Super-squash branch 'main' using huggingface_hub

Co-authored-by: Viperboy123 <Viperboy123@users.noreply.huggingface.co>
Co-authored-by: zx18 <zx18@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,55 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,15 @@
+
+.ipynb_checkpoints
+
+/Codeformer
+/ControlNet
+/GFPGAN
+/hypernetworks
+/LDSR
+/SwinIR
+/karlo
+/deepbooru
+/Stable-diffusion/*.safetensors
+
+**/BackupNo/
+*.BackupNo

Lora/Normal_Ad/BlueArchive-000008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1919f054b61b43c578de8b2fa3fbf3a5257208acdef36bb4c0e50c74484aceda
+size 228600292

Lora/Normal_Ad/Hand pony style v1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40045916027cca0b85cc62c0db8585367fd240cc6c5bc538a8af043e0dfe1299
+size 456484940

Lora/Normal_Ad/analmp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:933c012b34d9fdd15cbfbdd67b44e71d787b830345a5b2a67b36ff6cbcd13723
+size 57450772

Lora/Normal_Ad/blue_archive-ixl-style-soralz.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04fad2ba6e02e7167c4bd5dc989d4832704fea6a79ccf1ac370d2f1727231c3b
+size 114459524

Lora/Normal_Ad/dmd2-lighting8step_cfg1.5.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a3b4475c27007b2821ea13ef437b6247c3bc6469ffdd74a60537dd98856fd69
+size 349018504

Lora/Normal_Ad/finger_in_anothers_mouth.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a568856b92c8f388657af92732b1fc7167660d109474743f8fa9111768bbab2d
+size 57469132

Lora/Normal_Ad/hand_grabbing_both_breasts_concept_Illustrious_v2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a739a65515cc5c4b7938ace16f771674fe7a7e5cce0db09874bc1544773d0991
+size 228457844

Lora/Normal_Ad/hug_ilxl_v1.0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ed4f76213786452a2db4ca47f5a3666a13ead51702664ca1f963a902a28877
+size 28915124

Lora/Normal_Ad/捏乳.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7581434e559477f8cd093bf8e31b2a73445f01d9dd614ddf81e743d7ba82fda2
+size 228453860

Lora/XLRN/___commit_sub.bat

@@ -0,0 +1,6 @@
+@echo off
+
+cd..
+cd..
+
+commit.bat

RealESRGAN/RealESRGAN_x4plus.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa0d38905f75ac06eb49a7951b426670021be3018265fd191d2125df9d682f1
+size 67040989

RealESRGAN/RealESRGAN_x4plus_anime_6B.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f872d837d3c90ed2e05227bed711af5671a6fd1c9f7d7e91c911a61f155e99da
+size 17938799

Stable-diffusion/__get.bat

@@ -0,0 +1 @@
+wget -N https://huggingface.co/zuv0/test/resolve/main/noobaiXLNAIXL_epsilonPred05Version.safetensors

VAE-approx/vaeapprox-sdxl.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8db511f910184436a613807ce06a729f4cf96bbf7977c7c6c40d5b3e4a8333
+size 213777

VAE/sdxl_vae.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63aeecb90ff7bc1c115395962d3e803571385b61938377bc7089b36e81e92e2e
+size 334641164

commit.bat

@@ -0,0 +1,30 @@
+@echo off
+
+git config user.name "anonymous"
+git config user.email my@gmail.com
+
+set /P comment=Comment?
+
+if not "%comment%" == "" goto :next
+set comment=auto
+:next
+
+git reset
+
+::git add *.* --force
+::git add *
+git add --all
+
+echo ----- git add done ------
+
+git status
+
+echo ready. press any key to commit START.
+::timeout /t 1
+pause
+
+git commit -m "%comment%"
+
+git push -u origin main
+
+pause

config_co1.json

@@ -0,0 +1,326 @@
+{
+    "ldsr_steps": 100,
+    "ldsr_cached": false,
+    "SCUNET_tile": 256,
+    "SCUNET_tile_overlap": 8,
+    "SWIN_tile": 192,
+    "SWIN_tile_overlap": 8,
+    "SWIN_torch_compile": false,
+    "control_net_detectedmap_dir": "detected_maps",
+    "control_net_models_path": "",
+    "control_net_modules_path": "",
+    "control_net_unit_count": 3,
+    "control_net_model_cache_size": 5,
+    "control_net_no_detectmap": false,
+    "control_net_detectmap_autosaving": false,
+    "control_net_allow_script_control": false,
+    "control_net_sync_field_args": true,
+    "controlnet_show_batch_images_in_ui": false,
+    "controlnet_increment_seed_during_batch": false,
+    "controlnet_disable_openpose_edit": false,
+    "controlnet_disable_photopea_edit": false,
+    "controlnet_photopea_warning": true,
+    "controlnet_input_thumbnail": true,
+    "sd_checkpoint_hash": "821aa5537f8ddafdbf963827551865c31c5bbfab1abe7925cb5f006c8f71e485",
+    "sd_model_checkpoint": "autismmixSDXL_autismmixPony.safetensors [821aa5537f]",
+    "use_downcasted_alpha_bar": true,
+    "CLIP_stop_at_last_layers": 2,
+    "k_sched_type": "Automatic",
+    "sd_vae": "sdxlVAE_sdxlVAE.safetensors",
+    "uni_pc_order": 3,
+    "outdir_samples": "",
+    "outdir_txt2img_samples": "/content/drive/MyDrive/SD/output/txt2img-images",
+    "outdir_img2img_samples": "/content/drive/MyDrive/SD/output/img2img-images",
+    "outdir_extras_samples": "/content/drive/MyDrive/SD/output/extras-images",
+    "outdir_grids": "",
+    "outdir_txt2img_grids": "/content/drive/MyDrive/SD/output/txt2img-grids",
+    "outdir_img2img_grids": "/content/drive/MyDrive/SD/output/img2img-grids",
+    "outdir_save": "log/images",
+    "outdir_init_images": "/content/drive/MyDrive/SD/output/init-images",
+    "samples_save": true,
+    "samples_format": "webp",
+    "samples_filename_pattern": "[seed]-",
+    "save_images_add_number": true,
+    "save_images_replace_action": "Replace",
+    "grid_save": false,
+    "grid_format": "png",
+    "grid_extended_filename": true,
+    "grid_only_if_multiple": true,
+    "grid_prevent_empty_spots": false,
+    "grid_zip_filename_pattern": "",
+    "n_rows": -1,
+    "font": "",
+    "grid_text_active_color": "#000000",
+    "grid_text_inactive_color": "#999999",
+    "grid_background_color": "#ffffff",
+    "save_images_before_face_restoration": false,
+    "save_images_before_highres_fix": false,
+    "save_images_before_color_correction": false,
+    "save_mask": false,
+    "save_mask_composite": false,
+    "jpeg_quality": 80,
+    "webp_lossless": false,
+    "export_for_4chan": true,
+    "img_downscale_threshold": 4.0,
+    "target_side_length": 4000.0,
+    "img_max_size_mp": 200.0,
+    "use_original_name_batch": true,
+    "use_upscaler_name_as_suffix": false,
+    "save_selected_only": true,
+    "save_init_img": false,
+    "temp_dir": "",
+    "clean_temp_dir_at_start": false,
+    "save_incomplete_images": false,
+    "notification_audio": true,
+    "notification_volume": 100,
+    "save_to_dirs": false,
+    "grid_save_to_dirs": false,
+    "use_save_to_dirs_for_ui": false,
+    "directories_filename_pattern": "[date]",
+    "directories_max_prompt_words": 8,
+    "auto_backcompat": true,
+    "use_old_emphasis_implementation": false,
+    "use_old_karras_scheduler_sigmas": false,
+    "no_dpmpp_sde_batch_determinism": false,
+    "use_old_hires_fix_width_height": false,
+    "dont_fix_second_order_samplers_schedule": false,
+    "hires_fix_use_firstpass_conds": false,
+    "use_old_scheduling": false,
+    "lora_functional": false,
+    "extra_networks_show_hidden_directories": true,
+    "extra_networks_dir_button_function": false,
+    "extra_networks_hidden_models": "When searched",
+    "extra_networks_default_multiplier": 1,
+    "extra_networks_card_width": 0.0,
+    "extra_networks_card_height": 0.0,
+    "extra_networks_card_text_scale": 1,
+    "extra_networks_card_show_desc": true,
+    "extra_networks_card_description_is_html": false,
+    "extra_networks_card_order_field": "Path",
+    "extra_networks_card_order": "Ascending",
+    "extra_networks_tree_view_default_enabled": false,
+    "extra_networks_add_text_separator": " ",
+    "ui_extra_networks_tab_reorder": "",
+    "textual_inversion_print_at_load": false,
+    "textual_inversion_add_hashes_to_infotext": true,
+    "sd_hypernetwork": "None",
+    "sd_lora": "None",
+    "lora_preferred_name": "Alias from file",
+    "lora_add_hashes_to_infotext": true,
+    "lora_show_all": false,
+    "lora_hide_unknown_for_versions": [],
+    "lora_in_memory_limit": 0,
+    "lora_not_found_warning_console": false,
+    "lora_not_found_gradio_warning": false,
+    "cross_attention_optimization": "Automatic",
+    "s_min_uncond": 0,
+    "token_merging_ratio": 0,
+    "token_merging_ratio_img2img": 0,
+    "token_merging_ratio_hr": 0,
+    "pad_cond_uncond": false,
+    "pad_cond_uncond_v0": false,
+    "persistent_cond_cache": true,
+    "batch_cond_uncond": true,
+    "fp8_storage": "Enable for SDXL",
+    "cache_fp16_weight": false,
+    "hide_samplers": [],
+    "eta_ddim": 0,
+    "eta_ancestral": 1,
+    "ddim_discretize": "uniform",
+    "s_churn": 0,
+    "s_tmin": 0,
+    "s_tmax": 0,
+    "s_noise": 1,
+    "sigma_min": 0.0,
+    "sigma_max": 0.0,
+    "rho": 0.0,
+    "eta_noise_seed_delta": 0,
+    "always_discard_next_to_last_sigma": false,
+    "sgm_noise_multiplier": false,
+    "uni_pc_variant": "bh1",
+    "uni_pc_skip_type": "time_uniform",
+    "uni_pc_lower_order_final": true,
+    "sd_noise_schedule": "Default",
+    "sd_checkpoints_limit": 1,
+    "sd_checkpoints_keep_in_cpu": true,
+    "sd_checkpoint_cache": 0,
+    "sd_unet": "Automatic",
+    "enable_quantization": false,
+    "emphasis": "Original",
+    "enable_batch_seeds": true,
+    "comma_padding_backtrack": 20,
+    "upcast_attn": false,
+    "randn_source": "CPU",
+    "tiling": false,
+    "hires_fix_refiner_pass": "second pass",
+    "enable_prompt_comments": true,
+    "sdxl_crop_top": 0.0,
+    "sdxl_crop_left": 0.0,
+    "sdxl_refiner_low_aesthetic_score": 2.5,
+    "sdxl_refiner_high_aesthetic_score": 6.0,
+    "sd_vae_checkpoint_cache": 0,
+    "sd_vae_overrides_per_model_preferences": true,
+    "auto_vae_precision_bfloat16": false,
+    "auto_vae_precision": true,
+    "sd_vae_encode_method": "Full",
+    "sd_vae_decode_method": "Full",
+    "inpainting_mask_weight": 1,
+    "initial_noise_multiplier": 1,
+    "img2img_extra_noise": 0,
+    "img2img_color_correction": true,
+    "img2img_fix_steps": false,
+    "img2img_background_color": "#ffffff",
+    "img2img_editor_height": 720,
+    "img2img_sketch_default_brush_color": "#ffffff",
+    "img2img_inpaint_mask_brush_color": "#ffffff",
+    "img2img_inpaint_sketch_default_brush_color": "#ffffff",
+    "return_mask": false,
+    "return_mask_composite": false,
+    "img2img_batch_show_results_limit": 32,
+    "overlay_inpaint": true,
+    "return_grid": true,
+    "do_not_show_images": false,
+    "js_modal_lightbox": true,
+    "js_modal_lightbox_initially_zoomed": true,
+    "js_modal_lightbox_gamepad": false,
+    "js_modal_lightbox_gamepad_repeat": 250.0,
+    "sd_webui_modal_lightbox_icon_opacity": 1,
+    "sd_webui_modal_lightbox_toolbar_opacity": 0.9,
+    "gallery_height": "",
+    "open_dir_button_choice": "Subdirectory",
+    "enable_pnginfo": true,
+    "save_txt": false,
+    "add_model_name_to_info": true,
+    "add_model_hash_to_info": true,
+    "add_vae_name_to_info": true,
+    "add_vae_hash_to_info": true,
+    "add_user_name_to_info": false,
+    "add_version_to_infotext": true,
+    "disable_weights_auto_swap": true,
+    "infotext_skip_pasting": [],
+    "infotext_styles": "Apply if any",
+    "show_progressbar": true,
+    "live_previews_enable": true,
+    "live_previews_image_format": "png",
+    "show_progress_grid": true,
+    "show_progress_every_n_steps": 10,
+    "show_progress_type": "Approx NN",
+    "live_preview_allow_lowvram_full": false,
+    "live_preview_content": "Prompt",
+    "live_preview_refresh_period": 1000.0,
+    "live_preview_fast_interrupt": false,
+    "js_live_preview_in_modal_lightbox": false,
+    "keyedit_precision_attention": 0.1,
+    "keyedit_precision_extra": 0.05,
+    "keyedit_delimiters": ".,\\/!?%^*;:{}=`~() ",
+    "keyedit_delimiters_whitespace": [
+        "Tab",
+        "Carriage Return",
+        "Line Feed"
+    ],
+    "keyedit_move": true,
+    "disable_token_counters": false,
+    "include_styles_into_token_counters": true,
+    "extra_options_txt2img": [],
+    "extra_options_img2img": [],
+    "extra_options_cols": 1,
+    "extra_options_accordion": false,
+    "compact_prompt_box": false,
+    "samplers_in_dropdown": true,
+    "dimensions_and_batch_together": true,
+    "sd_checkpoint_dropdown_use_short": false,
+    "hires_fix_show_sampler": false,
+    "hires_fix_show_prompts": false,
+    "txt2img_settings_accordion": false,
+    "img2img_settings_accordion": false,
+    "interrupt_after_current": true,
+    "localization": "None",
+    "quicksettings_list": [
+        "sd_model_checkpoint",
+        "sd_vae",
+        "CLIP_stop_at_last_layers"
+    ],
+    "ui_tab_order": [],
+    "hidden_tabs": [],
+    "ui_reorder_list": [],
+    "gradio_theme": "Default",
+    "gradio_themes_cache": true,
+    "show_progress_in_title": true,
+    "send_seed": true,
+    "send_size": true,
+    "api_enable_requests": true,
+    "api_forbid_local_requests": true,
+    "api_useragent": "",
+    "auto_launch_browser": "Local",
+    "enable_console_prompts": false,
+    "show_warnings": false,
+    "show_gradio_deprecation_warnings": true,
+    "memmon_poll_rate": 8,
+    "samples_log_stdout": false,
+    "multiple_tqdm": true,
+    "enable_upscale_progressbar": true,
+    "print_hypernet_extra": false,
+    "list_hidden_files": true,
+    "disable_mmap_load_safetensors": false,
+    "hide_ldm_prints": true,
+    "dump_stacks_on_signal": false,
+    "face_restoration": false,
+    "face_restoration_model": "CodeFormer",
+    "code_former_weight": 0.5,
+    "face_restoration_unload": false,
+    "postprocessing_enable_in_main_ui": [],
+    "postprocessing_operation_order": [],
+    "upscaling_max_images_in_cache": 5,
+    "postprocessing_existing_caption_action": "Ignore",
+    "ESRGAN_tile": 192,
+    "ESRGAN_tile_overlap": 8,
+    "realesrgan_enabled_models": [
+        "R-ESRGAN 4x+",
+        "R-ESRGAN 4x+ Anime6B"
+    ],
+    "dat_enabled_models": [
+        "DAT x2",
+        "DAT x3",
+        "DAT x4"
+    ],
+    "DAT_tile": 192,
+    "DAT_tile_overlap": 8,
+    "unload_models_when_training": false,
+    "pin_memory": false,
+    "save_optimizer_state": false,
+    "save_training_settings_to_txt": true,
+    "dataset_filename_word_regex": "",
+    "dataset_filename_join_string": " ",
+    "training_image_repeats_per_epoch": 1,
+    "training_write_csv_every": 500.0,
+    "training_xattention_optimizations": false,
+    "training_enable_tensorboard": false,
+    "training_tensorboard_save_images": false,
+    "training_tensorboard_flush_every": 120.0,
+    "canvas_hotkey_zoom": "Alt",
+    "canvas_hotkey_adjust": "Ctrl",
+    "canvas_hotkey_shrink_brush": "Q",
+    "canvas_hotkey_grow_brush": "W",
+    "canvas_hotkey_move": "F",
+    "canvas_hotkey_fullscreen": "S",
+    "canvas_hotkey_reset": "R",
+    "canvas_hotkey_overlap": "O",
+    "canvas_show_tooltip": true,
+    "canvas_auto_expand": true,
+    "canvas_blur_prompt": false,
+    "canvas_disabled_functions": [
+        "Overlap"
+    ],
+    "interrogate_keep_models_in_memory": false,
+    "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_clip_skip_categories": [],
+    "interrogate_deepbooru_score_threshold": 0.5,
+    "deepbooru_sort_alpha": true,
+    "deepbooru_use_spaces": true,
+    "deepbooru_escape": true,
+    "deepbooru_filter_tags": ""
+}

configs/anything_v3.yaml

@@ -0,0 +1,73 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+      params:
+        layer: "hidden"
+        layer_idx: -2

configs/v1-inference.yaml

@@ -0,0 +1,70 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder

configs/v1-inference_clip_skip_2.yaml

@@ -0,0 +1,73 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+      params:
+        layer: "hidden"
+        layer_idx: -2

configs/v1-inference_clip_skip_2_fp16.yaml

@@ -0,0 +1,74 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_fp16: True
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+      params:
+        layer: "hidden"
+        layer_idx: -2

configs/v1-inference_fp16.yaml

@@ -0,0 +1,71 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_fp16: True
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder

configs/v1-inpainting-inference.yaml

@@ -0,0 +1,71 @@
+model:
+  base_learning_rate: 7.5e-05
+  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: hybrid   # important
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    finetune_keys: null
+
+    scheduler_config: # 10000 warmup steps
+      target: ldm.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 9  # 4 data + 4 downscaled image + 1 mask
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
+

configs/v2-inference-v.yaml

@@ -0,0 +1,68 @@
+model:
+  base_learning_rate: 1.0e-4
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    parameterization: "v"
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False # we set this to false because this is an inference only config
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        use_fp16: True
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"

configs/v2-inference-v_fp32.yaml

@@ -0,0 +1,68 @@
+model:
+  base_learning_rate: 1.0e-4
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    parameterization: "v"
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False # we set this to false because this is an inference only config
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        use_fp16: False
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"

configs/v2-inference.yaml

@@ -0,0 +1,67 @@
+model:
+  base_learning_rate: 1.0e-4
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False # we set this to false because this is an inference only config
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        use_fp16: True
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"

configs/v2-inference_fp32.yaml

@@ -0,0 +1,67 @@
+model:
+  base_learning_rate: 1.0e-4
+  target: ldm.models.diffusion.ddpm.LatentDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False # we set this to false because this is an inference only config
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        use_fp16: False
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"

configs/v2-inpainting-inference.yaml

@@ -0,0 +1,158 @@
+model:
+  base_learning_rate: 5.0e-05
+  target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
+  params:
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false
+    conditioning_key: hybrid
+    scale_factor: 0.18215
+    monitor: val/loss_simple_ema
+    finetune_keys: null
+    use_ema: False
+
+    unet_config:
+      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
+      params:
+        use_checkpoint: True
+        image_size: 32 # unused
+        in_channels: 9
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_head_channels: 64 # need to fix for flash-attn
+        use_spatial_transformer: True
+        use_linear_in_transformer: True
+        transformer_depth: 1
+        context_dim: 1024
+        legacy: False
+
+    first_stage_config:
+      target: ldm.models.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          #attn_type: "vanilla-xformers"
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+            - 1
+            - 2
+            - 4
+            - 4
+          num_res_blocks: 2
+          attn_resolutions: [ ]
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
+      params:
+        freeze: True
+        layer: "penultimate"
+
+
+data:
+  target: ldm.data.laion.WebDataModuleFromConfig
+  params:
+    tar_base: null  # for concat as in LAION-A
+    p_unsafe_threshold: 0.1
+    filter_word_list: "data/filters.yaml"
+    max_pwatermark: 0.45
+    batch_size: 8
+    num_workers: 6
+    multinode: True
+    min_size: 512
+    train:
+      shards:
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-0/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-1/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-2/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-3/{00000..18699}.tar -"
+        - "pipe:aws s3 cp s3://stability-aws/laion-a-native/part-4/{00000..18699}.tar -"  #{00000-94333}.tar"
+      shuffle: 10000
+      image_key: jpg
+      image_transforms:
+      - target: torchvision.transforms.Resize
+        params:
+          size: 512
+          interpolation: 3
+      - target: torchvision.transforms.RandomCrop
+        params:
+          size: 512
+      postprocess:
+        target: ldm.data.laion.AddMask
+        params:
+          mode: "512train-large"
+          p_drop: 0.25
+    # NOTE use enough shards to avoid empty validation loops in workers
+    validation:
+      shards:
+        - "pipe:aws s3 cp s3://deep-floyd-s3/datasets/laion_cleaned-part5/{93001..94333}.tar - "
+      shuffle: 0
+      image_key: jpg
+      image_transforms:
+      - target: torchvision.transforms.Resize
+        params:
+          size: 512
+          interpolation: 3
+      - target: torchvision.transforms.CenterCrop
+        params:
+          size: 512
+      postprocess:
+        target: ldm.data.laion.AddMask
+        params:
+          mode: "512train-large"
+          p_drop: 0.25
+
+lightning:
+  find_unused_parameters: True
+  modelcheckpoint:
+    params:
+      every_n_train_steps: 5000
+
+  callbacks:
+    metrics_over_trainsteps_checkpoint:
+      params:
+        every_n_train_steps: 10000
+
+    image_logger:
+      target: main.ImageLogger
+      params:
+        enable_autocast: False
+        disabled: False
+        batch_frequency: 1000
+        max_images: 4
+        increase_log_steps: False
+        log_first_step: False
+        log_images_kwargs:
+          use_ema_scope: False
+          inpaint: False
+          plot_progressive_rows: False
+          plot_diffusion_rows: False
+          N: 4
+          unconditional_guidance_scale: 5.0
+          unconditional_guidance_label: [""]
+          ddim_steps: 50  # todo check these out for depth2img,
+          ddim_eta: 0.0   # todo check these out for depth2img,
+
+  trainer:
+    benchmark: True
+    val_check_interval: 5000000
+    num_sanity_val_steps: 0
+    accumulate_grad_batches: 1

diffusers/version.txt

@@ -0,0 +1 @@
+1

diffusers/version_diffusers_cache.txt

@@ -0,0 +1 @@
+1

embeddings/NEGATIVE_HANDS.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1411f312e096b3a0313f9c03f489f39cc24b8c34466aecfa1c80c7e942b9f88b
+size 24728

embeddings/aidxlv05_neg.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a6266ecaa6f869dc56d992e929e47098ddd4c495be5b80430cb037c4d89bd5
+size 131224

embeddings/negativeXL_D.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fff5d51ab6558d2bf0b77f805c67af855116718284f24877fbf26200e52fd5f5
+size 131224

forcePull.bat

@@ -0,0 +1,13 @@
+@echo off
+
+git fetch --all
+git reset --hard origin/main
+git pull
+git repack -a -d --depth=250 --window=250
+mkdir "../embeddings"
+xcopy embeddings "../embeddings" /y /c /h /e /q
+cd .git
+rmdir /S /Q lfs
+cd ..
+
+pause

text_encoder/Put Text Encoders here.txt

@@ -0,0 +1 @@
+https://github.com/Haoming02/All-in-One-Stable-Diffusion-Guide#text-encoder

upscale_models/4x-UltraSharpV2_Lite.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a330ef6b7c632477d311ac03499c91c350e35c5986d4a6c295f0628cb871a09
+size 29590776

upscale_models/RealESRGAN_x4plus.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa0d38905f75ac06eb49a7951b426670021be3018265fd191d2125df9d682f1
+size 67040989