diff options
34 files changed, 1105 insertions, 275 deletions
diff --git a/.github/workflows/on_pull_request.yaml b/.github/workflows/on_pull_request.yaml index 78e608ee..9e44c806 100644 --- a/.github/workflows/on_pull_request.yaml +++ b/.github/workflows/on_pull_request.yaml @@ -20,7 +20,7 @@ jobs: # not to have GHA download an (at the time of writing) 4 GB cache # of PyTorch and other dependencies. - name: Install Ruff - run: pip install ruff==0.0.272 + run: pip install ruff==0.1.6 - name: Run Ruff run: ruff . lint-js: @@ -121,7 +121,9 @@ Alternatively, use online services (like Google Colab): # Debian-based:
sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
# Red Hat-based:
-sudo dnf install wget git python3
+sudo dnf install wget git python3 gperftools-libs libglvnd-glx
+# openSUSE-based:
+sudo zypper install wget git python3 libtcmalloc4 libglvnd
# Arch-based:
sudo pacman -S wget git python3
```
@@ -174,5 +176,6 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al - TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
- LyCORIS - KohakuBlueleaf
- Restart sampling - lambertae - https://github.com/Newbeeer/diffusion_restart_sampling
+- Hypertile - tfernd - https://github.com/tfernd/HyperTile
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
- (You)
diff --git a/extensions-builtin/extra-options-section/scripts/extra_options_section.py b/extensions-builtin/extra-options-section/scripts/extra_options_section.py index 983f87ff..a903df62 100644 --- a/extensions-builtin/extra-options-section/scripts/extra_options_section.py +++ b/extensions-builtin/extra-options-section/scripts/extra_options_section.py @@ -64,11 +64,14 @@ class ExtraOptionsSection(scripts.Script): p.override_settings[name] = value
-shared.options_templates.update(shared.options_section(('ui', "User interface"), {
- "extra_options_txt2img": shared.OptionInfo([], "Options in main UI - txt2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img interfaces").needs_reload_ui(),
- "extra_options_img2img": shared.OptionInfo([], "Options in main UI - img2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in img2img interfaces").needs_reload_ui(),
- "extra_options_cols": shared.OptionInfo(1, "Options in main UI - number of columns", gr.Number, {"precision": 0}).needs_reload_ui(),
- "extra_options_accordion": shared.OptionInfo(False, "Options in main UI - place into an accordion").needs_reload_ui()
+shared.options_templates.update(shared.options_section(('settings_in_ui', "Settings in UI", "ui"), {
+ "settings_in_ui": shared.OptionHTML("""
+This page allows you to add some settings to the main interface of txt2img and img2img tabs.
+"""),
+ "extra_options_txt2img": shared.OptionInfo([], "Settings for txt2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in txt2img interfaces").needs_reload_ui(),
+ "extra_options_img2img": shared.OptionInfo([], "Settings for img2img", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that also appear in img2img interfaces").needs_reload_ui(),
+ "extra_options_cols": shared.OptionInfo(1, "Number of columns for added settings", gr.Number, {"precision": 0}).needs_reload_ui(),
+ "extra_options_accordion": shared.OptionInfo(False, "Place added settings into an accordion").needs_reload_ui()
}))
diff --git a/extensions-builtin/hypertile/hypertile.py b/extensions-builtin/hypertile/hypertile.py new file mode 100644 index 00000000..0f40e2d3 --- /dev/null +++ b/extensions-builtin/hypertile/hypertile.py @@ -0,0 +1,351 @@ +""" +Hypertile module for splitting attention layers in SD-1.5 U-Net and SD-1.5 VAE +Warn: The patch works well only if the input image has a width and height that are multiples of 128 +Original author: @tfernd Github: https://github.com/tfernd/HyperTile +""" + +from __future__ import annotations + +from dataclasses import dataclass +from typing import Callable + +from functools import wraps, cache + +import math +import torch.nn as nn +import random + +from einops import rearrange + + +@dataclass +class HypertileParams: + depth = 0 + layer_name = "" + tile_size: int = 0 + swap_size: int = 0 + aspect_ratio: float = 1.0 + forward = None + enabled = False + + + +# TODO add SD-XL layers +DEPTH_LAYERS = { + 0: [ + # SD 1.5 U-Net (diffusers) + "down_blocks.0.attentions.0.transformer_blocks.0.attn1", + "down_blocks.0.attentions.1.transformer_blocks.0.attn1", + "up_blocks.3.attentions.0.transformer_blocks.0.attn1", + "up_blocks.3.attentions.1.transformer_blocks.0.attn1", + "up_blocks.3.attentions.2.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "input_blocks.1.1.transformer_blocks.0.attn1", + "input_blocks.2.1.transformer_blocks.0.attn1", + "output_blocks.9.1.transformer_blocks.0.attn1", + "output_blocks.10.1.transformer_blocks.0.attn1", + "output_blocks.11.1.transformer_blocks.0.attn1", + # SD 1.5 VAE + "decoder.mid_block.attentions.0", + "decoder.mid.attn_1", + ], + 1: [ + # SD 1.5 U-Net (diffusers) + "down_blocks.1.attentions.0.transformer_blocks.0.attn1", + "down_blocks.1.attentions.1.transformer_blocks.0.attn1", + "up_blocks.2.attentions.0.transformer_blocks.0.attn1", + "up_blocks.2.attentions.1.transformer_blocks.0.attn1", + "up_blocks.2.attentions.2.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "input_blocks.4.1.transformer_blocks.0.attn1", + "input_blocks.5.1.transformer_blocks.0.attn1", + "output_blocks.6.1.transformer_blocks.0.attn1", + "output_blocks.7.1.transformer_blocks.0.attn1", + "output_blocks.8.1.transformer_blocks.0.attn1", + ], + 2: [ + # SD 1.5 U-Net (diffusers) + "down_blocks.2.attentions.0.transformer_blocks.0.attn1", + "down_blocks.2.attentions.1.transformer_blocks.0.attn1", + "up_blocks.1.attentions.0.transformer_blocks.0.attn1", + "up_blocks.1.attentions.1.transformer_blocks.0.attn1", + "up_blocks.1.attentions.2.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "input_blocks.7.1.transformer_blocks.0.attn1", + "input_blocks.8.1.transformer_blocks.0.attn1", + "output_blocks.3.1.transformer_blocks.0.attn1", + "output_blocks.4.1.transformer_blocks.0.attn1", + "output_blocks.5.1.transformer_blocks.0.attn1", + ], + 3: [ + # SD 1.5 U-Net (diffusers) + "mid_block.attentions.0.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "middle_block.1.transformer_blocks.0.attn1", + ], +} +# XL layers, thanks for GitHub@gel-crabs for the help +DEPTH_LAYERS_XL = { + 0: [ + # SD 1.5 U-Net (diffusers) + "down_blocks.0.attentions.0.transformer_blocks.0.attn1", + "down_blocks.0.attentions.1.transformer_blocks.0.attn1", + "up_blocks.3.attentions.0.transformer_blocks.0.attn1", + "up_blocks.3.attentions.1.transformer_blocks.0.attn1", + "up_blocks.3.attentions.2.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "input_blocks.4.1.transformer_blocks.0.attn1", + "input_blocks.5.1.transformer_blocks.0.attn1", + "output_blocks.3.1.transformer_blocks.0.attn1", + "output_blocks.4.1.transformer_blocks.0.attn1", + "output_blocks.5.1.transformer_blocks.0.attn1", + # SD 1.5 VAE + "decoder.mid_block.attentions.0", + "decoder.mid.attn_1", + ], + 1: [ + # SD 1.5 U-Net (diffusers) + #"down_blocks.1.attentions.0.transformer_blocks.0.attn1", + #"down_blocks.1.attentions.1.transformer_blocks.0.attn1", + #"up_blocks.2.attentions.0.transformer_blocks.0.attn1", + #"up_blocks.2.attentions.1.transformer_blocks.0.attn1", + #"up_blocks.2.attentions.2.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "input_blocks.4.1.transformer_blocks.1.attn1", + "input_blocks.5.1.transformer_blocks.1.attn1", + "output_blocks.3.1.transformer_blocks.1.attn1", + "output_blocks.4.1.transformer_blocks.1.attn1", + "output_blocks.5.1.transformer_blocks.1.attn1", + "input_blocks.7.1.transformer_blocks.0.attn1", + "input_blocks.8.1.transformer_blocks.0.attn1", + "output_blocks.0.1.transformer_blocks.0.attn1", + "output_blocks.1.1.transformer_blocks.0.attn1", + "output_blocks.2.1.transformer_blocks.0.attn1", + "input_blocks.7.1.transformer_blocks.1.attn1", + "input_blocks.8.1.transformer_blocks.1.attn1", + "output_blocks.0.1.transformer_blocks.1.attn1", + "output_blocks.1.1.transformer_blocks.1.attn1", + "output_blocks.2.1.transformer_blocks.1.attn1", + "input_blocks.7.1.transformer_blocks.2.attn1", + "input_blocks.8.1.transformer_blocks.2.attn1", + "output_blocks.0.1.transformer_blocks.2.attn1", + "output_blocks.1.1.transformer_blocks.2.attn1", + "output_blocks.2.1.transformer_blocks.2.attn1", + "input_blocks.7.1.transformer_blocks.3.attn1", + "input_blocks.8.1.transformer_blocks.3.attn1", + "output_blocks.0.1.transformer_blocks.3.attn1", + "output_blocks.1.1.transformer_blocks.3.attn1", + "output_blocks.2.1.transformer_blocks.3.attn1", + "input_blocks.7.1.transformer_blocks.4.attn1", + "input_blocks.8.1.transformer_blocks.4.attn1", + "output_blocks.0.1.transformer_blocks.4.attn1", + "output_blocks.1.1.transformer_blocks.4.attn1", + "output_blocks.2.1.transformer_blocks.4.attn1", + "input_blocks.7.1.transformer_blocks.5.attn1", + "input_blocks.8.1.transformer_blocks.5.attn1", + "output_blocks.0.1.transformer_blocks.5.attn1", + "output_blocks.1.1.transformer_blocks.5.attn1", + "output_blocks.2.1.transformer_blocks.5.attn1", + "input_blocks.7.1.transformer_blocks.6.attn1", + "input_blocks.8.1.transformer_blocks.6.attn1", + "output_blocks.0.1.transformer_blocks.6.attn1", + "output_blocks.1.1.transformer_blocks.6.attn1", + "output_blocks.2.1.transformer_blocks.6.attn1", + "input_blocks.7.1.transformer_blocks.7.attn1", + "input_blocks.8.1.transformer_blocks.7.attn1", + "output_blocks.0.1.transformer_blocks.7.attn1", + "output_blocks.1.1.transformer_blocks.7.attn1", + "output_blocks.2.1.transformer_blocks.7.attn1", + "input_blocks.7.1.transformer_blocks.8.attn1", + "input_blocks.8.1.transformer_blocks.8.attn1", + "output_blocks.0.1.transformer_blocks.8.attn1", + "output_blocks.1.1.transformer_blocks.8.attn1", + "output_blocks.2.1.transformer_blocks.8.attn1", + "input_blocks.7.1.transformer_blocks.9.attn1", + "input_blocks.8.1.transformer_blocks.9.attn1", + "output_blocks.0.1.transformer_blocks.9.attn1", + "output_blocks.1.1.transformer_blocks.9.attn1", + "output_blocks.2.1.transformer_blocks.9.attn1", + ], + 2: [ + # SD 1.5 U-Net (diffusers) + "mid_block.attentions.0.transformer_blocks.0.attn1", + # SD 1.5 U-Net (ldm) + "middle_block.1.transformer_blocks.0.attn1", + "middle_block.1.transformer_blocks.1.attn1", + "middle_block.1.transformer_blocks.2.attn1", + "middle_block.1.transformer_blocks.3.attn1", + "middle_block.1.transformer_blocks.4.attn1", + "middle_block.1.transformer_blocks.5.attn1", + "middle_block.1.transformer_blocks.6.attn1", + "middle_block.1.transformer_blocks.7.attn1", + "middle_block.1.transformer_blocks.8.attn1", + "middle_block.1.transformer_blocks.9.attn1", + ], + 3 : [] # TODO - separate layers for SD-XL +} + + +RNG_INSTANCE = random.Random() + +@cache +def get_divisors(value: int, min_value: int, /, max_options: int = 1) -> list[int]: + """ + Returns divisors of value that + x * min_value <= value + in big -> small order, amount of divisors is limited by max_options + """ + max_options = max(1, max_options) # at least 1 option should be returned + min_value = min(min_value, value) + divisors = [i for i in range(min_value, value + 1) if value % i == 0] # divisors in small -> big order + ns = [value // i for i in divisors[:max_options]] # has at least 1 element # big -> small order + return ns + + +def random_divisor(value: int, min_value: int, /, max_options: int = 1) -> int: + """ + Returns a random divisor of value that + x * min_value <= value + if max_options is 1, the behavior is deterministic + """ + ns = get_divisors(value, min_value, max_options=max_options) # get cached divisors + idx = RNG_INSTANCE.randint(0, len(ns) - 1) + + return ns[idx] + + +def set_hypertile_seed(seed: int) -> None: + RNG_INSTANCE.seed(seed) + + +@cache +def largest_tile_size_available(width: int, height: int) -> int: + """ + Calculates the largest tile size available for a given width and height + Tile size is always a power of 2 + """ + gcd = math.gcd(width, height) + largest_tile_size_available = 1 + while gcd % (largest_tile_size_available * 2) == 0: + largest_tile_size_available *= 2 + return largest_tile_size_available + + +def iterative_closest_divisors(hw:int, aspect_ratio:float) -> tuple[int, int]: + """ + Finds h and w such that h*w = hw and h/w = aspect_ratio + We check all possible divisors of hw and return the closest to the aspect ratio + """ + divisors = [i for i in range(2, hw + 1) if hw % i == 0] # all divisors of hw + pairs = [(i, hw // i) for i in divisors] # all pairs of divisors of hw + ratios = [w/h for h, w in pairs] # all ratios of pairs of divisors of hw + closest_ratio = min(ratios, key=lambda x: abs(x - aspect_ratio)) # closest ratio to aspect_ratio + closest_pair = pairs[ratios.index(closest_ratio)] # closest pair of divisors to aspect_ratio + return closest_pair + + +@cache +def find_hw_candidates(hw:int, aspect_ratio:float) -> tuple[int, int]: + """ + Finds h and w such that h*w = hw and h/w = aspect_ratio + """ + h, w = round(math.sqrt(hw * aspect_ratio)), round(math.sqrt(hw / aspect_ratio)) + # find h and w such that h*w = hw and h/w = aspect_ratio + if h * w != hw: + w_candidate = hw / h + # check if w is an integer + if not w_candidate.is_integer(): + h_candidate = hw / w + # check if h is an integer + if not h_candidate.is_integer(): + return iterative_closest_divisors(hw, aspect_ratio) + else: + h = int(h_candidate) + else: + w = int(w_candidate) + return h, w + + +def self_attn_forward(params: HypertileParams, scale_depth=True) -> Callable: + + @wraps(params.forward) + def wrapper(*args, **kwargs): + if not params.enabled: + return params.forward(*args, **kwargs) + + latent_tile_size = max(128, params.tile_size) // 8 + x = args[0] + + # VAE + if x.ndim == 4: + b, c, h, w = x.shape + + nh = random_divisor(h, latent_tile_size, params.swap_size) + nw = random_divisor(w, latent_tile_size, params.swap_size) + + if nh * nw > 1: + x = rearrange(x, "b c (nh h) (nw w) -> (b nh nw) c h w", nh=nh, nw=nw) # split into nh * nw tiles + + out = params.forward(x, *args[1:], **kwargs) + + if nh * nw > 1: + out = rearrange(out, "(b nh nw) c h w -> b c (nh h) (nw w)", nh=nh, nw=nw) + + # U-Net + else: + hw: int = x.size(1) + h, w = find_hw_candidates(hw, params.aspect_ratio) + assert h * w == hw, f"Invalid aspect ratio {params.aspect_ratio} for input of shape {x.shape}, hw={hw}, h={h}, w={w}" + + factor = 2 ** params.depth if scale_depth else 1 + nh = random_divisor(h, latent_tile_size * factor, params.swap_size) + nw = random_divisor(w, latent_tile_size * factor, params.swap_size) + + if nh * nw > 1: + x = rearrange(x, "b (nh h nw w) c -> (b nh nw) (h w) c", h=h // nh, w=w // nw, nh=nh, nw=nw) + + out = params.forward(x, *args[1:], **kwargs) + + if nh * nw > 1: + out = rearrange(out, "(b nh nw) hw c -> b nh nw hw c", nh=nh, nw=nw) + out = rearrange(out, "b nh nw (h w) c -> b (nh h nw w) c", h=h // nh, w=w // nw) + + return out + + return wrapper + + +def hypertile_hook_model(model: nn.Module, width, height, *, enable=False, tile_size_max=128, swap_size=1, max_depth=3, is_sdxl=False): + hypertile_layers = getattr(model, "__webui_hypertile_layers", None) + if hypertile_layers is None: + if not enable: + return + + hypertile_layers = {} + layers = DEPTH_LAYERS_XL if is_sdxl else DEPTH_LAYERS + + for depth in range(4): + for layer_name, module in model.named_modules(): + if any(layer_name.endswith(try_name) for try_name in layers[depth]): + params = HypertileParams() + module.__webui_hypertile_params = params + params.forward = module.forward + params.depth = depth + params.layer_name = layer_name + module.forward = self_attn_forward(params) + + hypertile_layers[layer_name] = 1 + + model.__webui_hypertile_layers = hypertile_layers + + aspect_ratio = width / height + tile_size = min(largest_tile_size_available(width, height), tile_size_max) + + for layer_name, module in model.named_modules(): + if layer_name in hypertile_layers: + params = module.__webui_hypertile_params + + params.tile_size = tile_size + params.swap_size = swap_size + params.aspect_ratio = aspect_ratio + params.enabled = enable and params.depth <= max_depth diff --git a/extensions-builtin/hypertile/scripts/hypertile_script.py b/extensions-builtin/hypertile/scripts/hypertile_script.py new file mode 100644 index 00000000..d3ab6091 --- /dev/null +++ b/extensions-builtin/hypertile/scripts/hypertile_script.py @@ -0,0 +1,78 @@ +import hypertile
+from modules import scripts, script_callbacks, shared
+from scripts.hypertile_xyz import add_axis_options
+
+
+class ScriptHypertile(scripts.Script):
+ name = "Hypertile"
+
+ def title(self):
+ return self.name
+
+ def show(self, is_img2img):
+ return scripts.AlwaysVisible
+
+ def process(self, p, *args):
+ hypertile.set_hypertile_seed(p.all_seeds[0])
+
+ configure_hypertile(p.width, p.height, enable_unet=shared.opts.hypertile_enable_unet)
+
+ def before_hr(self, p, *args):
+ # exclusive hypertile seed for the second pass
+ if not shared.opts.hypertile_enable_unet:
+ hypertile.set_hypertile_seed(p.all_seeds[0])
+ configure_hypertile(p.hr_upscale_to_x, p.hr_upscale_to_y, enable_unet=shared.opts.hypertile_enable_unet_secondpass)
+
+
+def configure_hypertile(width, height, enable_unet=True):
+ hypertile.hypertile_hook_model(
+ shared.sd_model.first_stage_model,
+ width,
+ height,
+ swap_size=shared.opts.hypertile_swap_size_vae,
+ max_depth=shared.opts.hypertile_max_depth_vae,
+ tile_size_max=shared.opts.hypertile_max_tile_vae,
+ enable=shared.opts.hypertile_enable_vae,
+ )
+
+ hypertile.hypertile_hook_model(
+ shared.sd_model.model,
+ width,
+ height,
+ swap_size=shared.opts.hypertile_swap_size_unet,
+ max_depth=shared.opts.hypertile_max_depth_unet,
+ tile_size_max=shared.opts.hypertile_max_tile_unet,
+ enable=enable_unet,
+ is_sdxl=shared.sd_model.is_sdxl
+ )
+
+
+def on_ui_settings():
+ import gradio as gr
+
+ options = {
+ "hypertile_explanation": shared.OptionHTML("""
+ <a href='https://github.com/tfernd/HyperTile'>Hypertile</a> optimizes the self-attention layer within U-Net and VAE models,
+ resulting in a reduction in computation time ranging from 1 to 4 times. The larger the generated image is, the greater the
+ benefit.
+ """),
+
+ "hypertile_enable_unet": shared.OptionInfo(False, "Enable Hypertile U-Net").info("noticeable change in details of the generated picture; if enabled, overrides the setting below"),
+ "hypertile_enable_unet_secondpass": shared.OptionInfo(False, "Enable Hypertile U-Net for hires fix second pass"),
+ "hypertile_max_depth_unet": shared.OptionInfo(3, "Hypertile U-Net max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}),
+ "hypertile_max_tile_unet": shared.OptionInfo(256, "Hypertile U-net max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),
+ "hypertile_swap_size_unet": shared.OptionInfo(3, "Hypertile U-net swap size", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}),
+
+ "hypertile_enable_vae": shared.OptionInfo(False, "Enable Hypertile VAE").info("minimal change in the generated picture"),
+ "hypertile_max_depth_vae": shared.OptionInfo(3, "Hypertile VAE max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}),
+ "hypertile_max_tile_vae": shared.OptionInfo(128, "Hypertile VAE max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),
+ "hypertile_swap_size_vae": shared.OptionInfo(3, "Hypertile VAE swap size ", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}),
+ }
+
+ for name, opt in options.items():
+ opt.section = ('hypertile', "Hypertile")
+ shared.opts.add_option(name, opt)
+
+
+script_callbacks.on_ui_settings(on_ui_settings)
+script_callbacks.on_before_ui(add_axis_options)
diff --git a/extensions-builtin/hypertile/scripts/hypertile_xyz.py b/extensions-builtin/hypertile/scripts/hypertile_xyz.py new file mode 100644 index 00000000..9e96ae3c --- /dev/null +++ b/extensions-builtin/hypertile/scripts/hypertile_xyz.py @@ -0,0 +1,51 @@ +from modules import scripts +from modules.shared import opts + +xyz_grid = [x for x in scripts.scripts_data if x.script_class.__module__ == "xyz_grid.py"][0].module + +def int_applier(value_name:str, min_range:int = -1, max_range:int = -1): + """ + Returns a function that applies the given value to the given value_name in opts.data. + """ + def validate(value_name:str, value:str): + value = int(value) + # validate value + if not min_range == -1: + assert value >= min_range, f"Value {value} for {value_name} must be greater than or equal to {min_range}" + if not max_range == -1: + assert value <= max_range, f"Value {value} for {value_name} must be less than or equal to {max_range}" + def apply_int(p, x, xs): + validate(value_name, x) + opts.data[value_name] = int(x) + return apply_int + +def bool_applier(value_name:str): + """ + Returns a function that applies the given value to the given value_name in opts.data. + """ + def validate(value_name:str, value:str): + assert value.lower() in ["true", "false"], f"Value {value} for {value_name} must be either true or false" + def apply_bool(p, x, xs): + validate(value_name, x) + value_boolean = x.lower() == "true" + opts.data[value_name] = value_boolean + return apply_bool + +def add_axis_options(): + extra_axis_options = [ + xyz_grid.AxisOption("[Hypertile] Unet First pass Enabled", str, bool_applier("hypertile_enable_unet"), choices=xyz_grid.boolean_choice(reverse=True)), + xyz_grid.AxisOption("[Hypertile] Unet Second pass Enabled", str, bool_applier("hypertile_enable_unet_secondpass"), choices=xyz_grid.boolean_choice(reverse=True)), + xyz_grid.AxisOption("[Hypertile] Unet Max Depth", int, int_applier("hypertile_max_depth_unet", 0, 3), choices=lambda: [str(x) for x in range(4)]), + xyz_grid.AxisOption("[Hypertile] Unet Max Tile Size", int, int_applier("hypertile_max_tile_unet", 0, 512)), + xyz_grid.AxisOption("[Hypertile] Unet Swap Size", int, int_applier("hypertile_swap_size_unet", 0, 64)), + xyz_grid.AxisOption("[Hypertile] VAE Enabled", str, bool_applier("hypertile_enable_vae"), choices=xyz_grid.boolean_choice(reverse=True)), + xyz_grid.AxisOption("[Hypertile] VAE Max Depth", int, int_applier("hypertile_max_depth_vae", 0, 3), choices=lambda: [str(x) for x in range(4)]), + xyz_grid.AxisOption("[Hypertile] VAE Max Tile Size", int, int_applier("hypertile_max_tile_vae", 0, 512)), + xyz_grid.AxisOption("[Hypertile] VAE Swap Size", int, int_applier("hypertile_swap_size_vae", 0, 64)), + ] + set_a = {opt.label for opt in xyz_grid.axis_options} + set_b = {opt.label for opt in extra_axis_options} + if set_a.intersection(set_b): + return + + xyz_grid.axis_options.extend(extra_axis_options) diff --git a/javascript/extraNetworks.js b/javascript/extraNetworks.js index a1bf29a8..98a7abb7 100644 --- a/javascript/extraNetworks.js +++ b/javascript/extraNetworks.js @@ -130,6 +130,10 @@ function extraNetworksMovePromptToTab(tabname, id, showPrompt, showNegativePromp } else { promptContainer.insertBefore(prompt, promptContainer.firstChild); } + + if (elem) { + elem.classList.toggle('extra-page-prompts-active', showNegativePrompt || showPrompt); + } } @@ -388,3 +392,9 @@ function extraNetworksRefreshSingleCard(page, tabname, name) { } }); } + +window.addEventListener("keydown", function(event) { + if (event.key == "Escape") { + closePopup(); + } +}); diff --git a/javascript/settings.js b/javascript/settings.js index 4e79ec00..e6009290 100644 --- a/javascript/settings.js +++ b/javascript/settings.js @@ -44,3 +44,28 @@ onUiLoaded(function() { buttonShowAllPages.addEventListener("click", settingsShowAllTabs); }); + + +onOptionsChanged(function() { + if (gradioApp().querySelector('#settings .settings-category')) return; + + var sectionMap = {}; + gradioApp().querySelectorAll('#settings > div > button').forEach(function(x) { + sectionMap[x.textContent.trim()] = x; + }); + + opts._categories.forEach(function(x) { + var section = x[0]; + var category = x[1]; + + var span = document.createElement('SPAN'); + span.textContent = category; + span.className = 'settings-category'; + + var sectionElem = sectionMap[section]; + if (!sectionElem) return; + + sectionElem.parentElement.insertBefore(span, sectionElem); + }); +}); + diff --git a/modules/cache.py b/modules/cache.py index ff26a213..2d37e7b9 100644 --- a/modules/cache.py +++ b/modules/cache.py @@ -32,7 +32,7 @@ def dump_cache(): with cache_lock:
cache_filename_tmp = cache_filename + "-"
with open(cache_filename_tmp, "w", encoding="utf8") as file:
- json.dump(cache_data, file, indent=4)
+ json.dump(cache_data, file, indent=4, ensure_ascii=False)
os.replace(cache_filename_tmp, cache_filename)
diff --git a/modules/devices.py b/modules/devices.py index 1d4eb563..f97f9cfb 100644 --- a/modules/devices.py +++ b/modules/devices.py @@ -38,7 +38,7 @@ def get_optimal_device(): def get_device_for(task): - if task in shared.cmd_opts.use_cpu: + if task in shared.cmd_opts.use_cpu or "all" in shared.cmd_opts.use_cpu: return cpu return get_optimal_device() diff --git a/modules/errors.py b/modules/errors.py index 8c339464..eb234a83 100644 --- a/modules/errors.py +++ b/modules/errors.py @@ -6,6 +6,21 @@ import traceback exception_records = []
+def format_traceback(tb):
+ return [[f"{x.filename}, line {x.lineno}, {x.name}", x.line] for x in traceback.extract_tb(tb)]
+
+
+def format_exception(e, tb):
+ return {"exception": str(e), "traceback": format_traceback(tb)}
+
+
+def get_exceptions():
+ try:
+ return list(reversed(exception_records))
+ except Exception as e:
+ return str(e)
+
+
def record_exception():
_, e, tb = sys.exc_info()
if e is None:
@@ -14,8 +29,7 @@ def record_exception(): if exception_records and exception_records[-1] == e:
return
- from modules import sysinfo
- exception_records.append(sysinfo.format_exception(e, tb))
+ exception_records.append(format_exception(e, tb))
if len(exception_records) > 5:
exception_records.pop(0)
diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index 0a606515..4efe53e0 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -1,3 +1,4 @@ +from __future__ import annotations
import base64
import io
import json
@@ -15,9 +16,6 @@ re_imagesize = re.compile(r"^(\d+)x(\d+)$") re_hypernet_hash = re.compile("\(([0-9a-f]+)\)$")
type_of_gr_update = type(gr.update())
-paste_fields = {}
-registered_param_bindings = []
-
class ParamBinding:
def __init__(self, paste_button, tabname, source_text_component=None, source_image_component=None, source_tabname=None, override_settings_component=None, paste_field_names=None):
@@ -30,6 +28,10 @@ class ParamBinding: self.paste_field_names = paste_field_names or []
+paste_fields: dict[str, dict] = {}
+registered_param_bindings: list[ParamBinding] = []
+
+
def reset():
paste_fields.clear()
registered_param_bindings.clear()
@@ -113,7 +115,6 @@ def register_paste_params_button(binding: ParamBinding): def connect_paste_params_buttons():
- binding: ParamBinding
for binding in registered_param_bindings:
destination_image_component = paste_fields[binding.tabname]["init_img"]
fields = paste_fields[binding.tabname]["fields"]
@@ -313,6 +314,9 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model if "VAE Decoder" not in res:
res["VAE Decoder"] = "Full"
+ skip = set(shared.opts.infotext_skip_pasting)
+ res = {k: v for k, v in res.items() if k not in skip}
+
return res
@@ -443,3 +447,4 @@ def connect_paste(button, paste_fields, input_comp, override_settings_component, outputs=[],
show_progress=False,
)
+
diff --git a/modules/gradio_extensons.py b/modules/gradio_extensons.py index e6b6835a..7d88dc98 100644 --- a/modules/gradio_extensons.py +++ b/modules/gradio_extensons.py @@ -47,10 +47,20 @@ def Block_get_config(self): def BlockContext_init(self, *args, **kwargs):
+ if scripts.scripts_current is not None:
+ scripts.scripts_current.before_component(self, **kwargs)
+
+ scripts.script_callbacks.before_component_callback(self, **kwargs)
+
res = original_BlockContext_init(self, *args, **kwargs)
add_classes_to_gradio_component(self)
+ scripts.script_callbacks.after_component_callback(self, **kwargs)
+
+ if scripts.scripts_current is not None:
+ scripts.scripts_current.after_component(self, **kwargs)
+
return res
diff --git a/modules/mac_specific.py b/modules/mac_specific.py index 89256c5b..d96d86d7 100644 --- a/modules/mac_specific.py +++ b/modules/mac_specific.py @@ -1,6 +1,7 @@ import logging import torch +from torch import Tensor import platform from modules.sd_hijack_utils import CondFunc from packaging import version @@ -51,6 +52,17 @@ def cumsum_fix(input, cumsum_func, *args, **kwargs): return cumsum_func(input, *args, **kwargs) +# MPS workaround for https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046 +def interpolate_with_fp32_fallback(orig_func, *args, **kwargs) -> Tensor: + try: + return orig_func(*args, **kwargs) + except RuntimeError as e: + if "not implemented for" in str(e) and "Half" in str(e): + input_tensor = args[0] + return orig_func(input_tensor.to(torch.float32), *args[1:], **kwargs).to(input_tensor.dtype) + else: + print(f"An unexpected RuntimeError occurred: {str(e)}") + if has_mps: if platform.mac_ver()[0].startswith("13.2."): # MPS workaround for https://github.com/pytorch/pytorch/issues/95188, thanks to danieldk (https://github.com/explosion/curated-transformers/pull/124) @@ -77,6 +89,9 @@ if has_mps: # MPS workaround for https://github.com/pytorch/pytorch/issues/96113 CondFunc('torch.nn.functional.layer_norm', lambda orig_func, x, normalized_shape, weight, bias, eps, **kwargs: orig_func(x.float(), normalized_shape, weight.float() if weight is not None else None, bias.float() if bias is not None else bias, eps).to(x.dtype), lambda _, input, *args, **kwargs: len(args) == 4 and input.device.type == 'mps') + # MPS workaround for https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046 + CondFunc('torch.nn.functional.interpolate', interpolate_with_fp32_fallback, None) + # MPS workaround for https://github.com/pytorch/pytorch/issues/92311 if platform.processor() == 'i386': for funcName in ['torch.argmax', 'torch.Tensor.argmax']: diff --git a/modules/options.py b/modules/options.py index ab40aff7..4fead690 100644 --- a/modules/options.py +++ b/modules/options.py @@ -1,5 +1,6 @@ import json
import sys
+from dataclasses import dataclass
import gradio as gr
@@ -8,13 +9,14 @@ from modules.shared_cmd_options import cmd_opts class OptionInfo:
- def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, section=None, refresh=None, comment_before='', comment_after='', infotext=None, restrict_api=False):
+ def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, section=None, refresh=None, comment_before='', comment_after='', infotext=None, restrict_api=False, category_id=None):
self.default = default
self.label = label
self.component = component
self.component_args = component_args
self.onchange = onchange
self.section = section
+ self.category_id = category_id
self.refresh = refresh
self.do_not_save = False
@@ -63,7 +65,11 @@ class OptionHTML(OptionInfo): def options_section(section_identifier, options_dict):
for v in options_dict.values():
- v.section = section_identifier
+ if len(section_identifier) == 2:
+ v.section = section_identifier
+ elif len(section_identifier) == 3:
+ v.section = section_identifier[0:2]
+ v.category_id = section_identifier[2]
return options_dict
@@ -76,7 +82,7 @@ class Options: def __init__(self, data_labels: dict[str, OptionInfo], restricted_opts):
self.data_labels = data_labels
- self.data = {k: v.default for k, v in self.data_labels.items()}
+ self.data = {k: v.default for k, v in self.data_labels.items() if not v.do_not_save}
self.restricted_opts = restricted_opts
def __setattr__(self, key, value):
@@ -158,7 +164,7 @@ class Options: assert not cmd_opts.freeze_settings, "saving settings is disabled"
with open(filename, "w", encoding="utf8") as file:
- json.dump(self.data, file, indent=4)
+ json.dump(self.data, file, indent=4, ensure_ascii=False)
def same_type(self, x, y):
if x is None or y is None:
@@ -206,23 +212,59 @@ class Options: d = {k: self.data.get(k, v.default) for k, v in self.data_labels.items()}
d["_comments_before"] = {k: v.comment_before for k, v in self.data_labels.items() if v.comment_before is not None}
d["_comments_after"] = {k: v.comment_after for k, v in self.data_labels.items() if v.comment_after is not None}
+
+ item_categories = {}
+ for item in self.data_labels.values():
+ category = categories.mapping.get(item.category_id)
+ category = "Uncategorized" if category is None else category.label
+ if category not in item_categories:
+ item_categories[category] = item.section[1]
+
+ # _categories is a list of pairs: [section, category]. Each section (a setting page) will get a special heading above it with the category as text.
+ d["_categories"] = [[v, k] for k, v in item_categories.items()] + [["Defaults", "Other"]]
+
return json.dumps(d)
def add_option(self, key, info):
self.data_labels[key] = info
- if key not in self.data:
+ if key not in self.data and not info.do_not_save:
self.data[key] = info.default
def reorder(self):
- """reorder settings so that all items related to section always go together"""
+ """Reorder settings so that:
+ - all items related to section always go together
+ - all sections belonging to a category go together
+ - sections inside a category are ordered alphabetically
+ - categories are ordered by creation order
+
+ Category is a superset of sections: for category "postprocessing" there could be multiple sections: "face restoration", "upscaling".
+
+ This function also changes items' category_id so that all items belonging to a section have the same category_id.
+ """
+
+ category_ids = {}
+ section_categories = {}
- section_ids = {}
settings_items = self.data_labels.items()
for _, item in settings_items:
- if item.section not in section_ids:
- section_ids[item.section] = len(section_ids)
+ if item.section not in section_categories:
+ section_categories[item.section] = item.category_id
+
+ for _, item in settings_items:
+ item.category_id = section_categories.get(item.section)
+
+ for category_id in categories.mapping:
+ if category_id not in category_ids:
+ category_ids[category_id] = len(category_ids)
- self.data_labels = dict(sorted(settings_items, key=lambda x: section_ids[x[1].section]))
+ def sort_key(x):
+ item: OptionInfo = x[1]
+ category_order = category_ids.get(item.category_id, len(category_ids))
+ section_order = item.section[1]
+
+ return category_order, section_order
+
+ self.data_labels = dict(sorted(settings_items, key=sort_key))
def cast_value(self, key, value):
"""casts an arbitrary to the same type as this setting's value with key
@@ -245,3 +287,22 @@ class Options: value = expected_type(value)
return value
+
+
+@dataclass
+class OptionsCategory:
+ id: str
+ label: str
+
+class OptionsCategories:
+ def __init__(self):
+ self.mapping = {}
+
+ def register_category(self, category_id, label):
+ if category_id in self.mapping:
+ return category_id
+
+ self.mapping[category_id] = OptionsCategory(category_id, label)
+
+
+categories = OptionsCategories()
diff --git a/modules/processing.py b/modules/processing.py index b0e240a4..5ab6ddde 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -679,8 +679,8 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Size": f"{p.width}x{p.height}",
"Model hash": p.sd_model_hash if opts.add_model_hash_to_info else None,
"Model": p.sd_model_name if opts.add_model_name_to_info else None,
- "VAE hash": p.sd_vae_hash if opts.add_model_hash_to_info else None,
- "VAE": p.sd_vae_name if opts.add_model_name_to_info else None,
+ "VAE hash": p.sd_vae_hash if opts.add_vae_hash_to_info else None,
+ "VAE": p.sd_vae_name if opts.add_vae_name_to_info else None,
"Variation seed": (None if p.subseed_strength == 0 else (p.all_subseeds[0] if use_main_prompt else all_subseeds[index])),
"Variation seed strength": (None if p.subseed_strength == 0 else p.subseed_strength),
"Seed resize from": (None if p.seed_resize_from_w <= 0 or p.seed_resize_from_h <= 0 else f"{p.seed_resize_from_w}x{p.seed_resize_from_h}"),
@@ -799,7 +799,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: infotexts = []
output_images = []
-
with torch.no_grad(), p.sd_model.ema_scope():
with devices.autocast():
p.init(p.all_prompts, p.all_seeds, p.all_subseeds)
@@ -873,7 +872,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: else:
if opts.sd_vae_decode_method != 'Full':
p.extra_generation_params['VAE Decoder'] = opts.sd_vae_decode_method
-
x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True)
x_samples_ddim = torch.stack(x_samples_ddim).float()
@@ -1147,6 +1145,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): if not self.enable_hr:
return samples
+ devices.torch_gc()
if self.latent_scale_mode is None:
decoded_samples = torch.stack(decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True)).to(dtype=torch.float32)
@@ -1156,8 +1155,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): with sd_models.SkipWritingToConfig():
sd_models.reload_model_weights(info=self.hr_checkpoint_info)
- devices.torch_gc()
-
return self.sample_hr_pass(samples, decoded_samples, seeds, subseeds, subseed_strength, prompts)
def sample_hr_pass(self, samples, decoded_samples, seeds, subseeds, subseed_strength, prompts):
@@ -1165,7 +1162,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): return samples
self.is_hr_pass = True
-
target_width = self.hr_upscale_to_x
target_height = self.hr_upscale_to_y
@@ -1254,7 +1250,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): decoded_samples = decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True)
self.is_hr_pass = False
-
return decoded_samples
def close(self):
diff --git a/modules/scripts.py b/modules/scripts.py index b0689a23..7f9454eb 100644 --- a/modules/scripts.py +++ b/modules/scripts.py @@ -560,17 +560,25 @@ class ScriptRunner: on_after.clear()
def create_script_ui(self, script):
- import modules.api.models as api_models
script.args_from = len(self.inputs)
script.args_to = len(self.inputs)
+ try:
+ self.create_script_ui_inner(script)
+ except Exception:
+ errors.report(f"Error creating UI for {script.name}: ", exc_info=True)
+
+ def create_script_ui_inner(self, script):
+ import modules.api.models as api_models
+
controls = wrap_call(script.ui, script.filename, "ui", script.is_img2img)
if controls is None:
return
script.name = wrap_call(script.title, script.filename, "title", default=script.filename).lower()
+
api_args = []
for control in controls:
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index 0157e19f..3d340fc9 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -38,9 +38,6 @@ ldm.models.diffusion.ddpm.print = shared.ldm_print optimizers = []
current_optimizer: sd_hijack_optimizations.SdOptimization = None
-ldm_original_forward = patches.patch(__file__, ldm.modules.diffusionmodules.openaimodel.UNetModel, "forward", sd_unet.UNetModel_forward)
-sgm_original_forward = patches.patch(__file__, sgm.modules.diffusionmodules.openaimodel.UNetModel, "forward", sd_unet.UNetModel_forward)
-
def list_optimizers():
new_optimizers = script_callbacks.list_optimizers_callback()
@@ -258,6 +255,9 @@ class StableDiffusionModelHijack: import modules.models.diffusion.ddpm_edit
+ ldm_original_forward = patches.patch(__file__, ldm.modules.diffusionmodules.openaimodel.UNetModel, "forward", sd_unet.UNetModel_forward)
+ sgm_original_forward = patches.patch(__file__, sgm.modules.diffusionmodules.openaimodel.UNetModel, "forward", sd_unet.UNetModel_forward)
+
if isinstance(m, ldm.models.diffusion.ddpm.LatentDiffusion):
sd_unet.original_forward = ldm_original_forward
elif isinstance(m, modules.models.diffusion.ddpm_edit.LatentDiffusion):
@@ -303,6 +303,9 @@ class StableDiffusionModelHijack: self.layers = None
self.clip = None
+ patches.undo(__file__, ldm.modules.diffusionmodules.openaimodel.UNetModel, "forward")
+ patches.undo(__file__, sgm.modules.diffusionmodules.openaimodel.UNetModel, "forward")
+
sd_unet.original_forward = None
diff --git a/modules/sd_models.py b/modules/sd_models.py index 841402e8..9355f1e1 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -230,15 +230,19 @@ def select_checkpoint(): return checkpoint_info
-checkpoint_dict_replacements = {
+checkpoint_dict_replacements_sd1 = {
'cond_stage_model.transformer.embeddings.': 'cond_stage_model.transformer.text_model.embeddings.',
'cond_stage_model.transformer.encoder.': 'cond_stage_model.transformer.text_model.encoder.',
'cond_stage_model.transformer.final_layer_norm.': 'cond_stage_model.transformer.text_model.final_layer_norm.',
}
+checkpoint_dict_replacements_sd2_turbo = { # Converts SD 2.1 Turbo from SGM to LDM format.
+ 'conditioner.embedders.0.': 'cond_stage_model.',
+}
+
-def transform_checkpoint_dict_key(k):
- for text, replacement in checkpoint_dict_replacements.items():
+def transform_checkpoint_dict_key(k, replacements):
+ for text, replacement in replacements.items():
if k.startswith(text):
k = replacement + k[len(text):]
@@ -249,9 +253,14 @@ def get_state_dict_from_checkpoint(pl_sd): pl_sd = pl_sd.pop("state_dict", pl_sd)
pl_sd.pop("state_dict", None)
+ is_sd2_turbo = 'conditioner.embedders.0.model.ln_final.weight' in pl_sd and pl_sd['conditioner.embedders.0.model.ln_final.weight'].size()[0] == 1024
+
sd = {}
for k, v in pl_sd.items():
- new_key = transform_checkpoint_dict_key(k)
+ if is_sd2_turbo:
+ new_key = transform_checkpoint_dict_key(k, checkpoint_dict_replacements_sd2_turbo)
+ else:
+ new_key = transform_checkpoint_dict_key(k, checkpoint_dict_replacements_sd1)
if new_key is not None:
sd[new_key] = v
diff --git a/modules/sd_samplers_extra.py b/modules/sd_samplers_extra.py index 1b981ca8..72fd0aa5 100644 --- a/modules/sd_samplers_extra.py +++ b/modules/sd_samplers_extra.py @@ -60,7 +60,7 @@ def restart_sampler(model, x, sigmas, extra_args=None, callback=None, disable=No sigma_restart = get_sigmas_karras(restart_steps, sigmas[min_idx].item(), sigmas[max_idx].item(), device=sigmas.device)[:-1]
while restart_times > 0:
restart_times -= 1
- step_list.extend([(old_sigma, new_sigma) for (old_sigma, new_sigma) in zip(sigma_restart[:-1], sigma_restart[1:])])
+ step_list.extend(zip(sigma_restart[:-1], sigma_restart[1:]))
last_sigma = None
for old_sigma, new_sigma in tqdm.tqdm(step_list, disable=disable):
diff --git a/modules/shared_items.py b/modules/shared_items.py index 5024b426..991971ad 100644 --- a/modules/shared_items.py +++ b/modules/shared_items.py @@ -66,6 +66,22 @@ def reload_hypernetworks(): shared.hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
+def get_infotext_names():
+ from modules import generation_parameters_copypaste, shared
+ res = {}
+
+ for info in shared.opts.data_labels.values():
+ if info.infotext:
+ res[info.infotext] = 1
+
+ for tab_data in generation_parameters_copypaste.paste_fields.values():
+ for _, name in tab_data.get("fields") or []:
+ if isinstance(name, str):
+ res[name] = 1
+
+ return list(res)
+
+
ui_reorder_categories_builtin_items = [
"prompt",
"image",
diff --git a/modules/shared_options.py b/modules/shared_options.py index 9bcd7914..1390152d 100644 --- a/modules/shared_options.py +++ b/modules/shared_options.py @@ -3,7 +3,7 @@ import gradio as gr from modules import localization, ui_components, shared_items, shared, interrogate, shared_gradio_themes
from modules.paths_internal import models_path, script_path, data_path, sd_configs_path, sd_default_config, sd_model_file, default_sd_model_file, extensions_dir, extensions_builtin_dir # noqa: F401
from modules.shared_cmd_options import cmd_opts
-from modules.options import options_section, OptionInfo, OptionHTML
+from modules.options import options_section, OptionInfo, OptionHTML, categories
options_templates = {}
hide_dirs = shared.hide_dirs
@@ -21,7 +21,14 @@ restricted_opts = { "outdir_init_images"
}
-options_templates.update(options_section(('saving-images', "Saving images/grids"), {
+categories.register_category("saving", "Saving images")
+categories.register_category("sd", "Stable Diffusion")
+categories.register_category("ui", "User Interface")
+categories.register_category("system", "System")
+categories.register_category("postprocessing", "Postprocessing")
+categories.register_category("training", "Training")
+
+options_templates.update(options_section(('saving-images', "Saving images/grids", "saving"), {
"samples_save": OptionInfo(True, "Always save all generated images"),
"samples_format": OptionInfo('png', 'File format for images'),
"samples_filename_pattern": OptionInfo("", "Images filename pattern", component_args=hide_dirs).link("wiki", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory"),
@@ -39,8 +46,6 @@ options_templates.update(options_section(('saving-images', "Saving images/grids" "grid_text_inactive_color": OptionInfo("#999999", "Inactive text color for image grids", ui_components.FormColorPicker, {}),
"grid_background_color": OptionInfo("#ffffff", "Background color for image grids", ui_components.FormColorPicker, {}),
- "enable_pnginfo": OptionInfo(True, "Save text information about generation parameters as chunks to png files"),
- "save_txt": OptionInfo(False, "Create a text file next to every image with generation parameters."),
"save_images_before_face_restoration": OptionInfo(False, "Save a copy of image before doing face restoration."),
"save_images_before_highres_fix": OptionInfo(False, "Save a copy of image before applying highres fix."),
"save_images_before_color_correction": OptionInfo(False, "Save a copy of image before applying color correction to img2img results"),
@@ -67,7 +72,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids" "notification_volume": OptionInfo(100, "Notification sound volume", gr.Slider, {"minimum": 0, "maximum": 100, "step": 1}).info("in %"),
}))
-options_templates.update(options_section(('saving-paths', "Paths for saving"), {
+options_templates.update(options_section(('saving-paths', "Paths for saving", "saving"), {
"outdir_samples": OptionInfo("", "Output directory for images; if empty, defaults to three directories below", component_args=hide_dirs),
"outdir_txt2img_samples": OptionInfo("outputs/txt2img-images", 'Output directory for txt2img images', component_args=hide_dirs),
"outdir_img2img_samples": OptionInfo("outputs/img2img-images", 'Output directory for img2img images', component_args=hide_dirs),
@@ -79,7 +84,7 @@ options_templates.update(options_section(('saving-paths', "Paths for saving"), { "outdir_init_images": OptionInfo("outputs/init-images", "Directory for saving init images when using img2img", component_args=hide_dirs),
}))
-options_templates.update(options_section(('saving-to-dirs', "Saving to a directory"), {
+options_templates.update(options_section(('saving-to-dirs', "Saving to a directory", "saving"), {
"save_to_dirs": OptionInfo(True, "Save images to a subdirectory"),
"grid_save_to_dirs": OptionInfo(True, "Save grids to a subdirectory"),
"use_save_to_dirs_for_ui": OptionInfo(False, "When using \"Save\" button, save images to a subdirectory"),
@@ -87,21 +92,21 @@ options_templates.update(options_section(('saving-to-dirs', "Saving to a directo "directories_max_prompt_words": OptionInfo(8, "Max prompt words for [prompt_words] pattern", gr.Slider, {"minimum": 1, "maximum": 20, "step": 1, **hide_dirs}),
}))
-options_templates.update(options_section(('upscaling', "Upscaling"), {
+options_templates.update(options_section(('upscaling', "Upscaling", "postprocessing"), {
"ESRGAN_tile": OptionInfo(192, "Tile size for ESRGAN upscalers.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}).info("0 = no tiling"),
"ESRGAN_tile_overlap": OptionInfo(8, "Tile overlap for ESRGAN upscalers.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}).info("Low values = visible seam"),
"realesrgan_enabled_models": OptionInfo(["R-ESRGAN 4x+", "R-ESRGAN 4x+ Anime6B"], "Select which Real-ESRGAN models to show in the web UI.", gr.CheckboxGroup, lambda: {"choices": shared_items.realesrgan_models_names()}),
"upscaler_for_img2img": OptionInfo(None, "Upscaler for img2img", gr.Dropdown, lambda: {"choices": [x.name for x in shared.sd_upscalers]}),
}))
-options_templates.update(options_section(('face-restoration', "Face restoration"), {
+options_templates.update(options_section(('face-restoration', "Face restoration", "postprocessing"), {
"face_restoration": OptionInfo(False, "Restore faces", infotext='Face restoration').info("will use a third-party model on generation result to reconstruct faces"),
"face_restoration_model": OptionInfo("CodeFormer", "Face restoration model", gr.Radio, lambda: {"choices": [x.name() for x in shared.face_restorers]}),
"code_former_weight": OptionInfo(0.5, "CodeFormer weight", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}).info("0 = maximum effect; 1 = minimum effect"),
"face_restoration_unload": OptionInfo(False, "Move face restoration model from VRAM into RAM after processing"),
}))
-options_templates.update(options_section(('system', "System"), {
+options_templates.update(options_section(('system', "System", "system"), {
"auto_launch_browser": OptionInfo("Local", "Automatically open webui in browser on startup", gr.Radio, lambda: {"choices": ["Disable", "Local", "Remote"]}),
"enable_console_prompts": OptionInfo(shared.cmd_opts.enable_console_prompts, "Print prompts to console when generating with txt2img and img2img."),
"show_warnings": OptionInfo(False, "Show warnings in console.").needs_reload_ui(),
@@ -116,13 +121,13 @@ options_templates.update(options_section(('system', "System"), { "dump_stacks_on_signal": OptionInfo(False, "Print stack traces before exiting the program with ctrl+c."),
}))
-options_templates.update(options_section(('API', "API"), {
+options_templates.update(options_section(('API', "API", "system"), {
"api_enable_requests": OptionInfo(True, "Allow http:// and https:// URLs for input images in API", restrict_api=True),
"api_forbid_local_requests": OptionInfo(True, "Forbid URLs to local resources", restrict_api=True),
"api_useragent": OptionInfo("", "User agent for requests", restrict_api=True),
}))
-options_templates.update(options_section(('training', "Training"), {
+options_templates.update(options_section(('training', "Training", "training"), {
"unload_models_when_training": OptionInfo(False, "Move VAE and CLIP to RAM when training if possible. Saves VRAM."),
"pin_memory": OptionInfo(False, "Turn on pin_memory for DataLoader. Makes training slightly faster but can increase memory usage."),
"save_optimizer_state": OptionInfo(False, "Saves Optimizer state as separate *.optim file. Training of embedding or HN can be resumed with the matching optim file."),
@@ -137,7 +142,7 @@ options_templates.update(options_section(('training', "Training"), { "training_tensorboard_flush_every": OptionInfo(120, "How often, in seconds, to flush the pending tensorboard events and summaries to disk."),
}))
-options_templates.update(options_section(('sd', "Stable Diffusion"), {
+options_templates.update(options_section(('sd', "Stable Diffusion", "sd"), {
"sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": shared_items.list_checkpoint_tiles(shared.opts.sd_checkpoint_dropdown_use_short)}, refresh=shared_items.refresh_checkpoints, infotext='Model hash'),
"sd_checkpoints_limit": OptionInfo(1, "Maximum number of checkpoints loaded at the same time", gr.Slider, {"minimum": 1, "maximum": 10, "step": 1}),
"sd_checkpoints_keep_in_cpu": OptionInfo(True, "Only keep one model on device").info("will keep models other than the currently used one in RAM rather than VRAM"),
@@ -154,14 +159,14 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { "hires_fix_refiner_pass": OptionInfo("second pass", "Hires fix: which pass to enable refiner for", gr.Radio, {"choices": ["first pass", "second pass", "both passes"]}, infotext="Hires refiner"),
}))
-options_templates.update(options_section(('sdxl', "Stable Diffusion XL"), {
+options_templates.update(options_section(('sdxl', "Stable Diffusion XL", "sd"), {
"sdxl_crop_top": OptionInfo(0, "crop top coordinate"),
"sdxl_crop_left": OptionInfo(0, "crop left coordinate"),
"sdxl_refiner_low_aesthetic_score": OptionInfo(2.5, "SDXL low aesthetic score", gr.Number).info("used for refiner model negative prompt"),
"sdxl_refiner_high_aesthetic_score": OptionInfo(6.0, "SDXL high aesthetic score", gr.Number).info("used for refiner model prompt"),
}))
-options_templates.update(options_section(('vae', "VAE"), {
+options_templates.update(options_section(('vae', "VAE", "sd"), {
"sd_vae_explanation": OptionHTML("""
<abbr title='Variational autoencoder'>VAE</abbr> is a neural network that transforms a standard <abbr title='red/green/blue'>RGB</abbr>
image into latent space representation and back. Latent space representation is what stable diffusion is working on during sampling
@@ -176,7 +181,7 @@ For img2img, VAE is used to process user's input image before the sampling, and "sd_vae_decode_method": OptionInfo("Full", "VAE type for decode", gr.Radio, {"choices": ["Full", "TAESD"]}, infotext='VAE Decoder').info("method to decode latent to image"),
}))
-options_templates.update(options_section(('img2img', "img2img"), {
+options_templates.update(options_section(('img2img', "img2img", "sd"), {
"inpainting_mask_weight": OptionInfo(1.0, "Inpainting conditioning mask strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Conditional mask weight'),
"initial_noise_multiplier": OptionInfo(1.0, "Noise multiplier for img2img", gr.Slider, {"minimum": 0.0, "maximum": 1.5, "step": 0.001}, infotext='Noise multiplier'),
"img2img_extra_noise": OptionInfo(0.0, "Extra noise multiplier for img2img and hires fix", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Extra noise').info("0 = disabled (default); should be lower than denoising strength"),
@@ -192,7 +197,7 @@ options_templates.update(options_section(('img2img', "img2img"), { "img2img_batch_show_results_limit": OptionInfo(32, "Show the first N batch img2img results in UI", gr.Slider, {"minimum": -1, "maximum": 1000, "step": 1}).info('0: disable, -1: show all images. Too many images can cause lag'),
}))
-options_templates.update(options_section(('optimizations', "Optimizations"), {
+options_templates.update(options_section(('optimizations', "Optimizations", "sd"), {
"cross_attention_optimization": OptionInfo("Automatic", "Cross attention optimization", gr.Dropdown, lambda: {"choices": shared_items.cross_attention_optimizations()}),
"s_min_uncond": OptionInfo(0.0, "Negative Guidance minimum sigma", gr.Slider, {"minimum": 0.0, "maximum": 15.0, "step": 0.01}).link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9177").info("skip negative prompt for some steps when the image is almost ready; 0=disable, higher=faster"),
"token_merging_ratio": OptionInfo(0.0, "Token merging ratio", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}, infotext='Token merging ratio').link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9256").info("0=disable, higher=faster"),
@@ -203,7 +208,7 @@ options_templates.update(options_section(('optimizations', "Optimizations"), { "batch_cond_uncond": OptionInfo(True, "Batch cond/uncond").info("do both conditional and unconditional denoising in one batch; uses a bit more VRAM during sampling, but improves speed; previously this was controlled by --always-batch-cond-uncond comandline argument"),
}))
-options_templates.update(options_section(('compatibility', "Compatibility"), {
+options_templates.update(options_section(('compatibility', "Compatibility", "sd"), {
"use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
"use_old_karras_scheduler_sigmas": OptionInfo(False, "Use old karras scheduler sigmas (0.1 to 10)."),
"no_dpmpp_sde_batch_determinism": OptionInfo(False, "Do not make DPM++ SDE deterministic across different batch sizes."),
@@ -228,7 +233,7 @@ options_templates.update(options_section(('interrogate', "Interrogate"), { "deepbooru_filter_tags": OptionInfo("", "deepbooru: filter out those tags").info("separate by comma"),
}))
-options_templates.update(options_section(('extra_networks', "Extra Networks"), {
+options_templates.update(options_section(('extra_networks', "Extra Networks", "sd"), {
"extra_networks_show_hidden_directories": OptionInfo(True, "Show hidden directories").info("directory is hidden if its name starts with \".\"."),
"extra_networks_hidden_models": OptionInfo("When searched", "Show cards for models in hidden directories", gr.Radio, {"choices": ["Always", "When searched", "Never"]}).info('"When searched" option will only show the item when the search string has 4 characters or more'),
"extra_networks_default_multiplier": OptionInfo(1.0, "Default multiplier for extra networks", gr.Slider, {"minimum": 0.0, "maximum": 2.0, "step": 0.01}),
@@ -245,47 +250,64 @@ options_templates.update(options_section(('extra_networks', "Extra Networks"), { "sd_hypernetwork": OptionInfo("None", "Add hypernetwork to prompt", gr.Dropdown, lambda: {"choices": ["None", *shared.hypernetworks]}, refresh=shared_items.reload_hypernetworks),
}))
-options_templates.update(options_section(('ui', "User interface"), {
- "localization": OptionInfo("None", "Localization", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)).needs_reload_ui(),
- "gradio_theme": OptionInfo("Default", "Gradio theme", ui_components.DropdownEditable, lambda: {"choices": ["Default"] + shared_gradio_themes.gradio_hf_hub_themes}).info("you can also manually enter any of themes from the <a href='https://huggingface.co/spaces/gradio/theme-gallery'>gallery</a>.").needs_reload_ui(),
- "gradio_themes_cache": OptionInfo(True, "Cache gradio themes locally").info("disable to update the selected Gradio theme"),
- "gallery_height": OptionInfo("", "Gallery height", gr.Textbox).info("an be any valid CSS value").needs_reload_ui(),
- "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"),
- "send_seed": OptionInfo(True, "Send seed when sending prompt or image to other interface"),
- "send_size": OptionInfo(True, "Send size when sending prompt or image to another interface"),
- "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"),
- "js_modal_lightbox_gamepad": OptionInfo(False, "Navigate image viewer with gamepad"),
- "js_modal_lightbox_gamepad_repeat": OptionInfo(250, "Gamepad repeat period, in milliseconds"),
- "show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
+options_templates.update(options_section(('ui_prompt_editing', "Prompt editing", "ui"), {
+ "keyedit_precision_attention": OptionInfo(0.1, "Precision for (attention:1.1) when editing the prompt with Ctrl+up/down", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
+ "keyedit_precision_extra": OptionInfo(0.05, "Precision for <extra networks:0.9> when editing the prompt with Ctrl+up/down", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
+ "keyedit_delimiters": OptionInfo(r".,\/!?%^*;:{}=`~() ", "Word delimiters when editing the prompt with Ctrl+up/down"),
+ "disable_token_counters": OptionInfo(False, "Disable prompt token counters").needs_reload_ui(),
+}))
+
+options_templates.update(options_section(('ui_gallery', "Gallery", "ui"), {
+ "return_grid": OptionInfo(True, "Show grid in gallery"),
+ "do_not_show_images": OptionInfo(False, "Do not show any images in gallery"),
+ "js_modal_lightbox": OptionInfo(True, "Full page image viewer: enable"),
+ "js_modal_lightbox_initially_zoomed": OptionInfo(True, "Full page image viewer: show images zoomed in by default"),
+ "js_modal_lightbox_gamepad": OptionInfo(False, "Full page image viewer: navigate with gamepad"),
+ "js_modal_lightbox_gamepad_repeat": OptionInfo(250, "Full page image viewer: gamepad repeat period").info("in milliseconds"),
+ "gallery_height": OptionInfo("", "Gallery height", gr.Textbox).info("can be any valid CSS value, for example 768px or 20em").needs_reload_ui(),
+}))
+
+options_templates.update(options_section(('ui_alternatives', "UI alternatives", "ui"), {
+ "compact_prompt_box": OptionInfo(False, "Compact prompt layout").info("puts prompt and negative prompt inside the Generate tab, leaving more vertical space for the image on the right").needs_reload_ui(),
"samplers_in_dropdown": OptionInfo(True, "Use dropdown for sampler selection instead of radio group").needs_reload_ui(),
"dimensions_and_batch_together": OptionInfo(True, "Show Width/Height and Batch sliders in same row").needs_reload_ui(),
- "keyedit_precision_attention": OptionInfo(0.1, "Ctrl+up/down precision when editing (attention:1.1)", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
- "keyedit_precision_extra": OptionInfo(0.05, "Ctrl+up/down precision when editing <extra networks:0.9>", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
- "keyedit_delimiters": OptionInfo(r".,\/!?%^*;:{}=`~() ", "Ctrl+up/down word delimiters"),
- "keyedit_delimiters_whitespace": OptionInfo(["Tab", "Carriage Return", "Line Feed"], "Ctrl+up/down whitespace delimiters", gr.CheckboxGroup, lambda: {"choices": ["Tab", "Carriage Return", "Line Feed"]}),
- "keyedit_move": OptionInfo(True, "Alt+left/right moves prompt elements"),
- "quicksettings_list": OptionInfo(["sd_model_checkpoint"], "Quicksettings list", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that appear at the top of page rather than in settings tab").needs_reload_ui(),
- "ui_tab_order": OptionInfo([], "UI tab order", ui_components.DropdownMulti, lambda: {"choices": list(shared.tab_names)}).needs_reload_ui(),
- "hidden_tabs": OptionInfo([], "Hidden UI tabs", ui_components.DropdownMulti, lambda: {"choices": list(shared.tab_names)}).needs_reload_ui(),
- "ui_reorder_list": OptionInfo([], "txt2img/img2img UI item order", ui_components.DropdownMulti, lambda: {"choices": list(shared_items.ui_reorder_categories())}).info("selected items appear first").needs_reload_ui(),
"sd_checkpoint_dropdown_use_short": OptionInfo(False, "Checkpoint dropdown: use filenames without paths").info("models in subdirectories like photo/sd15.ckpt will be listed as just sd15.ckpt"),
"hires_fix_show_sampler": OptionInfo(False, "Hires fix: show hires checkpoint and sampler selection").needs_reload_ui(),
"hires_fix_show_prompts": OptionInfo(False, "Hires fix: show hires prompt and negative prompt").needs_reload_ui(),
- "disable_token_counters": OptionInfo(False, "Disable prompt token counters").needs_reload_ui(),
"txt2img_settings_accordion": OptionInfo(False, "Settings in txt2img hidden under Accordion").needs_reload_ui(),
"img2img_settings_accordion": OptionInfo(False, "Settings in img2img hidden under Accordion").needs_reload_ui(),
- "compact_prompt_box": OptionInfo(False, "Compact prompt layout").info("puts prompt and negative prompt inside the Generate tab, leaving more vertical space for the image on the right").needs_reload_ui(),
+}))
+
+options_templates.update(options_section(('ui', "User interface", "ui"), {
+ "localization": OptionInfo("None", "Localization", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)).needs_reload_ui(),
+ "quicksettings_list": OptionInfo(["sd_model_checkpoint"], "Quicksettings list", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that appear at the top of page rather than in settings tab").needs_reload_ui(),
+ "ui_tab_order": OptionInfo([], "UI tab order", ui_components.DropdownMulti, lambda: {"choices": list(shared.tab_names)}).needs_reload_ui(),
+ "hidden_tabs": OptionInfo([], "Hidden UI tabs", ui_components.DropdownMulti, lambda: {"choices": list(shared.tab_names)}).needs_reload_ui(),
+ "ui_reorder_list": OptionInfo([], "UI item order for txt2img/img2img tabs", ui_components.DropdownMulti, lambda: {"choices": list(shared_items.ui_reorder_categories())}).info("selected items appear first").needs_reload_ui(),
+ "gradio_theme": OptionInfo("Default", "Gradio theme", ui_components.DropdownEditable, lambda: {"choices": ["Default"] + shared_gradio_themes.gradio_hf_hub_themes}).info("you can also manually enter any of themes from the <a href='https://huggingface.co/spaces/gradio/theme-gallery'>gallery</a>.").needs_reload_ui(),
+ "gradio_themes_cache": OptionInfo(True, "Cache gradio themes locally").info("disable to update the selected Gradio theme"),
+ "show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
+ "send_seed": OptionInfo(True, "Send seed when sending prompt or image to other interface"),
+ "send_size": OptionInfo(True, "Send size when sending prompt or image to another interface"),
}))
-options_templates.update(options_section(('infotext', "Infotext"), {
- "add_model_hash_to_info": OptionInfo(True, "Add model hash to generation information"),
- "add_model_name_to_info": OptionInfo(True, "Add model name to generation information"),
- "add_user_name_to_info": OptionInfo(False, "Add user name to generation information when authenticated"),
- "add_version_to_infotext": OptionInfo(True, "Add program version to generation information"),
+options_templates.update(options_section(('infotext', "Infotext", "ui"), {
+ "infotext_explanation": OptionHTML("""
+Infotext is what this software calls the text that contains generation parameters and can be used to generate the same picture again.
+It is displayed in UI below the image. To use infotext, paste it into the prompt and click the ↙️ paste button.
+"""),
+ "enable_pnginfo": OptionInfo(True, "Write infotext to metadata of the generated image"),
+ "save_txt": OptionInfo(False, "Create a text file with infotext next to every generated image"),
+
+ "add_model_name_to_info": OptionInfo(True, "Add model name to infotext"),
+ "add_model_hash_to_info": OptionInfo(True, "Add model hash to infotext"),
+ "add_vae_name_to_info": OptionInfo(True, "Add VAE name to infotext"),
+ "add_vae_hash_to_info": OptionInfo(True, "Add VAE hash to infotext"),
+ "add_user_name_to_info": OptionInfo(False, "Add user name to infotext when authenticated"),
+ "add_version_to_infotext": OptionInfo(True, "Add program version to infotext"),
"disable_weights_auto_swap": OptionInfo(True, "Disregard checkpoint information from pasted infotext").info("when reading generation parameters from text into UI"),
+ "infotext_skip_pasting": OptionInfo([], "Disregard fields from pasted infotext", ui_components.DropdownMulti, lambda: {"choices": shared_items.get_infotext_names()}),
"infotext_styles": OptionInfo("Apply if any", "Infer styles from prompts of pasted infotext", gr.Radio, {"choices": ["Ignore", "Apply", "Discard", "Apply if any"]}).info("when reading generation parameters from text into UI)").html("""<ul style='margin-left: 1.5em'>
<li>Ignore: keep prompt and styles dropdown as it is.</li>
<li>Apply: remove style text from prompt, always replace styles dropdown value with found styles (even if none are found).</li>
@@ -295,7 +317,7 @@ options_templates.update(options_section(('infotext', "Infotext"), { }))
-options_templates.update(options_section(('ui', "Live previews"), {
+options_templates.update(options_section(('ui', "Live previews", "ui"), {
"show_progressbar": OptionInfo(True, "Show progressbar"),
"live_previews_enable": OptionInfo(True, "Show live previews of the created image"),
"live_previews_image_format": OptionInfo("png", "Live preview file format", gr.Radio, {"choices": ["jpeg", "png", "webp"]}),
@@ -308,7 +330,7 @@ options_templates.update(options_section(('ui', "Live previews"), { "live_preview_fast_interrupt": OptionInfo(False, "Return image with chosen live preview method on interrupt").info("makes interrupts faster"),
}))
-options_templates.update(options_section(('sampler-params', "Sampler parameters"), {
+options_templates.update(options_section(('sampler-params', "Sampler parameters", "sd"), {
"hide_samplers": OptionInfo([], "Hide samplers in user interface", gr.CheckboxGroup, lambda: {"choices": [x.name for x in shared_items.list_samplers()]}).needs_reload_ui(),
"eta_ddim": OptionInfo(0.0, "Eta for DDIM", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Eta DDIM').info("noise multiplier; higher = more unpredictable results"),
"eta_ancestral": OptionInfo(1.0, "Eta for k-diffusion samplers", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Eta').info("noise multiplier; currently only applies to ancestral samplers (i.e. Euler a) and SDE samplers"),
@@ -330,7 +352,7 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters" 'uni_pc_lower_order_final': OptionInfo(True, "UniPC lower order final", infotext='UniPC lower order final'),
}))
-options_templates.update(options_section(('postprocessing', "Postprocessing"), {
+options_templates.update(options_section(('postprocessing', "Postprocessing", "postprocessing"), {
'postprocessing_enable_in_main_ui': OptionInfo([], "Enable postprocessing operations in txt2img and img2img tabs", ui_components.DropdownMulti, lambda: {"choices": [x.name for x in shared_items.postprocessing_scripts()]}),
'postprocessing_operation_order': OptionInfo([], "Postprocessing operation order", ui_components.DropdownMulti, lambda: {"choices": [x.name for x in shared_items.postprocessing_scripts()]}),
'upscaling_max_images_in_cache': OptionInfo(5, "Maximum number of images in upscaling cache", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),
diff --git a/modules/styles.py b/modules/styles.py index 0740fe1b..4d218cd7 100644 --- a/modules/styles.py +++ b/modules/styles.py @@ -1,4 +1,5 @@ import csv
+import fnmatch
import os
import os.path
import re
@@ -10,6 +11,23 @@ class PromptStyle(typing.NamedTuple): name: str
prompt: str
negative_prompt: str
+ path: str = None
+
+
+def clean_text(text: str) -> str:
+ """
+ Iterating through a list of regular expressions and replacement strings, we
+ clean up the prompt and style text to make it easier to match against each
+ other.
+ """
+ re_list = [
+ ("multiple commas", re.compile("(,+\s+)+,?"), ", "),
+ ("multiple spaces", re.compile("\s{2,}"), " "),
+ ]
+ for _, regex, replace in re_list:
+ text = regex.sub(replace, text)
+
+ return text.strip(", ")
def merge_prompts(style_prompt: str, prompt: str) -> str:
@@ -26,41 +44,64 @@ def apply_styles_to_prompt(prompt, styles): for style in styles:
prompt = merge_prompts(style, prompt)
- return prompt
+ return clean_text(prompt)
-re_spaces = re.compile(" +")
+def unwrap_style_text_from_prompt(style_text, prompt):
+ """
+ Checks the prompt to see if the style text is wrapped around it. If so,
+ returns True plus the prompt text without the style text. Otherwise, returns
+ False with the original prompt.
-
-def extract_style_text_from_prompt(style_text, prompt):
- stripped_prompt = re.sub(re_spaces, " ", prompt.strip())
- stripped_style_text = re.sub(re_spaces, " ", style_text.strip())
+ Note that the "cleaned" version of the style text is only used for matching
+ purposes here. It isn't returned; the original style text is not modified.
+ """
+ stripped_prompt = clean_text(prompt)
+ stripped_style_text = clean_text(style_text)
if "{prompt}" in stripped_style_text:
- left, right = stripped_style_text.split("{prompt}", 2)
+ # Work out whether the prompt is wrapped in the style text. If so, we
+ # return True and the "inner" prompt text that isn't part of the style.
+ try:
+ left, right = stripped_style_text.split("{prompt}", 2)
+ except ValueError as e:
+ # If the style text has multple "{prompt}"s, we can't split it into
+ # two parts. This is an error, but we can't do anything about it.
+ print(f"Unable to compare style text to prompt:\n{style_text}")
+ print(f"Error: {e}")
+ return False, prompt
if stripped_prompt.startswith(left) and stripped_prompt.endswith(right):
- prompt = stripped_prompt[len(left):len(stripped_prompt)-len(right)]
+ prompt = stripped_prompt[len(left) : len(stripped_prompt) - len(right)]
return True, prompt
else:
+ # Work out whether the given prompt ends with the style text. If so, we
+ # return True and the prompt text up to where the style text starts.
if stripped_prompt.endswith(stripped_style_text):
- prompt = stripped_prompt[:len(stripped_prompt)-len(stripped_style_text)]
-
- if prompt.endswith(', '):
+ prompt = stripped_prompt[: len(stripped_prompt) - len(stripped_style_text)]
+ if prompt.endswith(", "):
prompt = prompt[:-2]
-
return True, prompt
return False, prompt
-def extract_style_from_prompts(style: PromptStyle, prompt, negative_prompt):
+def extract_original_prompts(style: PromptStyle, prompt, negative_prompt):
+ """
+ Takes a style and compares it to the prompt and negative prompt. If the style
+ matches, returns True plus the prompt and negative prompt with the style text
+ removed. Otherwise, returns False with the original prompt and negative prompt.
+ """
if not style.prompt and not style.negative_prompt:
return False, prompt, negative_prompt
- match_positive, extracted_positive = extract_style_text_from_prompt(style.prompt, prompt)
+ match_positive, extracted_positive = unwrap_style_text_from_prompt(
+ style.prompt, prompt
+ )
if not match_positive:
return False, prompt, negative_prompt
- match_negative, extracted_negative = extract_style_text_from_prompt(style.negative_prompt, negative_prompt)
+ match_negative, extracted_negative = unwrap_style_text_from_prompt(
+ style.negative_prompt, negative_prompt
+ )
if not match_negative:
return False, prompt, negative_prompt
@@ -69,25 +110,88 @@ def extract_style_from_prompts(style: PromptStyle, prompt, negative_prompt): class StyleDatabase:
def __init__(self, path: str):
- self.no_style = PromptStyle("None", "", "")
+ self.no_style = PromptStyle("None", "", "", None)
self.styles = {}
self.path = path
+ folder, file = os.path.split(self.path)
+ self.default_file = file.split("*")[0] + ".csv"
+ if self.default_file == ".csv":
+ self.default_file = "styles.csv"
+ self.default_path = os.path.join(folder, self.default_file)
+
+ self.prompt_fields = [field for field in PromptStyle._fields if field != "path"]
+
self.reload()
def reload(self):
+ """
+ Clears the style database and reloads the styles from the CSV file(s)
+ matching the path used to initialize the database.
+ """
self.styles.clear()
- if not os.path.exists(self.path):
+ path, filename = os.path.split(self.path)
+
+ if "*" in filename:
+ fileglob = filename.split("*")[0] + "*.csv"
+ filelist = []
+ for file in os.listdir(path):
+ if fnmatch.fnmatch(file, fileglob):
+ filelist.append(file)
+ # Add a visible divider to the style list
+ half_len = round(len(file) / 2)
+ divider = f"{'-' * (20 - half_len)} {file.upper()}"
+ divider = f"{divider} {'-' * (40 - len(divider))}"
+ self.styles[divider] = PromptStyle(
+ f"{divider}", None, None, "do_not_save"
+ )
+ # Add styles from this CSV file
+ self.load_from_csv(os.path.join(path, file))
+ if len(filelist) == 0:
+ print(f"No styles found in {path} matching {fileglob}")
+ return
+ elif not os.path.exists(self.path):
+ print(f"Style database not found: {self.path}")
return
+ else:
+ self.load_from_csv(self.path)
- with open(self.path, "r", encoding="utf-8-sig", newline='') as file:
+ def load_from_csv(self, path: str):
+ with open(path, "r", encoding="utf-8-sig", newline="") as file:
reader = csv.DictReader(file, skipinitialspace=True)
for row in reader:
+ # Ignore empty rows or rows starting with a comment
+ if not row or row["name"].startswith("#"):
+ continue
# Support loading old CSV format with "name, text"-columns
prompt = row["prompt"] if "prompt" in row else row["text"]
negative_prompt = row.get("negative_prompt", "")
- self.styles[row["name"]] = PromptStyle(row["name"], prompt, negative_prompt)
+ # Add style to database
+ self.styles[row["name"]] = PromptStyle(
+ row["name"], prompt, negative_prompt, path
+ )
+
+ def get_style_paths(self) -> list():
+ """
+ Returns a list of all distinct paths, including the default path, of
+ files that styles are loaded from."""
+ # Update any styles without a path to the default path
+ for style in list(self.styles.values()):
+ if not style.path:
+ self.styles[style.name] = style._replace(path=self.default_path)
+
+ # Create a list of all distinct paths, including the default path
+ style_paths = set()
+ style_paths.add(self.default_path)
+ for _, style in self.styles.items():
+ if style.path:
+ style_paths.add(style.path)
+
+ # Remove any paths for styles that are just list dividers
+ style_paths.remove("do_not_save")
+
+ return list(style_paths)
def get_style_prompts(self, styles):
return [self.styles.get(x, self.no_style).prompt for x in styles]
@@ -96,20 +200,53 @@ class StyleDatabase: return [self.styles.get(x, self.no_style).negative_prompt for x in styles]
def apply_styles_to_prompt(self, prompt, styles):
- return apply_styles_to_prompt(prompt, [self.styles.get(x, self.no_style).prompt for x in styles])
+ return apply_styles_to_prompt(
+ prompt, [self.styles.get(x, self.no_style).prompt for x in styles]
+ )
def apply_negative_styles_to_prompt(self, prompt, styles):
- return apply_styles_to_prompt(prompt, [self.styles.get(x, self.no_style).negative_prompt for x in styles])
-
- def save_styles(self, path: str) -> None:
- # Always keep a backup file around
- if os.path.exists(path):
- shutil.copy(path, f"{path}.bak")
-
- with open(path, "w", encoding="utf-8-sig", newline='') as file:
- writer = csv.DictWriter(file, fieldnames=PromptStyle._fields)
- writer.writeheader()
- writer.writerows(style._asdict() for k, style in self.styles.items())
+ return apply_styles_to_prompt(
+ prompt, [self.styles.get(x, self.no_style).negative_prompt for x in styles]
+ )
+
+ def save_styles(self, path: str = None) -> None:
+ # The path argument is deprecated, but kept for backwards compatibility
+ _ = path
+
+ # Update any styles without a path to the default path
+ for style in list(self.styles.values()):
+ if not style.path:
+ self.styles[style.name] = style._replace(path=self.default_path)
+
+ # Create a list of all distinct paths, including the default path
+ style_paths = set()
+ style_paths.add(self.default_path)
+ for _, style in self.styles.items():
+ if style.path:
+ style_paths.add(style.path)
+
+ # Remove any paths for styles that are just list dividers
+ style_paths.remove("do_not_save")
+
+ csv_names = [os.path.split(path)[1].lower() for path in style_paths]
+
+ for style_path in style_paths:
+ # Always keep a backup file around
+ if os.path.exists(style_path):
+ shutil.copy(style_path, f"{style_path}.bak")
+
+ # Write the styles to the CSV file
+ with open(style_path, "w", encoding="utf-8-sig", newline="") as file:
+ writer = csv.DictWriter(file, fieldnames=self.prompt_fields)
+ writer.writeheader()
+ for style in (s for s in self.styles.values() if s.path == style_path):
+ # Skip style list dividers, e.g. "STYLES.CSV"
+ if style.name.lower().strip("# ") in csv_names:
+ continue
+ # Write style fields, ignoring the path field
+ writer.writerow(
+ {k: v for k, v in style._asdict().items() if k != "path"}
+ )
def extract_styles_from_prompt(self, prompt, negative_prompt):
extracted = []
@@ -120,7 +257,9 @@ class StyleDatabase: found_style = None
for style in applicable_styles:
- is_match, new_prompt, new_neg_prompt = extract_style_from_prompts(style, prompt, negative_prompt)
+ is_match, new_prompt, new_neg_prompt = extract_original_prompts(
+ style, prompt, negative_prompt
+ )
if is_match:
found_style = style
prompt = new_prompt
diff --git a/modules/sysinfo.py b/modules/sysinfo.py index 2db7551d..b669edd0 100644 --- a/modules/sysinfo.py +++ b/modules/sysinfo.py @@ -1,7 +1,6 @@ import json
import os
import sys
-import traceback
import platform
import hashlib
@@ -84,7 +83,7 @@ def get_dict(): "Checksum": checksum_token,
"Commandline": get_argv(),
"Torch env info": get_torch_sysinfo(),
- "Exceptions": get_exceptions(),
+ "Exceptions": errors.get_exceptions(),
"CPU": {
"model": platform.processor(),
"count logical": psutil.cpu_count(logical=True),
@@ -104,21 +103,6 @@ def get_dict(): return res
-def format_traceback(tb):
- return [[f"{x.filename}, line {x.lineno}, {x.name}", x.line] for x in traceback.extract_tb(tb)]
-
-
-def format_exception(e, tb):
- return {"exception": str(e), "traceback": format_traceback(tb)}
-
-
-def get_exceptions():
- try:
- return list(reversed(errors.exception_records))
- except Exception as e:
- return str(e)
-
-
def get_environment():
return {k: os.environ[k] for k in sorted(os.environ) if k in environment_whitelist}
diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index 1675e39a..e223a2e0 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -3,6 +3,8 @@ import requests import os
import numpy as np
from PIL import ImageDraw
+from modules import paths_internal
+from pkg_resources import parse_version
GREEN = "#0F0"
BLUE = "#00F"
@@ -25,7 +27,6 @@ def crop_image(im, settings): elif is_portrait(settings.crop_width, settings.crop_height):
scale_by = settings.crop_height / im.height
-
im = im.resize((int(im.width * scale_by), int(im.height * scale_by)))
im_debug = im.copy()
@@ -69,6 +70,7 @@ def crop_image(im, settings): return results
+
def focal_point(im, settings):
corner_points = image_corner_points(im, settings) if settings.corner_points_weight > 0 else []
entropy_points = image_entropy_points(im, settings) if settings.entropy_points_weight > 0 else []
@@ -78,118 +80,120 @@ def focal_point(im, settings): weight_pref_total = 0
if corner_points:
- weight_pref_total += settings.corner_points_weight
+ weight_pref_total += settings.corner_points_weight
if entropy_points:
- weight_pref_total += settings.entropy_points_weight
+ weight_pref_total += settings.entropy_points_weight
if face_points:
- weight_pref_total += settings.face_points_weight
+ weight_pref_total += settings.face_points_weight
corner_centroid = None
if corner_points:
- corner_centroid = centroid(corner_points)
- corner_centroid.weight = settings.corner_points_weight / weight_pref_total
- pois.append(corner_centroid)
+ corner_centroid = centroid(corner_points)
+ corner_centroid.weight = settings.corner_points_weight / weight_pref_total
+ pois.append(corner_centroid)
entropy_centroid = None
if entropy_points:
- entropy_centroid = centroid(entropy_points)
- entropy_centroid.weight = settings.entropy_points_weight / weight_pref_total
- pois.append(entropy_centroid)
+ entropy_centroid = centroid(entropy_points)
+ entropy_centroid.weight = settings.entropy_points_weight / weight_pref_total
+ pois.append(entropy_centroid)
face_centroid = None
if face_points:
- face_centroid = centroid(face_points)
- face_centroid.weight = settings.face_points_weight / weight_pref_total
- pois.append(face_centroid)
+ face_centroid = centroid(face_points)
+ face_centroid.weight = settings.face_points_weight / weight_pref_total
+ pois.append(face_centroid)
average_point = poi_average(pois, settings)
if settings.annotate_image:
- d = ImageDraw.Draw(im)
- max_size = min(im.width, im.height) * 0.07
- if corner_centroid is not None:
- color = BLUE
- box = corner_centroid.bounding(max_size * corner_centroid.weight)
- d.text((box[0], box[1]-15), f"Edge: {corner_centroid.weight:.02f}", fill=color)
- d.ellipse(box, outline=color)
- if len(corner_points) > 1:
- for f in corner_points:
- d.rectangle(f.bounding(4), outline=color)
- if entropy_centroid is not None:
- color = "#ff0"
- box = entropy_centroid.bounding(max_size * entropy_centroid.weight)
- d.text((box[0], box[1]-15), f"Entropy: {entropy_centroid.weight:.02f}", fill=color)
- d.ellipse(box, outline=color)
- if len(entropy_points) > 1:
- for f in entropy_points:
- d.rectangle(f.bounding(4), outline=color)
- if face_centroid is not None:
- color = RED
- box = face_centroid.bounding(max_size * face_centroid.weight)
- d.text((box[0], box[1]-15), f"Face: {face_centroid.weight:.02f}", fill=color)
- d.ellipse(box, outline=color)
- if len(face_points) > 1:
- for f in face_points:
- d.rectangle(f.bounding(4), outline=color)
-
- d.ellipse(average_point.bounding(max_size), outline=GREEN)
+ d = ImageDraw.Draw(im)
+ max_size = min(im.width, im.height) * 0.07
+ if corner_centroid is not None:
+ color = BLUE
+ box = corner_centroid.bounding(max_size * corner_centroid.weight)
+ d.text((box[0], box[1] - 15), f"Edge: {corner_centroid.weight:.02f}", fill=color)
+ d.ellipse(box, outline=color)
+ if len(corner_points) > 1:
+ for f in corner_points:
+ d.rectangle(f.bounding(4), outline=color)
+ if entropy_centroid is not None:
+ color = "#ff0"
+ box = entropy_centroid.bounding(max_size * entropy_centroid.weight)
+ d.text((box[0], box[1] - 15), f"Entropy: {entropy_centroid.weight:.02f}", fill=color)
+ d.ellipse(box, outline=color)
+ if len(entropy_points) > 1:
+ for f in entropy_points:
+ d.rectangle(f.bounding(4), outline=color)
+ if face_centroid is not None:
+ color = RED
+ box = face_centroid.bounding(max_size * face_centroid.weight)
+ d.text((box[0], box[1] - 15), f"Face: {face_centroid.weight:.02f}", fill=color)
+ d.ellipse(box, outline=color)
+ if len(face_points) > 1:
+ for f in face_points:
+ d.rectangle(f.bounding(4), outline=color)
+
+ d.ellipse(average_point.bounding(max_size), outline=GREEN)
return average_point
def image_face_points(im, settings):
if settings.dnn_model_path is not None:
- detector = cv2.FaceDetectorYN.create(
- settings.dnn_model_path,
- "",
- (im.width, im.height),
- 0.9, # score threshold
- 0.3, # nms threshold
- 5000 # keep top k before nms
- )
- faces = detector.detect(np.array(im))
- results = []
- if faces[1] is not None:
- for face in faces[1]:
- x = face[0]
- y = face[1]
- w = face[2]
- h = face[3]
- results.append(
- PointOfInterest(
- int(x + (w * 0.5)), # face focus left/right is center
- int(y + (h * 0.33)), # face focus up/down is close to the top of the head
- size = w,
- weight = 1/len(faces[1])
- )
- )
- return results
+ detector = cv2.FaceDetectorYN.create(
+ settings.dnn_model_path,
+ "",
+ (im.width, im.height),
+ 0.9, # score threshold
+ 0.3, # nms threshold
+ 5000 # keep top k before nms
+ )
+ faces = detector.detect(np.array(im))
+ results = []
+ if faces[1] is not None:
+ for face in faces[1]:
+ x = face[0]
+ y = face[1]
+ w = face[2]
+ h = face[3]
+ results.append(
+ PointOfInterest(
+ int(x + (w * 0.5)), # face focus left/right is center
+ int(y + (h * 0.33)), # face focus up/down is close to the top of the head
+ size=w,
+ weight=1 / len(faces[1])
+ )
+ )
+ return results
else:
- np_im = np.array(im)
- gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY)
-
- tries = [
- [ f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01 ],
- [ f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05 ],
- [ f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05 ]
- ]
- for t in tries:
- classifier = cv2.CascadeClassifier(t[0])
- minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side
- try:
- faces = classifier.detectMultiScale(gray, scaleFactor=1.1,
- minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE)
- except Exception:
- continue
-
- if faces:
- rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces]
- return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0]-r[2]), weight=1/len(rects)) for r in rects]
+ np_im = np.array(im)
+ gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY)
+
+ tries = [
+ [f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01],
+ [f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05],
+ [f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05]
+ ]
+ for t in tries:
+ classifier = cv2.CascadeClassifier(t[0])
+ minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side
+ try:
+ faces = classifier.detectMultiScale(gray, scaleFactor=1.1,
+ minNeighbors=7, minSize=(minsize, minsize),
+ flags=cv2.CASCADE_SCALE_IMAGE)
+ except Exception:
+ continue
+
+ if faces:
+ rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces]
+ return [PointOfInterest((r[0] + r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0] - r[2]),
+ weight=1 / len(rects)) for r in rects]
return []
@@ -198,7 +202,7 @@ def image_corner_points(im, settings): # naive attempt at preventing focal points from collecting at watermarks near the bottom
gd = ImageDraw.Draw(grayscale)
- gd.rectangle([0, im.height*.9, im.width, im.height], fill="#999")
+ gd.rectangle([0, im.height * .9, im.width, im.height], fill="#999")
np_im = np.array(grayscale)
@@ -206,7 +210,7 @@ def image_corner_points(im, settings): np_im,
maxCorners=100,
qualityLevel=0.04,
- minDistance=min(grayscale.width, grayscale.height)*0.06,
+ minDistance=min(grayscale.width, grayscale.height) * 0.06,
useHarrisDetector=False,
)
@@ -215,8 +219,8 @@ def image_corner_points(im, settings): focal_points = []
for point in points:
- x, y = point.ravel()
- focal_points.append(PointOfInterest(x, y, size=4, weight=1/len(points)))
+ x, y = point.ravel()
+ focal_points.append(PointOfInterest(x, y, size=4, weight=1 / len(points)))
return focal_points
@@ -225,13 +229,13 @@ def image_entropy_points(im, settings): landscape = im.height < im.width
portrait = im.height > im.width
if landscape:
- move_idx = [0, 2]
- move_max = im.size[0]
+ move_idx = [0, 2]
+ move_max = im.size[0]
elif portrait:
- move_idx = [1, 3]
- move_max = im.size[1]
+ move_idx = [1, 3]
+ move_max = im.size[1]
else:
- return []
+ return []
e_max = 0
crop_current = [0, 0, settings.crop_width, settings.crop_height]
@@ -241,14 +245,14 @@ def image_entropy_points(im, settings): e = image_entropy(crop)
if (e > e_max):
- e_max = e
- crop_best = list(crop_current)
+ e_max = e
+ crop_best = list(crop_current)
crop_current[move_idx[0]] += 4
crop_current[move_idx[1]] += 4
- x_mid = int(crop_best[0] + settings.crop_width/2)
- y_mid = int(crop_best[1] + settings.crop_height/2)
+ x_mid = int(crop_best[0] + settings.crop_width / 2)
+ y_mid = int(crop_best[1] + settings.crop_height / 2)
return [PointOfInterest(x_mid, y_mid, size=25, weight=1.0)]
@@ -294,22 +298,23 @@ def is_square(w, h): return w == h
-def download_and_cache_models(dirname):
- download_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true'
- model_file_name = 'face_detection_yunet.onnx'
+model_dir_opencv = os.path.join(paths_internal.models_path, 'opencv')
+if parse_version(cv2.__version__) >= parse_version('4.8'):
+ model_file_path = os.path.join(model_dir_opencv, 'face_detection_yunet_2023mar.onnx')
+ model_url = 'https://github.com/opencv/opencv_zoo/blob/b6e370b10f641879a87890d44e42173077154a05/models/face_detection_yunet/face_detection_yunet_2023mar.onnx?raw=true'
+else:
+ model_file_path = os.path.join(model_dir_opencv, 'face_detection_yunet.onnx')
+ model_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true'
- os.makedirs(dirname, exist_ok=True)
- cache_file = os.path.join(dirname, model_file_name)
- if not os.path.exists(cache_file):
- print(f"downloading face detection model from '{download_url}' to '{cache_file}'")
- response = requests.get(download_url)
- with open(cache_file, "wb") as f:
+def download_and_cache_models():
+ if not os.path.exists(model_file_path):
+ os.makedirs(model_dir_opencv, exist_ok=True)
+ print(f"downloading face detection model from '{model_url}' to '{model_file_path}'")
+ response = requests.get(model_url)
+ with open(model_file_path, "wb") as f:
f.write(response.content)
-
- if os.path.exists(cache_file):
- return cache_file
- return None
+ return model_file_path
class PointOfInterest:
diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index dbd856bd..789fa083 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -3,7 +3,7 @@ from PIL import Image, ImageOps import math
import tqdm
-from modules import paths, shared, images, deepbooru
+from modules import shared, images, deepbooru
from modules.textual_inversion import autocrop
@@ -196,7 +196,7 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre dnn_model_path = None
try:
- dnn_model_path = autocrop.download_and_cache_models(os.path.join(paths.models_path, "opencv"))
+ dnn_model_path = autocrop.download_and_cache_models()
except Exception as e:
print("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", e)
diff --git a/modules/ui.py b/modules/ui.py index b82f3c5e..08e0ad77 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -635,12 +635,6 @@ def create_ui(): scale_by.release(**on_change_args)
button_update_resize_to.click(**on_change_args)
- # the code below is meant to update the resolution label after the image in the image selection UI has changed.
- # as it is now the event keeps firing continuously for inpaint edits, which ruins the page with constant requests.
- # I assume this must be a gradio bug and for now we'll just do it for non-inpaint inputs.
- for component in [init_img, sketch]:
- component.change(fn=lambda: None, _js="updateImg2imgResizeToTextAfterChangingImage", inputs=[], outputs=[], show_progress=False)
-
tab_scale_to.select(fn=lambda: 0, inputs=[], outputs=[selected_scale_tab])
tab_scale_by.select(fn=lambda: 1, inputs=[], outputs=[selected_scale_tab])
@@ -701,6 +695,12 @@ def create_ui(): if category not in {"accordions"}:
scripts.scripts_img2img.setup_ui_for_section(category)
+ # the code below is meant to update the resolution label after the image in the image selection UI has changed.
+ # as it is now the event keeps firing continuously for inpaint edits, which ruins the page with constant requests.
+ # I assume this must be a gradio bug and for now we'll just do it for non-inpaint inputs.
+ for component in [init_img, sketch]:
+ component.change(fn=lambda: None, _js="updateImg2imgResizeToTextAfterChangingImage", inputs=[], outputs=[], show_progress=False)
+
def select_img2img_tab(tab):
return gr.update(visible=tab in [2, 3, 4]), gr.update(visible=tab == 3),
diff --git a/modules/ui_extensions.py b/modules/ui_extensions.py index 252e6ff2..dc1e34c8 100644 --- a/modules/ui_extensions.py +++ b/modules/ui_extensions.py @@ -65,7 +65,7 @@ def save_config_state(name): filename = os.path.join(config_states_dir, f"{timestamp}_{name}.json")
print(f"Saving backup of webui/extension state to {filename}.")
with open(filename, "w", encoding="utf-8") as f:
- json.dump(current_config_state, f, indent=4)
+ json.dump(current_config_state, f, indent=4, ensure_ascii=False)
config_states.list_config_states()
new_value = next(iter(config_states.all_config_states.keys()), "Current")
new_choices = ["Current"] + list(config_states.all_config_states.keys())
diff --git a/modules/ui_extra_networks.py b/modules/ui_extra_networks.py index f03e2033..f3b23cc9 100644 --- a/modules/ui_extra_networks.py +++ b/modules/ui_extra_networks.py @@ -370,6 +370,9 @@ def create_ui(interface: gr.Blocks, unrelated_tabs, tabname): for page in ui.stored_extra_pages:
with gr.Tab(page.title, elem_id=f"{tabname}_{page.id_page}", elem_classes=["extra-page"]) as tab:
+ with gr.Column(elem_id=f"{tabname}_{page.id_page}_prompts", elem_classes=["extra-page-prompts"]):
+ pass
+
elem_id = f"{tabname}_{page.id_page}_cards_html"
page_elem = gr.HTML('Loading...', elem_id=elem_id)
ui.pages.append(page_elem)
@@ -400,7 +403,7 @@ def create_ui(interface: gr.Blocks, unrelated_tabs, tabname): allow_prompt = "true" if page.allow_prompt else "false"
allow_negative_prompt = "true" if page.allow_negative_prompt else "false"
- jscode = 'extraNetworksTabSelected("' + tabname + '", "' + f"{tabname}_{page.id_page}" + '", ' + allow_prompt + ', ' + allow_negative_prompt + ');'
+ jscode = 'extraNetworksTabSelected("' + tabname + '", "' + f"{tabname}_{page.id_page}_prompts" + '", ' + allow_prompt + ', ' + allow_negative_prompt + ');'
tab.select(fn=lambda: [gr.update(visible=True) for _ in tab_controls], _js='function(){ ' + jscode + ' }', inputs=[], outputs=tab_controls, show_progress=False)
diff --git a/modules/ui_extra_networks_user_metadata.py b/modules/ui_extra_networks_user_metadata.py index bfec140c..36a807fc 100644 --- a/modules/ui_extra_networks_user_metadata.py +++ b/modules/ui_extra_networks_user_metadata.py @@ -134,7 +134,7 @@ class UserMetadataEditor: basename, ext = os.path.splitext(filename)
with open(basename + '.json', "w", encoding="utf8") as file:
- json.dump(metadata, file, indent=4)
+ json.dump(metadata, file, indent=4, ensure_ascii=False)
def save_user_metadata(self, name, desc, notes):
user_metadata = self.get_user_metadata(name)
diff --git a/modules/ui_loadsave.py b/modules/ui_loadsave.py index eb20ff25..7826786c 100644 --- a/modules/ui_loadsave.py +++ b/modules/ui_loadsave.py @@ -141,7 +141,7 @@ class UiLoadsave: def write_to_file(self, current_ui_settings):
with open(self.filename, "w", encoding="utf8") as file:
- json.dump(current_ui_settings, file, indent=4)
+ json.dump(current_ui_settings, file, indent=4, ensure_ascii=False)
def dump_defaults(self):
"""saves default values to a file unless tjhe file is present and there was an error loading default values at start"""
diff --git a/pyproject.toml b/pyproject.toml index 80541a8f..d03036e7 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -16,6 +16,7 @@ exclude = [ ignore = [ "E501", # Line too long + "E721", # Do not compare types, use `isinstance` "E731", # Do not assign a `lambda` expression, use a `def` "I001", # Import block is un-sorted or un-formatted @@ -462,6 +462,15 @@ div.toprow-compact-tools{ padding: 4px;
}
+#settings > div.tab-nav .settings-category{
+ display: block;
+ margin: 1em 0 0.25em 0;
+ font-weight: bold;
+ text-decoration: underline;
+ cursor: default;
+ user-select: none;
+}
+
#settings_result{
height: 1.4em;
margin: 0 1.2em;
@@ -637,6 +646,8 @@ table.popup-table .link{ margin: auto;
padding: 2em;
z-index: 1001;
+ max-height: 90%;
+ max-width: 90%;
}
/* fullpage image viewer */
@@ -840,8 +851,16 @@ footer { /* extra networks UI */
-.extra-page .prompt{
- margin: 0 0 0.5em 0;
+.extra-page > div.gap{
+ gap: 0;
+}
+
+.extra-page-prompts{
+ margin-bottom: 0;
+}
+
+.extra-page-prompts.extra-page-prompts-active{
+ margin-bottom: 1em;
}
.extra-network-cards{
@@ -89,7 +89,7 @@ delimiter="################################################################" printf "\n%s\n" "${delimiter}" printf "\e[1m\e[32mInstall script for stable-diffusion + Web UI\n" -printf "\e[1m\e[34mTested on Debian 11 (Bullseye)\e[0m" +printf "\e[1m\e[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.\e[0m" printf "\n%s\n" "${delimiter}" # Do not run as root @@ -223,7 +223,7 @@ fi # Try using TCMalloc on Linux prepare_tcmalloc() { if [[ "${OSTYPE}" == "linux"* ]] && [[ -z "${NO_TCMALLOC}" ]] && [[ -z "${LD_PRELOAD}" ]]; then - TCMALLOC="$(PATH=/usr/sbin:$PATH ldconfig -p | grep -Po "libtcmalloc(_minimal|)\.so\.\d" | head -n 1)" + TCMALLOC="$(PATH=/sbin:$PATH ldconfig -p | grep -Po "libtcmalloc(_minimal|)\.so\.\d" | head -n 1)" if [[ ! -z "${TCMALLOC}" ]]; then echo "Using TCMalloc: ${TCMALLOC}" export LD_PRELOAD="${TCMALLOC}" |