aboutsummaryrefslogtreecommitdiffstats
path: root/modules/shared.py
diff options
context:
space:
mode:
Diffstat (limited to 'modules/shared.py')
-rw-r--r--modules/shared.py120
1 files changed, 104 insertions, 16 deletions
diff --git a/modules/shared.py b/modules/shared.py
index 6ecc2503..b55371d3 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -3,6 +3,7 @@ import datetime
import json
import os
import sys
+from collections import OrderedDict
import gradio as gr
import tqdm
@@ -13,7 +14,8 @@ import modules.memmon
import modules.sd_models
import modules.styles
import modules.devices as devices
-from modules import sd_samplers, hypernetwork
+from modules import sd_samplers, sd_models, localization
+from modules.hypernetworks import hypernetwork
from modules.paths import models_path, script_path, sd_path
sd_model_file = os.path.join(script_path, 'model.ckpt')
@@ -25,16 +27,22 @@ parser.add_argument("--ckpt-dir", type=str, default=None, help="Path to director
parser.add_argument("--gfpgan-dir", type=str, help="GFPGAN directory", default=('./src/gfpgan' if os.path.exists('./src/gfpgan') else './GFPGAN'))
parser.add_argument("--gfpgan-model", type=str, help="GFPGAN model file name", default=None)
parser.add_argument("--no-half", action='store_true', help="do not switch the model to 16-bit floats")
+parser.add_argument("--no-half-vae", action='store_true', help="do not switch the VAE model to 16-bit floats")
parser.add_argument("--no-progressbar-hiding", action='store_true', help="do not hide progressbar in gradio UI (we hide it because it slows down ML if you have hardware acceleration in browser)")
parser.add_argument("--max-batch-count", type=int, default=16, help="maximum batch count value for the UI")
parser.add_argument("--embeddings-dir", type=str, default=os.path.join(script_path, 'embeddings'), help="embeddings directory for textual inversion (default: embeddings)")
+parser.add_argument("--hypernetwork-dir", type=str, default=os.path.join(models_path, 'hypernetworks'), help="hypernetwork directory")
+parser.add_argument("--localizations-dir", type=str, default=os.path.join(script_path, 'localizations'), help="localizations directory")
parser.add_argument("--allow-code", action='store_true', help="allow custom script execution from webui")
parser.add_argument("--medvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a little speed for low VRM usage")
parser.add_argument("--lowvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a lot of speed for very low VRM usage")
+parser.add_argument("--lowram", action='store_true', help="load stable diffusion checkpoint weights to VRAM instead of RAM")
parser.add_argument("--always-batch-cond-uncond", action='store_true', help="disables cond/uncond batching that is enabled to save memory with --medvram or --lowvram")
parser.add_argument("--unload-gfpgan", action='store_true', help="does not do anything.")
parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast")
parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site (doesn't work for me but you might have better luck)")
+parser.add_argument("--ngrok", type=str, help="ngrok authtoken, alternative to gradio --share", default=None)
+parser.add_argument("--ngrok-region", type=str, help="The region in which ngrok should start.", default="us")
parser.add_argument("--codeformer-models-path", type=str, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer'))
parser.add_argument("--gfpgan-models-path", type=str, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN'))
parser.add_argument("--esrgan-models-path", type=str, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN'))
@@ -46,15 +54,17 @@ parser.add_argument("--ldsr-models-path", type=str, help="Path to directory with
parser.add_argument("--xformers", action='store_true', help="enable xformers for cross attention layers")
parser.add_argument("--force-enable-xformers", action='store_true', help="enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work")
parser.add_argument("--deepdanbooru", action='store_true', help="enable deepdanbooru interrogator")
-parser.add_argument("--opt-split-attention", action='store_true', help="force-enables cross-attention layer optimization. By default, it's on for torch.cuda and off for other torch devices.")
-parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
+parser.add_argument("--opt-split-attention", action='store_true', help="force-enables Doggettx's cross-attention layer optimization. By default, it's on for torch cuda.")
+parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
-parser.add_argument("--use-cpu", nargs='+',choices=['SD', 'GFPGAN', 'BSRGAN', 'ESRGAN', 'SCUNet', 'CodeFormer'], help="use CPU as torch device for specified modules", default=[])
+parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
+parser.add_argument("--use-cpu", nargs='+',choices=['all', 'sd', 'interrogate', 'gfpgan', 'bsrgan', 'esrgan', 'scunet', 'codeformer'], help="use CPU as torch device for specified modules", default=[], type=str.lower)
parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
parser.add_argument("--show-negative-prompt", action='store_true', help="does not do anything", default=False)
parser.add_argument("--ui-config-file", type=str, help="filename to use for ui configuration", default=os.path.join(script_path, 'ui-config.json'))
parser.add_argument("--hide-ui-dir-config", action='store_true', help="hide directory configuration from webui", default=False)
+parser.add_argument("--freeze-settings", action='store_true', help="disable editing settings", default=False)
parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui settings", default=os.path.join(script_path, 'config.json'))
parser.add_argument("--gradio-debug", action='store_true', help="launch gradio with --debug option")
parser.add_argument("--gradio-auth", type=str, help='set gradio authentication like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
@@ -62,26 +72,50 @@ parser.add_argument("--gradio-img2img-tool", type=str, help='gradio image upload
parser.add_argument("--opt-channelslast", action='store_true', help="change memory type for stable diffusion to channels last")
parser.add_argument("--styles-file", type=str, help="filename to use for styles", default=os.path.join(script_path, 'styles.csv'))
parser.add_argument("--autolaunch", action='store_true', help="open the webui URL in the system's default browser upon launch", default=False)
+parser.add_argument("--theme", type=str, help="launches the UI with light or dark theme", default=None)
parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox for seeds in UI (no up/down, but possible to input long seeds)", default=False)
parser.add_argument("--disable-console-progressbars", action='store_true', help="do not output progressbars to console", default=False)
parser.add_argument("--enable-console-prompts", action='store_true', help="print prompts to console when generating with txt2img and img2img", default=False)
-
+parser.add_argument('--vae-path', type=str, help='Path to Variational Autoencoders model', default=None)
+parser.add_argument("--disable-safe-unpickle", action='store_true', help="disable checking pytorch models for malicious code", default=False)
+parser.add_argument("--api", action='store_true', help="use api=True to launch the api with the webui")
+parser.add_argument("--nowebui", action='store_true', help="use api=True to launch the api instead of the webui")
+parser.add_argument("--device-id", type=str, help="Select the default CUDA device to use (export CUDA_VISIBLE_DEVICES=0,1,etc might be needed before)", default=None)
+parser.add_argument("--browse-all-images", action='store_true', help="Allow browsing all images by Image Browser", default=False)
cmd_opts = parser.parse_args()
-
-devices.device, devices.device_gfpgan, devices.device_bsrgan, devices.device_esrgan, devices.device_scunet, devices.device_codeformer = \
-(devices.cpu if x in cmd_opts.use_cpu else devices.get_optimal_device() for x in ['SD', 'GFPGAN', 'BSRGAN', 'ESRGAN', 'SCUNet', 'CodeFormer'])
+restricted_opts = [
+ "samples_filename_pattern",
+ "outdir_samples",
+ "outdir_txt2img_samples",
+ "outdir_img2img_samples",
+ "outdir_extras_samples",
+ "outdir_grids",
+ "outdir_txt2img_grids",
+ "outdir_save",
+]
+
+devices.device, devices.device_interrogate, devices.device_gfpgan, devices.device_bsrgan, devices.device_esrgan, devices.device_scunet, devices.device_codeformer = \
+(devices.cpu if any(y in cmd_opts.use_cpu for y in [x, 'all']) else devices.get_optimal_device() for x in ['sd', 'interrogate', 'gfpgan', 'bsrgan', 'esrgan', 'scunet', 'codeformer'])
device = devices.device
+weight_load_location = None if cmd_opts.lowram else "cpu"
batch_cond_uncond = cmd_opts.always_batch_cond_uncond or not (cmd_opts.lowvram or cmd_opts.medvram)
parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram
xformers_available = False
config_filename = cmd_opts.ui_settings_file
-hypernetworks = hypernetwork.list_hypernetworks(os.path.join(models_path, 'hypernetworks'))
+os.makedirs(cmd_opts.hypernetwork_dir, exist_ok=True)
+hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
loaded_hypernetwork = None
+def reload_hypernetworks():
+ global hypernetworks
+
+ hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
+ hypernetwork.load_hypernetwork(opts.sd_hypernetwork)
+
class State:
skipped = False
@@ -107,7 +141,7 @@ class State:
self.job_no += 1
self.sampling_step = 0
self.current_image_sampling_step = 0
-
+
def get_job_timestamp(self):
return datetime.datetime.now().strftime("%Y%m%d%H%M%S") # shouldn't this return job_timestamp?
@@ -123,6 +157,8 @@ interrogator = modules.interrogate.InterrogateModels("interrogate")
face_restorers = []
+localization.list_localizations(cmd_opts.localizations_dir)
+
def realesrgan_models_names():
import modules.realesrgan_model
@@ -130,13 +166,14 @@ def realesrgan_models_names():
class OptionInfo:
- def __init__(self, default=None, label="", component=None, component_args=None, onchange=None):
+ def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, section=None, refresh=None):
self.default = default
self.label = label
self.component = component
self.component_args = component_args
self.onchange = onchange
- self.section = None
+ self.section = section
+ self.refresh = refresh
def options_section(section_identifier, options_dict):
@@ -159,6 +196,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids"
"grid_format": OptionInfo('png', 'File format for grids'),
"grid_extended_filename": OptionInfo(False, "Add extended info (seed, prompt) to filename when saving grid"),
"grid_only_if_multiple": OptionInfo(True, "Do not save grids consisting of one picture"),
+ "grid_prevent_empty_spots": OptionInfo(False, "Prevent empty spots in grid (when set to autodetect)"),
"n_rows": OptionInfo(-1, "Grid row count; use -1 for autodetect and 0 for it to be same as batch size", gr.Slider, {"minimum": -1, "maximum": 16, "step": 1}),
"enable_pnginfo": OptionInfo(True, "Save text information about generation parameters as chunks to png files"),
@@ -169,6 +207,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids"
"use_original_name_batch": OptionInfo(False, "Use original name for output filename during batch process in extras tab"),
"save_selected_only": OptionInfo(True, "When using 'Save' button, only save a single selected image"),
+ "do_not_add_watermark": OptionInfo(False, "Do not add watermark to images"),
}))
options_templates.update(options_section(('saving-paths', "Paths for saving"), {
@@ -198,6 +237,7 @@ options_templates.update(options_section(('upscaling', "Upscaling"), {
"SWIN_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for SwinIR. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}),
"ldsr_steps": OptionInfo(100, "LDSR processing steps. Lower = faster", gr.Slider, {"minimum": 1, "maximum": 200, "step": 1}),
"upscaler_for_img2img": OptionInfo(None, "Upscaler for img2img", gr.Dropdown, lambda: {"choices": [x.name for x in sd_upscalers]}),
+ "use_scale_latent_for_hires_fix": OptionInfo(False, "Upscale latent space image when doing hires. fix"),
}))
options_templates.update(options_section(('face-restoration', "Face restoration"), {
@@ -212,9 +252,19 @@ options_templates.update(options_section(('system', "System"), {
"multiple_tqdm": OptionInfo(True, "Add a second progress bar to the console that shows progress for an entire job."),
}))
+options_templates.update(options_section(('training', "Training"), {
+ "unload_models_when_training": OptionInfo(False, "Move VAE and CLIP to RAM when training hypernetwork. Saves VRAM."),
+ "dataset_filename_word_regex": OptionInfo("", "Filename word regex"),
+ "dataset_filename_join_string": OptionInfo(" ", "Filename join string"),
+ "training_image_repeats_per_epoch": OptionInfo(1, "Number of repeats for a single input image per epoch; used only for displaying epoch number", gr.Number, {"precision": 0}),
+ "training_write_csv_every": OptionInfo(500, "Save an csv containing the loss to log directory every N steps, 0 to disable"),
+}))
+
options_templates.update(options_section(('sd', "Stable Diffusion"), {
- "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": modules.sd_models.checkpoint_tiles()}),
- "sd_hypernetwork": OptionInfo("None", "Stable Diffusion finetune hypernetwork", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}),
+ "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, refresh=sd_models.list_models),
+ "sd_checkpoint_cache": OptionInfo(0, "Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),
+ "sd_hypernetwork": OptionInfo("None", "Hypernetwork", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}, refresh=reload_hypernetworks),
+ "sd_hypernetwork_strength": OptionInfo(1.0, "Hypernetwork strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.001}),
"img2img_color_correction": OptionInfo(False, "Apply color correction to img2img results to match original colors."),
"save_images_before_color_correction": OptionInfo(False, "Save a copy of image before applying color correction to img2img results"),
"img2img_fix_steps": OptionInfo(False, "With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising)."),
@@ -222,31 +272,41 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
"enable_emphasis": OptionInfo(True, "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention"),
"use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
"enable_batch_seeds": OptionInfo(True, "Make K-diffusion samplers produce same images in a batch as when making a single image"),
+ "comma_padding_backtrack": OptionInfo(20, "Increase coherency by padding from the last comma within n tokens when using more than 75 tokens", gr.Slider, {"minimum": 0, "maximum": 74, "step": 1 }),
"filter_nsfw": OptionInfo(False, "Filter NSFW content"),
- 'CLIP_ignore_last_layers': OptionInfo(0, "Ignore last layers of CLIP model", gr.Slider, {"minimum": 0, "maximum": 5, "step": 1}),
+ 'CLIP_stop_at_last_layers': OptionInfo(1, "Stop At last layers of CLIP model", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}),
"random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}),
}))
options_templates.update(options_section(('interrogate', "Interrogate Options"), {
"interrogate_keep_models_in_memory": OptionInfo(False, "Interrogate: keep models in VRAM"),
"interrogate_use_builtin_artists": OptionInfo(True, "Interrogate: use artists from artists.csv"),
+ "interrogate_return_ranks": OptionInfo(False, "Interrogate: include ranks of model tags matches in results (Has no effect on caption-based interrogators)."),
"interrogate_clip_num_beams": OptionInfo(1, "Interrogate: num_beams for BLIP", gr.Slider, {"minimum": 1, "maximum": 16, "step": 1}),
"interrogate_clip_min_length": OptionInfo(24, "Interrogate: minimum description length (excluding artists, etc..)", gr.Slider, {"minimum": 1, "maximum": 128, "step": 1}),
"interrogate_clip_max_length": OptionInfo(48, "Interrogate: maximum description length", gr.Slider, {"minimum": 1, "maximum": 256, "step": 1}),
- "interrogate_clip_dict_limit": OptionInfo(1500, "Interrogate: maximum number of lines in text file (0 = No limit)"),
+ "interrogate_clip_dict_limit": OptionInfo(1500, "CLIP: maximum number of lines in text file (0 = No limit)"),
+ "interrogate_deepbooru_score_threshold": OptionInfo(0.5, "Interrogate: deepbooru score threshold", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}),
+ "deepbooru_sort_alpha": OptionInfo(True, "Interrogate: deepbooru sort alphabetically"),
+ "deepbooru_use_spaces": OptionInfo(False, "use spaces for tags in deepbooru"),
+ "deepbooru_escape": OptionInfo(True, "escape (\\) brackets in deepbooru (so they are used as literal brackets and not for emphasis)"),
}))
options_templates.update(options_section(('ui', "User interface"), {
"show_progressbar": OptionInfo(True, "Show progressbar"),
"show_progress_every_n_steps": OptionInfo(0, "Show image creation progress every N sampling steps. Set 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 32, "step": 1}),
+ "show_progress_grid": OptionInfo(True, "Show previews of all images generated in a batch as a grid"),
"return_grid": OptionInfo(True, "Show grid in results for web"),
"do_not_show_images": OptionInfo(False, "Do not show any images in results for web"),
"add_model_hash_to_info": OptionInfo(True, "Add model hash to generation information"),
"add_model_name_to_info": OptionInfo(False, "Add model name to generation information"),
+ "disable_weights_auto_swap": OptionInfo(False, "When reading generation parameters from text into UI (from PNG info or pasted text), do not change the selected model/checkpoint."),
"font": OptionInfo("", "Font for image grids that have text"),
"js_modal_lightbox": OptionInfo(True, "Enable full page image viewer"),
"js_modal_lightbox_initially_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),
"show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
+ 'quicksettings': OptionInfo("sd_model_checkpoint", "Quicksettings list"),
+ 'localization': OptionInfo("None", "Localization (requires restart)", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)),
}))
options_templates.update(options_section(('sampler-params', "Sampler parameters"), {
@@ -257,6 +317,16 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters"
's_churn': OptionInfo(0.0, "sigma churn", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
's_tmin': OptionInfo(0.0, "sigma tmin", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
's_noise': OptionInfo(1.0, "sigma noise", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
+ 'eta_noise_seed_delta': OptionInfo(0, "Eta noise seed delta", gr.Number, {"precision": 0}),
+}))
+
+options_templates.update(options_section(('images-history', "Images Browser"), {
+ #"images_history_reconstruct_directory": OptionInfo(False, "Reconstruct output directory structure.This can greatly improve the speed of loading , but will change the original output directory structure"),
+ "images_history_preload": OptionInfo(False, "Preload images at startup"),
+ "images_history_num_per_page": OptionInfo(36, "Number of pictures displayed on each page"),
+ "images_history_pages_num": OptionInfo(6, "Minimum number of pages per load "),
+ "images_history_grid_num": OptionInfo(6, "Number of grids in each row"),
+
}))
@@ -316,10 +386,26 @@ class Options:
item = self.data_labels.get(key)
item.onchange = func
+ func()
+
def dumpjson(self):
d = {k: self.data.get(k, self.data_labels.get(k).default) for k in self.data_labels.keys()}
return json.dumps(d)
+ def add_option(self, key, info):
+ self.data_labels[key] = info
+
+ def reorder(self):
+ """reorder settings so that all items related to section always go together"""
+
+ section_ids = {}
+ settings_items = self.data_labels.items()
+ for k, item in settings_items:
+ if item.section not in section_ids:
+ section_ids[item.section] = len(section_ids)
+
+ self.data_labels = {k: v for k, v in sorted(settings_items, key=lambda x: section_ids[x[1].section])}
+
opts = Options()
if os.path.exists(config_filename):
@@ -329,6 +415,8 @@ sd_upscalers = []
sd_model = None
+clip_model = None
+
progress_print_out = sys.stdout
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-30 13:51:59 +0000