diffusion\stable-diffusion-webui-directml>webui-user2 fatal: No names found, cannot describe anything. Python 3.10.0 | packaged by conda-forge | (default, Nov 20 2021, 02:18:13) [MSC v.1916 64 bit (AMD64)] Version: 1.7.0 Commit hash: cfa6e40e6d7e290b52940253bf705f282477b890 Launching Web UI with arguments: --opt-sdp-attention --skip-torch-cuda-test --olive --use-directml --lowvram 2024-01-02 13:56:50.232517: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. WARNING:tensorflow:From C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead. no module 'xformers'. Processing without... No SDP backend available, likely because you are running in pytorch versions < 2.0. In fact, you are using PyTorch 1.13.1+cpu. You might want to consider upgrading. no module 'xformers'. Processing without... --olive was integrated into --onnx. Use --onnx instead. No module 'xformers'. Proceeding without it. ============================================================================== You are running torch 1.13.1+cpu. The program is tested to work with torch 2.0.0. To reinstall the desired version, run with commandline flag --reinstall-torch. Beware that this will cause a lot of large files to be downloaded, as well as there are reports of issues with training tab on the latest version. Use --skip-version-check commandline argument to disable this check. ============================================================================== *** "Disable all extensions" option was set, will not load any extensions *** loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 946, in run self._target(*self._args, **self._kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\initialize.py", line 147, in load_model shared.sd_model # noqa: B018 File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load Applying attention optimization: InvokeAI... done. D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py:1326: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead. with gr.Row().style(equal_height=False): D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py:1448: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead. with gr.Row().style(equal_height=False): Running on local URL: http://127.0.0.1:7860 Thanks for being a Gradio user! If you have questions or feedback, please join our Discord server and chat with us: https://discord.gg/feTf9x3ZSB To create a public link, set `share=True` in `launch()`. Startup time: 40.3s (prepare environment: 0.8s, import torch: 9.1s, import gradio: 5.0s, setup paths: 21.0s, initialize shared: 1.6s, other imports: 0.3s, setup codeformer: 0.2s, scripts list_optimizers: 0.5s, create ui: 1.4s, gradio launch: 0.3s). loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\anyio\_backends\_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\gradio\utils.py", line 707, in wrapper response = f(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 2393, in visible=shared.sd_model and shared.sd_model.cond_stage_key == "edit" File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\anyio\_backends\_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\gradio\utils.py", line 707, in wrapper response = f(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 36, in f res = func(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 1759, in optimize return optimize_sd_from_ckpt( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 66, in optimize_sd_from_ckpt unoptimized_dir, optimized_dir = ready(unoptimized_dir, optimized_dir) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 34, in ready unload_model_weights(shared.sd_model) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load loading stable diffusion model: FileNotFoundError Traceback (most recent call last): File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 966, in _bootstrap self._bootstrap_inner() File "C:\Users\Linearch\.conda\envs\sdwebui\lib\threading.py", line 1009, in _bootstrap_inner self.run() File "C:\Users\Linearch\AppData\Roaming\Python\Python310\site-packages\anyio\_backends\_asyncio.py", line 807, in run result = context.run(func, *args) File "C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\gradio\utils.py", line 707, in wrapper response = f(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\call_queue.py", line 36, in f res = func(*args, **kwargs) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\ui.py", line 1759, in optimize return optimize_sd_from_ckpt( File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 66, in optimize_sd_from_ckpt unoptimized_dir, optimized_dir = ready(unoptimized_dir, optimized_dir) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_olive_ui.py", line 34, in ready unload_model_weights(shared.sd_model) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 882, in unload_model_weights send_model_to_cpu(sd_model or shared.sd_model) File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\shared_items.py", line 128, in sd_model return modules.sd_models.model_data.get_sd_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 576, in get_sd_model load_model() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 664, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\stable-diffusion\stable-diffusion-webui-directml\modules\sd_models.py", line 269, in select_checkpoint raise FileNotFoundError(error_message) FileNotFoundError: No checkpoints found. When searching for checkpoints, looked at: - file D:\stable-diffusion\stable-diffusion-webui-directml\model.ckpt - directory D:\stable-diffusion\stable-diffusion-webui-directml\models\Stable-diffusionCan't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. Stable diffusion model failed to load C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead. warnings.warn( Optimizing safety_checker [2024-01-02 13:58:06,892] [INFO] [engine.py:179:setup_accelerators] Running workflow on accelerator specs: gpu-dml [2024-01-02 13:58:06,938] [INFO] [engine.py:929:_run_pass] Running pass convert:OnnxConversion C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:284: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if attn_weights.size() != (bsz * self.num_heads, tgt_len, src_len): C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:324: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if attn_output.size() != (bsz * self.num_heads, tgt_len, self.head_dim): [2024-01-02 13:58:36,451] [INFO] [engine.py:929:_run_pass] Running pass optimize:OrtTransformersOptimization [2024-01-02 13:59:37,382] [INFO] [footprint.py:183:create_pareto_frontier] pareto frontier points: 1_OrtTransformersOptimization-0-619f2fd5ba69b6cafc9ccf2d841c3b38 { "latency-avg": 493.39677 } [2024-01-02 13:59:37,383] [INFO] [engine.py:610:create_pareto_frontier_footprints] Output all 1 models [2024-01-02 13:59:37,384] [INFO] [engine.py:357:run] Run history for gpu-dml: [2024-01-02 13:59:37,393] [INFO] [engine.py:634:dump_run_history] run history: +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ | model_id | parent_model_id | from_pass | duration_sec | metrics | +====================================================================================+====================================================================================+=============================+================+============================+ | 0bc47fe1d38bbc129af422adee1d5d94 | | | | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ | 0_OnnxConversion-0bc47fe1d38bbc129af422adee1d5d94-16f2a37f9cd543024ce55445ffe26e2b | 0bc47fe1d38bbc129af422adee1d5d94 | OnnxConversion | 29.4997 | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ | 1_OrtTransformersOptimization-0-619f2fd5ba69b6cafc9ccf2d841c3b38 | 0_OnnxConversion-0bc47fe1d38bbc129af422adee1d5d94-16f2a37f9cd543024ce55445ffe26e2b | OrtTransformersOptimization | 42.6233 | { | | | | | | "latency-avg": 493.39677 | | | | | | } | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+----------------------------+ [2024-01-02 13:59:37,395] [INFO] [engine.py:372:run] No packaging config provided, skip packaging artifacts Optimized safety_checker Optimizing text_encoder [2024-01-02 13:59:37,418] [INFO] [engine.py:179:setup_accelerators] Running workflow on accelerator specs: gpu-dml [2024-01-02 13:59:37,451] [INFO] [engine.py:929:_run_pass] Running pass convert:OnnxConversion D:\stable-diffusion\stable-diffusion-webui-directml\modules\dml\hijack\transformers.py:13: TracerWarning: torch.tensor results are registered as constants in the trace. You can safely ignore this warning if you use this function to create tensors out of constant variables that would be the same every time you call this function. In any other case, this might cause the trace to be incorrect. min = torch.tensor(torch.finfo(dtype).min, device="cpu") C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\transformers\models\clip\modeling_clip.py:292: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if causal_attention_mask.size() != (bsz, 1, tgt_len, src_len): [2024-01-02 13:59:51,554] [INFO] [engine.py:929:_run_pass] Running pass optimize:OrtTransformersOptimization [2024-01-02 14:00:15,583] [INFO] [footprint.py:183:create_pareto_frontier] pareto frontier points: 3_OrtTransformersOptimization-2-62c67214e0d8b2e59c4b857d7f513a48 { "latency-avg": 52.7122 } [2024-01-02 14:00:15,585] [INFO] [engine.py:610:create_pareto_frontier_footprints] Output all 1 models [2024-01-02 14:00:15,586] [INFO] [engine.py:357:run] Run history for gpu-dml: [2024-01-02 14:00:15,587] [INFO] [engine.py:634:dump_run_history] run history: +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+--------------------------+ | model_id | parent_model_id | from_pass | duration_sec | metrics | +====================================================================================+====================================================================================+=============================+================+==========================+ | 34c28b143af5f334cba9e8f3bfaf9bc8 | | | | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+--------------------------+ | 2_OnnxConversion-34c28b143af5f334cba9e8f3bfaf9bc8-16f2a37f9cd543024ce55445ffe26e2b | 34c28b143af5f334cba9e8f3bfaf9bc8 | OnnxConversion | 14.0912 | | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+--------------------------+ | 3_OrtTransformersOptimization-2-62c67214e0d8b2e59c4b857d7f513a48 | 2_OnnxConversion-34c28b143af5f334cba9e8f3bfaf9bc8-16f2a37f9cd543024ce55445ffe26e2b | OrtTransformersOptimization | 21.0615 | { | | | | | | "latency-avg": 52.7122 | | | | | | } | +------------------------------------------------------------------------------------+------------------------------------------------------------------------------------+-----------------------------+----------------+--------------------------+ [2024-01-02 14:00:15,588] [INFO] [engine.py:372:run] No packaging config provided, skip packaging artifacts Optimized text_encoder Optimizing unet [2024-01-02 14:00:15,612] [INFO] [engine.py:179:setup_accelerators] Running workflow on accelerator specs: gpu-dml [2024-01-02 14:00:15,651] [INFO] [engine.py:929:_run_pass] Running pass convert:OnnxConversion C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\diffusers\models\unet_2d_condition.py:915: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if dim % default_overall_up_factor != 0: C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\diffusers\models\downsampling.py:135: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! assert hidden_states.shape[1] == self.channels C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\diffusers\models\downsampling.py:144: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! assert hidden_states.shape[1] == self.channels C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\diffusers\models\upsampling.py:149: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! assert hidden_states.shape[1] == self.channels C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\diffusers\models\upsampling.py:165: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if hidden_states.shape[0] >= 64: C:\Users\Linearch\.conda\envs\sdwebui\lib\site-packages\diffusers\models\unet_2d_condition.py:1206: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if not return_dict: [2024-01-02 14:02:20,531] [INFO] [engine.py:929:_run_pass] Running pass optimize:OrtTransformersOptimization Press any key to continue . . . ```
R-N commented 9 months ago

The optimization process requires lots of RAM. You need at least 6GB of VRAM and at least 16GB of RAM, but you're sharing 20GB of RAM with integrated GPU. I recommend using optimized models that can be downloaded from huggingface.

Ohh, okay. That's already the minimum even with half and lowvram (if it matters)? It can't be helped then. Thank you