Merge branch 'dev' into torch210

README.md

@@ -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
 ```

extensions-builtin/Lora/network_oft.py

@@ -21,6 +21,8 @@ class NetworkModuleOFT(network.NetworkModule):
         self.lin_module = None
         self.org_module: list[torch.Module] = [self.sd_module]
 
+        self.scale = 1.0
+
         # kohya-ss
         if "oft_blocks" in weights.w.keys():
             self.is_kohya = True
@@ -53,12 +55,18 @@ class NetworkModuleOFT(network.NetworkModule):
             self.constraint = None
             self.block_size, self.num_blocks = factorization(self.out_dim, self.dim)
 
-    def calc_updown_kb(self, orig_weight, multiplier):
+    def calc_updown(self, orig_weight):
         oft_blocks = self.oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype)
-        oft_blocks = oft_blocks - oft_blocks.transpose(1, 2) # ensure skew-symmetric orthogonal matrix
+        eye = torch.eye(self.block_size, device=self.oft_blocks.device)
+
+        if self.is_kohya:
+            block_Q = oft_blocks - oft_blocks.transpose(1, 2) # ensure skew-symmetric orthogonal matrix
+            norm_Q = torch.norm(block_Q.flatten())
+            new_norm_Q = torch.clamp(norm_Q, max=self.constraint)
+            block_Q = block_Q * ((new_norm_Q + 1e-8) / (norm_Q + 1e-8))
+            oft_blocks = torch.matmul(eye + block_Q, (eye - block_Q).float().inverse())
 
         R = oft_blocks.to(orig_weight.device, dtype=orig_weight.dtype)
-        R = R * multiplier + torch.eye(self.block_size, device=orig_weight.device)
 
         # This errors out for MultiheadAttention, might need to be handled up-stream
         merged_weight = rearrange(orig_weight, '(k n) ... -> k n ...', k=self.num_blocks, n=self.block_size)
@@ -72,26 +80,3 @@ class NetworkModuleOFT(network.NetworkModule):
         updown = merged_weight.to(orig_weight.device, dtype=orig_weight.dtype) - orig_weight
         output_shape = orig_weight.shape
         return self.finalize_updown(updown, orig_weight, output_shape)
-
-    def calc_updown(self, orig_weight):
-        # if alpha is a very small number as in coft, calc_scale() will return a almost zero number so we ignore it
-        multiplier = self.multiplier()
-        return self.calc_updown_kb(orig_weight, multiplier)
-
-    # override to remove the multiplier/scale factor; it's already multiplied in get_weight
-    def finalize_updown(self, updown, orig_weight, output_shape, ex_bias=None):
-        if self.bias is not None:
-            updown = updown.reshape(self.bias.shape)
-            updown += self.bias.to(orig_weight.device, dtype=orig_weight.dtype)
-            updown = updown.reshape(output_shape)
-
-        if len(output_shape) == 4:
-            updown = updown.reshape(output_shape)
-
-        if orig_weight.size().numel() == updown.size().numel():
-            updown = updown.reshape(orig_weight.shape)
-
-        if ex_bias is not None:
-            ex_bias = ex_bias * self.multiplier()
-
-        return updown, ex_bias

extensions-builtin/Lora/networks.py

@@ -159,7 +159,8 @@ def load_network(name, network_on_disk):
     bundle_embeddings = {}
 
     for key_network, weight in sd.items():
-        key_network_without_network_parts, network_part = key_network.split(".", 1)
+        key_network_without_network_parts, _, network_part = key_network.partition(".")
+
         if key_network_without_network_parts == "bundle_emb":
             emb_name, vec_name = network_part.split(".", 1)
             emb_dict = bundle_embeddings.get(emb_name, {})

extensions-builtin/extra-options-section/scripts/extra_options_section.py

@@ -23,11 +23,12 @@ class ExtraOptionsSection(scripts.Script):
         self.setting_names = []
         self.infotext_fields = []
         extra_options = shared.opts.extra_options_img2img if is_img2img else shared.opts.extra_options_txt2img
+        elem_id_tabname = "extra_options_" + ("img2img" if is_img2img else "txt2img")
 
         mapping = {k: v for v, k in generation_parameters_copypaste.infotext_to_setting_name_mapping}
 
         with gr.Blocks() as interface:
-            with gr.Accordion("Options", open=False) if shared.opts.extra_options_accordion and extra_options else gr.Group():
+            with gr.Accordion("Options", open=False, elem_id=elem_id_tabname) if shared.opts.extra_options_accordion and extra_options else gr.Group(elem_id=elem_id_tabname):
 
                 row_count = math.ceil(len(extra_options) / shared.opts.extra_options_cols)
 
@@ -64,11 +65,14 @@ 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.Slider, {"step": 1, "minimum": 1, "maximum": 20}).info("displayed amount will depend on the actual browser window width").needs_reload_ui(),
+    "extra_options_accordion": shared.OptionInfo(False, "Place added settings into an accordion").needs_reload_ui()
 }))
 
 

extensions-builtin/hypertile/hypertile.py

@@ -6,7 +6,6 @@ Original author: @tfernd Github: https://github.com/tfernd/HyperTile
 
 from __future__ import annotations
 
-import functools
 from dataclasses import dataclass
 from typing import Callable
 
@@ -189,20 +188,27 @@ DEPTH_LAYERS_XL = {
 
 RNG_INSTANCE = random.Random()
 
-
-def random_divisor(value: int, min_value: int, /, max_options: int = 1) -> int:
+@cache
+def get_divisors(value: int, min_value: int, /, max_options: int = 1) -> list[int]:
     """
-    Returns a random divisor of value that
+    Returns divisors of value that
         x * min_value <= value
-    if max_options is 1, the behavior is deterministic
+    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)
-
-    # All big divisors of value (inclusive)
     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]
@@ -212,7 +218,7 @@ def set_hypertile_seed(seed: int) -> None:
     RNG_INSTANCE.seed(seed)
 
 
-@functools.cache
+@cache
 def largest_tile_size_available(width: int, height: int) -> int:
     """
     Calculates the largest tile size available for a given width and height

extensions-builtin/hypertile/scripts/hypertile_script.py

 import hypertile
 from modules import scripts, script_callbacks, shared
+from scripts.hypertile_xyz import add_axis_options
 
 
 class ScriptHypertile(scripts.Script):
@@ -16,8 +17,42 @@ class ScriptHypertile(scripts.Script):
 
         configure_hypertile(p.width, p.height, enable_unet=shared.opts.hypertile_enable_unet)
 
+        self.add_infotext(p)
+
     def before_hr(self, p, *args):
-        configure_hypertile(p.hr_upscale_to_x, p.hr_upscale_to_y, enable_unet=shared.opts.hypertile_enable_unet_secondpass or shared.opts.hypertile_enable_unet)
+
+        enable = shared.opts.hypertile_enable_unet_secondpass or shared.opts.hypertile_enable_unet
+
+        # exclusive hypertile seed for the second pass
+        if enable:
+            hypertile.set_hypertile_seed(p.all_seeds[0])
+
+        configure_hypertile(p.hr_upscale_to_x, p.hr_upscale_to_y, enable_unet=enable)
+
+        if enable and not shared.opts.hypertile_enable_unet:
+            p.extra_generation_params["Hypertile U-Net second pass"] = True
+
+            self.add_infotext(p, add_unet_params=True)
+
+    def add_infotext(self, p, add_unet_params=False):
+        def option(name):
+            value = getattr(shared.opts, name)
+            default_value = shared.opts.get_default(name)
+            return None if value == default_value else value
+
+        if shared.opts.hypertile_enable_unet:
+            p.extra_generation_params["Hypertile U-Net"] = True
+
+        if shared.opts.hypertile_enable_unet or add_unet_params:
+            p.extra_generation_params["Hypertile U-Net max depth"] = option('hypertile_max_depth_unet')
+            p.extra_generation_params["Hypertile U-Net max tile size"] = option('hypertile_max_tile_unet')
+            p.extra_generation_params["Hypertile U-Net swap size"] = option('hypertile_swap_size_unet')
+
+        if shared.opts.hypertile_enable_vae:
+            p.extra_generation_params["Hypertile VAE"] = True
+            p.extra_generation_params["Hypertile VAE max depth"] = option('hypertile_max_depth_vae')
+            p.extra_generation_params["Hypertile VAE max tile size"] = option('hypertile_max_tile_vae')
+            p.extra_generation_params["Hypertile VAE swap size"] = option('hypertile_swap_size_vae')
 
 
 def configure_hypertile(width, height, enable_unet=True):
@@ -53,16 +88,16 @@ def on_ui_settings():
     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": 6, "step": 1}),
+        "hypertile_enable_unet": shared.OptionInfo(False, "Enable Hypertile U-Net", infotext="Hypertile U-Net").info("enables hypertile for all modes, including hires fix second pass; noticeable change in details of the generated picture"),
+        "hypertile_enable_unet_secondpass": shared.OptionInfo(False, "Enable Hypertile U-Net for hires fix second pass", infotext="Hypertile U-Net second pass").info("enables hypertile just for hires fix second pass - regardless of whether the above setting is enabled"),
+        "hypertile_max_depth_unet": shared.OptionInfo(3, "Hypertile U-Net max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}, infotext="Hypertile U-Net max depth").info("larger = more neural network layers affected; minor effect on performance"),
+        "hypertile_max_tile_unet": shared.OptionInfo(256, "Hypertile U-Net max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, infotext="Hypertile U-Net max tile size").info("larger = worse performance"),
+        "hypertile_swap_size_unet": shared.OptionInfo(3, "Hypertile U-Net swap size", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, infotext="Hypertile U-Net swap size"),
 
-        "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": 6, "step": 1}),
+        "hypertile_enable_vae": shared.OptionInfo(False, "Enable Hypertile VAE", infotext="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}, infotext="Hypertile VAE max depth"),
+        "hypertile_max_tile_vae": shared.OptionInfo(128, "Hypertile VAE max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, infotext="Hypertile VAE max tile size"),
+        "hypertile_swap_size_vae": shared.OptionInfo(3, "Hypertile VAE swap size ", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, infotext="Hypertile VAE swap size"),
     }
 
     for name, opt in options.items():
@@ -71,3 +106,4 @@ def on_ui_settings():
 
 
 script_callbacks.on_ui_settings(on_ui_settings)
+script_callbacks.on_before_ui(add_axis_options)

extensions-builtin/hypertile/scripts/hypertile_xyz.py

+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)

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();
+    }
+});

javascript/imageviewer.js

@@ -34,7 +34,7 @@ function updateOnBackgroundChange() {
     if (modalImage && modalImage.offsetParent) {
         let currentButton = selected_gallery_button();
         let preview = gradioApp().querySelectorAll('.livePreview > img');
-        if (preview.length > 0) {
+        if (opts.js_live_preview_in_modal_lightbox && preview.length > 0) {
             // show preview image if available
             modalImage.src = preview[preview.length - 1].src;
         } else if (currentButton?.children?.length > 0 && modalImage.src != currentButton.children[0].src) {

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);
+    });
+});
+

javascript/ui.js

@@ -170,6 +170,23 @@ function submit_img2img() {
     return res;
 }
 
+function submit_extras() {
+    showSubmitButtons('extras', false);
+
+    var id = randomId();
+
+    requestProgress(id, gradioApp().getElementById('extras_gallery_container'), gradioApp().getElementById('extras_gallery'), function() {
+        showSubmitButtons('extras', true);
+    });
+
+    var res = create_submit_args(arguments);
+
+    res[0] = id;
+
+    console.log(res);
+    return res;
+}
+
 function restoreProgressTxt2img() {
     showRestoreProgressButton("txt2img", false);
     var id = localGet("txt2img_task_id");
@@ -198,9 +215,33 @@ function restoreProgressImg2img() {
 }
 
 
+/**
+ * Configure the width and height elements on `tabname` to accept
+ * pasting of resolutions in the form of "width x height".
+ */
+function setupResolutionPasting(tabname) {
+    var width = gradioApp().querySelector(`#${tabname}_width input[type=number]`);
+    var height = gradioApp().querySelector(`#${tabname}_height input[type=number]`);
+    for (const el of [width, height]) {
+        el.addEventListener('paste', function(event) {
+            var pasteData = event.clipboardData.getData('text/plain');
+            var parsed = pasteData.match(/^\s*(\d+)\D+(\d+)\s*$/);
+            if (parsed) {
+                width.value = parsed[1];
+                height.value = parsed[2];
+                updateInput(width);
+                updateInput(height);
+                event.preventDefault();
+            }
+        });
+    }
+}
+
 onUiLoaded(function() {
     showRestoreProgressButton('txt2img', localGet("txt2img_task_id"));
     showRestoreProgressButton('img2img', localGet("img2img_task_id"));
+    setupResolutionPasting('txt2img');
+    setupResolutionPasting('img2img');
 });
 
 

modules/api/api.py

@@ -22,7 +22,6 @@ from modules.api import models
 from modules.shared import opts
 from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images
 from modules.textual_inversion.textual_inversion import create_embedding, train_embedding
-from modules.textual_inversion.preprocess import preprocess
 from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork
 from PIL import PngImagePlugin, Image
 from modules.sd_models_config import find_checkpoint_config_near_filename
@@ -235,7 +234,6 @@ class Api:
         self.add_api_route("/sdapi/v1/refresh-vae", self.refresh_vae, methods=["POST"])
         self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=models.CreateResponse)
         self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=models.CreateResponse)
-        self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=models.PreprocessResponse)
         self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=models.TrainResponse)
         self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=models.TrainResponse)
         self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=models.MemoryResponse)
@@ -675,19 +673,6 @@ class Api:
         finally:
             shared.state.end()
 
-    def preprocess(self, args: dict):
-        try:
-            shared.state.begin(job="preprocess")
-            preprocess(**args) # quick operation unless blip/booru interrogation is enabled
-            shared.state.end()
-            return models.PreprocessResponse(info='preprocess complete')
-        except KeyError as e:
-            return models.PreprocessResponse(info=f"preprocess error: invalid token: {e}")
-        except Exception as e:
-            return models.PreprocessResponse(info=f"preprocess error: {e}")
-        finally:
-            shared.state.end()
-
     def train_embedding(self, args: dict):
         try:
             shared.state.begin(job="train_embedding")

modules/api/models.py

@@ -202,9 +202,6 @@ class TrainResponse(BaseModel):
 class CreateResponse(BaseModel):
     info: str = Field(title="Create info", description="Response string from create embedding or hypernetwork task.")
 
-class PreprocessResponse(BaseModel):
-    info: str = Field(title="Preprocess info", description="Response string from preprocessing task.")
-
 fields = {}
 for key, metadata in opts.data_labels.items():
     value = opts.data.get(key)

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)
 

modules/cmd_args.py

@@ -70,6 +70,7 @@ parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="pre
 parser.add_argument("--disable-opt-split-attention", action='store_true', help="prefer no cross-attention layer optimization for automatic choice of optimization")
 parser.add_argument("--disable-nan-check", action='store_true', help="do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI")
 parser.add_argument("--use-cpu", nargs='+', help="use CPU as torch device for specified modules", default=[], type=str.lower)
+parser.add_argument("--use-ipex", action="store_true", help="use Intel XPU as torch device")
 parser.add_argument("--disable-model-loading-ram-optimization", action='store_true', help="disable an optimization that reduces RAM use when loading a model")
 parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
 parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)

modules/devices.py

@@ -8,6 +8,13 @@ from modules import errors, shared
 if sys.platform == "darwin":
     from modules import mac_specific
 
+if shared.cmd_opts.use_ipex:
+    from modules import xpu_specific
+
+
+def has_xpu() -> bool:
+    return shared.cmd_opts.use_ipex and xpu_specific.has_xpu
+
 
 def has_mps() -> bool:
     if sys.platform != "darwin":
@@ -30,6 +37,9 @@ def get_optimal_device_name():
     if has_mps():
         return "mps"
 
+    if has_xpu():
+        return xpu_specific.get_xpu_device_string()
+
     return "cpu"
 
 
@@ -38,7 +48,7 @@ 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()
@@ -54,6 +64,9 @@ def torch_gc():
     if has_mps():
         mac_specific.torch_mps_gc()
 
+    if has_xpu():
+        xpu_specific.torch_xpu_gc()
+
 
 def enable_tf32():
     if torch.cuda.is_available():

modules/generation_parameters_copypaste.py

+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,
     )
+

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
 
 

modules/images.py

@@ -791,3 +791,4 @@ def flatten(img, bgcolor):
         img = background
 
     return img.convert('RGB')
+

modules/import_hook.py

@@ -3,3 +3,14 @@ import sys
 # this will break any attempt to import xformers which will prevent stability diffusion repo from trying to use it
 if "--xformers" not in "".join(sys.argv):
     sys.modules["xformers"] = None
+
+# Hack to fix a changed import in torchvision 0.17+, which otherwise breaks
+# basicsr; see https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/13985
+try:
+    import torchvision.transforms.functional_tensor  # noqa: F401
+except ImportError:
+    try:
+        import torchvision.transforms.functional as functional
+        sys.modules["torchvision.transforms.functional_tensor"] = functional
+    except ImportError:
+        pass  # shrug...

modules/launch_utils.py

@@ -6,6 +6,7 @@ import os
 import shutil
 import sys
 import importlib.util
+import importlib.metadata
 import platform
 import json
 from functools import lru_cache
@@ -119,11 +120,16 @@ def run(command, desc=None, errdesc=None, custom_env=None, live: bool = default_
 
 def is_installed(package):
     try:
-        spec = importlib.util.find_spec(package)
-    except ModuleNotFoundError:
-        return False
+        dist = importlib.metadata.distribution(package)
+    except importlib.metadata.PackageNotFoundError:
+        try:
+            spec = importlib.util.find_spec(package)
+        except ModuleNotFoundError:
+            return False
+
+        return spec is not None
 
-    return spec is not None
+    return dist is not None
 
 
 def repo_dir(name):
@@ -310,6 +316,26 @@ def requirements_met(requirements_file):
 def prepare_environment():
     torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://download.pytorch.org/whl/cu121")
     torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.1.0 torchvision==0.16.0 --extra-index-url {torch_index_url}")
+    if args.use_ipex:
+        if platform.system() == "Windows":
+            # The "Nuullll/intel-extension-for-pytorch" wheels were built from IPEX source for Intel Arc GPU: https://github.com/intel/intel-extension-for-pytorch/tree/xpu-main
+            # This is NOT an Intel official release so please use it at your own risk!!
+            # See https://github.com/Nuullll/intel-extension-for-pytorch/releases/tag/v2.0.110%2Bxpu-master%2Bdll-bundle for details.
+            #
+            # Strengths (over official IPEX 2.0.110 windows release):
+            #   - AOT build (for Arc GPU only) to eliminate JIT compilation overhead: https://github.com/intel/intel-extension-for-pytorch/issues/399
+            #   - Bundles minimal oneAPI 2023.2 dependencies into the python wheels, so users don't need to install oneAPI for the whole system.
+            #   - Provides a compatible torchvision wheel: https://github.com/intel/intel-extension-for-pytorch/issues/465
+            # Limitation:
+            #   - Only works for python 3.10
+            url_prefix = "https://github.com/Nuullll/intel-extension-for-pytorch/releases/download/v2.0.110%2Bxpu-master%2Bdll-bundle"
+            torch_command = os.environ.get('TORCH_COMMAND', f"pip install {url_prefix}/torch-2.0.0a0+gite9ebda2-cp310-cp310-win_amd64.whl {url_prefix}/torchvision-0.15.2a0+fa99a53-cp310-cp310-win_amd64.whl {url_prefix}/intel_extension_for_pytorch-2.0.110+gitc6ea20b-cp310-cp310-win_amd64.whl")
+        else:
+            # Using official IPEX release for linux since it's already an AOT build.
+            # However, users still have to install oneAPI toolkit and activate oneAPI environment manually.
+            # See https://intel.github.io/intel-extension-for-pytorch/index.html#installation for details.
+            torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://pytorch-extension.intel.com/release-whl/stable/xpu/us/")
+            torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.0.0a0 intel-extension-for-pytorch==2.0.110+gitba7f6c1 --extra-index-url {torch_index_url}")
     requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
 
     xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.22.post7')
@@ -352,6 +378,8 @@ def prepare_environment():
         run(f'"{python}" -m {torch_command}', "Installing torch and torchvision", "Couldn't install torch", live=True)
         startup_timer.record("install torch")
 
+    if args.use_ipex:
+        args.skip_torch_cuda_test = True
     if not args.skip_torch_cuda_test and not check_run_python("import torch; assert torch.cuda.is_available()"):
         raise RuntimeError(
             'Torch is not able to use GPU; '

modules/mac_specific.py

 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']:

modules/models/diffusion/ddpm_edit.py

@@ -24,10 +24,15 @@ from pytorch_lightning.utilities.distributed import rank_zero_only
 from ldm.util import log_txt_as_img, exists, default, ismap, isimage, mean_flat, count_params, instantiate_from_config
 from ldm.modules.ema import LitEma
 from ldm.modules.distributions.distributions import normal_kl, DiagonalGaussianDistribution
-from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
+from ldm.models.autoencoder import IdentityFirstStage, AutoencoderKL
 from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
 from ldm.models.diffusion.ddim import DDIMSampler
 
+try:
+    from ldm.models.autoencoder import VQModelInterface
+except Exception:
+    class VQModelInterface:
+        pass
 
 __conditioning_keys__ = {'concat': 'c_concat',
                          'crossattn': 'c_crossattn',

modules/options.py

 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
 
@@ -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:
@@ -206,6 +212,17 @@ 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):
@@ -214,15 +231,40 @@ class Options:
             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()

modules/postprocessing.py

@@ -29,11 +29,7 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
 
             image_list = shared.listfiles(input_dir)
             for filename in image_list:
-                try:
-                    image = Image.open(filename)
-                except Exception:
-                    continue
-                yield image, filename
+                yield filename, filename
         else:
             assert image, 'image not selected'
             yield image, None
@@ -45,35 +41,85 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
 
     infotext = ''
 
-    for image_data, name in get_images(extras_mode, image, image_folder, input_dir):
+    data_to_process = list(get_images(extras_mode, image, image_folder, input_dir))
+    shared.state.job_count = len(data_to_process)
+
+    for image_placeholder, name in data_to_process:
         image_data: Image.Image
 
+        shared.state.nextjob()
         shared.state.textinfo = name
+        shared.state.skipped = False
+
+        if shared.state.interrupted:
+            break
+
+        if isinstance(image_placeholder, str):
+            try:
+                image_data = Image.open(image_placeholder)
+            except Exception:
+                continue
+        else:
+            image_data = image_placeholder
+
+        shared.state.assign_current_image(image_data)
 
         parameters, existing_pnginfo = images.read_info_from_image(image_data)
         if parameters:
             existing_pnginfo["parameters"] = parameters
 
-        pp = scripts_postprocessing.PostprocessedImage(image_data.convert("RGB"))
+        initial_pp = scripts_postprocessing.PostprocessedImage(image_data.convert("RGB"))
 
-        scripts.scripts_postproc.run(pp, args)
+        scripts.scripts_postproc.run(initial_pp, args)
 
-        if opts.use_original_name_batch and name is not None:
-            basename = os.path.splitext(os.path.basename(name))[0]
-        else:
-            basename = ''
+        if shared.state.skipped:
+            continue
+
+        used_suffixes = {}
+        for pp in [initial_pp, *initial_pp.extra_images]:
+            suffix = pp.get_suffix(used_suffixes)
 
-        infotext = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in pp.info.items() if v is not None])
+            if opts.use_original_name_batch and name is not None:
+                basename = os.path.splitext(os.path.basename(name))[0]
+                forced_filename = basename + suffix
+            else:
+                basename = ''
+                forced_filename = None
 
-        if opts.enable_pnginfo:
-            pp.image.info = existing_pnginfo
-            pp.image.info["postprocessing"] = infotext
+            infotext = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in pp.info.items() if v is not None])
 
-        if save_output:
-            images.save_image(pp.image, path=outpath, basename=basename, seed=None, prompt=None, extension=opts.samples_format, info=infotext, short_filename=True, no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=None)
+            if opts.enable_pnginfo:
+                pp.image.info = existing_pnginfo
+                pp.image.info["postprocessing"] = infotext
 
-        if extras_mode != 2 or show_extras_results:
-            outputs.append(pp.image)
+            if save_output:
+                fullfn, _ = images.save_image(pp.image, path=outpath, basename=basename, extension=opts.samples_format, info=infotext, short_filename=True, no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=forced_filename, suffix=suffix)
+
+                if pp.caption:
+                    caption_filename = os.path.splitext(fullfn)[0] + ".txt"
+                    if os.path.isfile(caption_filename):
+                        with open(caption_filename, encoding="utf8") as file:
+                            existing_caption = file.read().strip()
+                    else:
+                        existing_caption = ""
+
+                    action = shared.opts.postprocessing_existing_caption_action
+                    if action == 'Prepend' and existing_caption:
+                        caption = f"{existing_caption} {pp.caption}"
+                    elif action == 'Append' and existing_caption:
+                        caption = f"{pp.caption} {existing_caption}"
+                    elif action == 'Keep' and existing_caption:
+                        caption = existing_caption
+                    else:
+                        caption = pp.caption
+
+                    caption = caption.strip()
+                    if caption:
+                        with open(caption_filename, "w", encoding="utf8") as file:
+                            file.write(caption)
+
+            if extras_mode != 2 or show_extras_results:
+                outputs.append(pp.image)
 
         image_data.close()
 
@@ -82,6 +128,10 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir,
     return outputs, ui_common.plaintext_to_html(infotext), ''
 
 
+def run_postprocessing_webui(id_task, *args, **kwargs):
+    return run_postprocessing(*args, **kwargs)
+
+
 def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_dir, show_extras_results, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, upscaling_resize_w, upscaling_resize_h, upscaling_crop, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility, upscale_first: bool, save_output: bool = True):
     """old handler for API"""
 
@@ -97,9 +147,11 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
             "upscaler_2_visibility": extras_upscaler_2_visibility,
         },
         "GFPGAN": {
+            "enable": True,
             "gfpgan_visibility": gfpgan_visibility,
         },
         "CodeFormer": {
+            "enable": True,
             "codeformer_visibility": codeformer_visibility,
             "codeformer_weight": codeformer_weight,
         },

modules/scripts.py

@@ -11,11 +11,31 @@ from modules import shared, paths, script_callbacks, extensions, script_loading,
 
 AlwaysVisible = object()
 
+class MaskBlendArgs:
+    def __init__(self, current_latent, nmask, init_latent, mask, blended_latent, denoiser=None, sigma=None):
+        self.current_latent = current_latent
+        self.nmask = nmask
+        self.init_latent = init_latent
+        self.mask = mask
+        self.blended_latent = blended_latent
+
+        self.denoiser = denoiser
+        self.is_final_blend = denoiser is None
+        self.sigma = sigma
+
+class PostSampleArgs:
+    def __init__(self, samples):
+        self.samples = samples
 
 class PostprocessImageArgs:
     def __init__(self, image):
         self.image = image
 
+class PostProcessMaskOverlayArgs:
+    def __init__(self, index, mask_for_overlay, overlay_image):
+        self.index = index
+        self.mask_for_overlay = mask_for_overlay
+        self.overlay_image = overlay_image
 
 class PostprocessBatchListArgs:
     def __init__(self, images):
@@ -206,6 +226,25 @@ class Script:
 
         pass
 
+    def on_mask_blend(self, p, mba: MaskBlendArgs, *args):
+        """
+        Called in inpainting mode when the original content is blended with the inpainted content.
+        This is called at every step in the denoising process and once at the end.
+        If is_final_blend is true, this is called for the final blending stage.
+        Otherwise, denoiser and sigma are defined and may be used to inform the procedure.
+        """
+
+        pass
+
+    def post_sample(self, p, ps: PostSampleArgs, *args):
+        """
+        Called after the samples have been generated,
+        but before they have been decoded by the VAE, if applicable.
+        Check getattr(samples, 'already_decoded', False) to test if the images are decoded.
+        """
+
+        pass
+
     def postprocess_image(self, p, pp: PostprocessImageArgs, *args):
         """
         Called for every image after it has been generated.
@@ -213,6 +252,13 @@ class Script:
 
         pass
 
+    def postprocess_maskoverlay(self, p, ppmo: PostProcessMaskOverlayArgs, *args):
+        """
+        Called for every image after it has been generated.
+        """
+
+        pass
+
     def postprocess(self, p, processed, *args):
         """
         This function is called after processing ends for AlwaysVisible scripts.
@@ -560,17 +606,25 @@ 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:
@@ -759,6 +813,22 @@ class ScriptRunner:
             except Exception:
                 errors.report(f"Error running postprocess_batch_list: {script.filename}", exc_info=True)
 
+    def post_sample(self, p, ps: PostSampleArgs):
+        for script in self.alwayson_scripts:
+            try:
+                script_args = p.script_args[script.args_from:script.args_to]
+                script.post_sample(p, ps, *script_args)
+            except Exception:
+                errors.report(f"Error running post_sample: {script.filename}", exc_info=True)
+
+    def on_mask_blend(self, p, mba: MaskBlendArgs):
+        for script in self.alwayson_scripts:
+            try:
+                script_args = p.script_args[script.args_from:script.args_to]
+                script.on_mask_blend(p, mba, *script_args)
+            except Exception:
+                errors.report(f"Error running post_sample: {script.filename}", exc_info=True)
+
     def postprocess_image(self, p, pp: PostprocessImageArgs):
         for script in self.alwayson_scripts:
             try:
@@ -767,6 +837,14 @@ class ScriptRunner:
             except Exception:
                 errors.report(f"Error running postprocess_image: {script.filename}", exc_info=True)
 
+    def postprocess_maskoverlay(self, p, ppmo: PostProcessMaskOverlayArgs):
+        for script in self.alwayson_scripts:
+            try:
+                script_args = p.script_args[script.args_from:script.args_to]
+                script.postprocess_maskoverlay(p, ppmo, *script_args)
+            except Exception:
+                errors.report(f"Error running postprocess_image: {script.filename}", exc_info=True)
+
     def before_component(self, component, **kwargs):
         for callback, script in self.on_before_component_elem_id.get(kwargs.get("elem_id"), []):
             try:

modules/scripts_postprocessing.py

+import dataclasses
 import os
 import gradio as gr
 
 from modules import errors, shared
 
 
+@dataclasses.dataclass
+class PostprocessedImageSharedInfo:
+    target_width: int = None
+    target_height: int = None
+
+
 class PostprocessedImage:
     def __init__(self, image):
         self.image = image
         self.info = {}
+        self.shared = PostprocessedImageSharedInfo()
+        self.extra_images = []
+        self.nametags = []
+        self.disable_processing = False
+        self.caption = None
+
+    def get_suffix(self, used_suffixes=None):
+        used_suffixes = {} if used_suffixes is None else used_suffixes
+        suffix = "-".join(self.nametags)
+        if suffix:
+            suffix = "-" + suffix
+
+        if suffix not in used_suffixes:
+            used_suffixes[suffix] = 1
+            return suffix
+
+        for i in range(1, 100):
+            proposed_suffix = suffix + "-" + str(i)
+
+            if proposed_suffix not in used_suffixes:
+                used_suffixes[proposed_suffix] = 1
+                return proposed_suffix
+
+        return suffix
+
+    def create_copy(self, new_image, *, nametags=None, disable_processing=False):
+        pp = PostprocessedImage(new_image)
+        pp.shared = self.shared
+        pp.nametags = self.nametags.copy()
+        pp.info = self.info.copy()
+        pp.disable_processing = disable_processing
+
+        if nametags is not None:
+            pp.nametags += nametags
+
+        return pp
 
 
 class ScriptPostprocessing:
@@ -42,10 +85,17 @@ class ScriptPostprocessing:
 
         pass
 
-    def image_changed(self):
-        pass
+    def process_firstpass(self, pp: PostprocessedImage, **args):
+        """
+        Called for all scripts before calling process(). Scripts can examine the image here and set fields
+        of the pp object to communicate things to other scripts.
+        args contains a dictionary with all values returned by components from ui()
+        """
 
+        pass
 
+    def image_changed(self):
+        pass
 
 
 def wrap_call(func, filename, funcname, *args, default=None, **kwargs):
@@ -118,16 +168,42 @@ class ScriptPostprocessingRunner:
         return inputs
 
     def run(self, pp: PostprocessedImage, args):
-        for script in self.scripts_in_preferred_order():
-            shared.state.job = script.name
+        scripts = []
 
+        for script in self.scripts_in_preferred_order():
             script_args = args[script.args_from:script.args_to]
 
             process_args = {}
             for (name, _component), value in zip(script.controls.items(), script_args):
                 process_args[name] = value
 
-            script.process(pp, **process_args)
+            scripts.append((script, process_args))
+
+        for script, process_args in scripts:
+            script.process_firstpass(pp, **process_args)
+
+        all_images = [pp]
+
+        for script, process_args in scripts:
+            if shared.state.skipped:
+                break
+
+            shared.state.job = script.name
+
+            for single_image in all_images.copy():
+
+                if not single_image.disable_processing:
+                    script.process(single_image, **process_args)
+
+                for extra_image in single_image.extra_images:
+                    if not isinstance(extra_image, PostprocessedImage):
+                        extra_image = single_image.create_copy(extra_image)
+
+                    all_images.append(extra_image)
+
+                single_image.extra_images.clear()
+
+        pp.extra_images = all_images[1:]
 
     def create_args_for_run(self, scripts_args):
         if not self.ui_created:

modules/sd_disable_initialization.py

@@ -215,7 +215,7 @@ class LoadStateDictOnMeta(ReplaceHelper):
             would be on the meta device.
             """
 
-            if state_dict == sd:
+            if state_dict is sd:
                 state_dict = {k: v.to(device="meta", dtype=v.dtype) for k, v in state_dict.items()}
 
             original(module, state_dict, strict=strict)

modules/sd_hijack.py

@@ -38,8 +38,12 @@ 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)
+ldm_patched_forward = sd_unet.create_unet_forward(ldm.modules.diffusionmodules.openaimodel.UNetModel.forward)
+ldm_original_forward = patches.patch(__file__, ldm.modules.diffusionmodules.openaimodel.UNetModel, "forward", ldm_patched_forward)
+
+sgm_patched_forward = sd_unet.create_unet_forward(sgm.modules.diffusionmodules.openaimodel.UNetModel.forward)
+sgm_original_forward = patches.patch(__file__, sgm.modules.diffusionmodules.openaimodel.UNetModel, "forward", sgm_patched_forward)
+
 
 def list_optimizers():
     new_optimizers = script_callbacks.list_optimizers_callback()
@@ -303,8 +307,6 @@ class StableDiffusionModelHijack:
         self.layers = None
         self.clip = None
 
-        sd_unet.original_forward = None
-
 
     def apply_circular(self, enable):
         if self.circular_enabled == enable:

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

modules/sd_samplers_cfg_denoiser.py

@@ -56,6 +56,9 @@ class CFGDenoiser(torch.nn.Module):
         self.sampler = sampler
         self.model_wrap = None
         self.p = None
+
+        # NOTE: masking before denoising can cause the original latents to be oversmoothed
+        # as the original latents do not have noise
         self.mask_before_denoising = False
 
     @property
@@ -105,8 +108,21 @@ class CFGDenoiser(torch.nn.Module):
 
         assert not is_edit_model or all(len(conds) == 1 for conds in conds_list), "AND is not supported for InstructPix2Pix checkpoint (unless using Image CFG scale = 1.0)"
 
+        # If we use masks, blending between the denoised and original latent images occurs here.
+        def apply_blend(current_latent):
+            blended_latent = current_latent * self.nmask + self.init_latent * self.mask
+
+            if self.p.scripts is not None:
+                from modules import scripts
+                mba = scripts.MaskBlendArgs(current_latent, self.nmask, self.init_latent, self.mask, blended_latent, denoiser=self, sigma=sigma)
+                self.p.scripts.on_mask_blend(self.p, mba)
+                blended_latent = mba.blended_latent
+
+            return blended_latent
+
+        # Blend in the original latents (before)
         if self.mask_before_denoising and self.mask is not None:
-            x = self.init_latent * self.mask + self.nmask * x
+            x = apply_blend(x)
 
         batch_size = len(conds_list)
         repeats = [len(conds_list[i]) for i in range(batch_size)]
@@ -207,8 +223,9 @@ class CFGDenoiser(torch.nn.Module):
         else:
             denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale)
 
+        # Blend in the original latents (after)
         if not self.mask_before_denoising and self.mask is not None:
-            denoised = self.init_latent * self.mask + self.nmask * denoised
+            denoised = apply_blend(denoised)
 
         self.sampler.last_latent = self.get_pred_x0(torch.cat([x_in[i:i + 1] for i in denoised_image_indexes]), torch.cat([x_out[i:i + 1] for i in denoised_image_indexes]), sigma)
 

modules/sd_samplers_timesteps_impl.py

@@ -11,7 +11,7 @@ from modules.models.diffusion.uni_pc import uni_pc
 def ddim(model, x, timesteps, extra_args=None, callback=None, disable=None, eta=0.0):
     alphas_cumprod = model.inner_model.inner_model.alphas_cumprod
     alphas = alphas_cumprod[timesteps]
-    alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(torch.float64 if x.device.type != 'mps' else torch.float32)
+    alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(torch.float64 if x.device.type != 'mps' and x.device.type != 'xpu' else torch.float32)
     sqrt_one_minus_alphas = torch.sqrt(1 - alphas)
     sigmas = eta * np.sqrt((1 - alphas_prev.cpu().numpy()) / (1 - alphas.cpu()) * (1 - alphas.cpu() / alphas_prev.cpu().numpy()))
 
@@ -43,7 +43,7 @@ def ddim(model, x, timesteps, extra_args=None, callback=None, disable=None, eta=
 def plms(model, x, timesteps, extra_args=None, callback=None, disable=None):
     alphas_cumprod = model.inner_model.inner_model.alphas_cumprod
     alphas = alphas_cumprod[timesteps]
-    alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(torch.float64 if x.device.type != 'mps' else torch.float32)
+    alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(torch.float64 if x.device.type != 'mps' and x.device.type != 'xpu' else torch.float32)
     sqrt_one_minus_alphas = torch.sqrt(1 - alphas)
 
     extra_args = {} if extra_args is None else extra_args

modules/sd_unet.py

@@ -5,8 +5,7 @@ from modules import script_callbacks, shared, devices
 unet_options = []
 current_unet_option = None
 current_unet = None
-original_forward = None
-
+original_forward = None  # not used, only left temporarily for compatibility
 
 def list_unets():
     new_unets = script_callbacks.list_unets_callback()
@@ -84,9 +83,12 @@ class SdUnet(torch.nn.Module):
         pass
 
 
-def UNetModel_forward(self, x, timesteps=None, context=None, *args, **kwargs):
-    if current_unet is not None:
-        return current_unet.forward(x, timesteps, context, *args, **kwargs)
+def create_unet_forward(original_forward):
+    def UNetModel_forward(self, x, timesteps=None, context=None, *args, **kwargs):
+        if current_unet is not None:
+            return current_unet.forward(x, timesteps, context, *args, **kwargs)
+
+        return original_forward(self, x, timesteps, context, *args, **kwargs)
 
-    return original_forward(self, x, timesteps, context, *args, **kwargs)
+    return UNetModel_forward
 

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",

modules/textual_inversion/ui.py

@@ -3,7 +3,6 @@ import html
 import gradio as gr
 
 import modules.textual_inversion.textual_inversion
-import modules.textual_inversion.preprocess
 from modules import sd_hijack, shared
 
 
@@ -15,12 +14,6 @@ def create_embedding(name, initialization_text, nvpt, overwrite_old):
     return gr.Dropdown.update(choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys())), f"Created: {filename}", ""
 
 
-def preprocess(*args):
-    modules.textual_inversion.preprocess.preprocess(*args)
-
-    return f"Preprocessing {'interrupted' if shared.state.interrupted else 'finished'}.", ""
-
-
 def train_embedding(*args):
 
     assert not shared.cmd_opts.lowvram, 'Training models with lowvram not possible'

modules/ui.py

@@ -912,71 +912,6 @@ def create_ui():
                         with gr.Column():
                             create_hypernetwork = gr.Button(value="Create hypernetwork", variant='primary', elem_id="train_create_hypernetwork")
 
-                with gr.Tab(label="Preprocess images", id="preprocess_images"):
-                    process_src = gr.Textbox(label='Source directory', elem_id="train_process_src")
-                    process_dst = gr.Textbox(label='Destination directory', elem_id="train_process_dst")
-                    process_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="train_process_width")
-                    process_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="train_process_height")
-                    preprocess_txt_action = gr.Dropdown(label='Existing Caption txt Action', value="ignore", choices=["ignore", "copy", "prepend", "append"], elem_id="train_preprocess_txt_action")
-
-                    with gr.Row():
-                        process_keep_original_size = gr.Checkbox(label='Keep original size', elem_id="train_process_keep_original_size")
-                        process_flip = gr.Checkbox(label='Create flipped copies', elem_id="train_process_flip")
-                        process_split = gr.Checkbox(label='Split oversized images', elem_id="train_process_split")
-                        process_focal_crop = gr.Checkbox(label='Auto focal point crop', elem_id="train_process_focal_crop")
-                        process_multicrop = gr.Checkbox(label='Auto-sized crop', elem_id="train_process_multicrop")
-                        process_caption = gr.Checkbox(label='Use BLIP for caption', elem_id="train_process_caption")
-                        process_caption_deepbooru = gr.Checkbox(label='Use deepbooru for caption', visible=True, elem_id="train_process_caption_deepbooru")
-
-                    with gr.Row(visible=False) as process_split_extra_row:
-                        process_split_threshold = gr.Slider(label='Split image threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_split_threshold")
-                        process_overlap_ratio = gr.Slider(label='Split image overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05, elem_id="train_process_overlap_ratio")
-
-                    with gr.Row(visible=False) as process_focal_crop_row:
-                        process_focal_crop_face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_face_weight")
-                        process_focal_crop_entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_entropy_weight")
-                        process_focal_crop_edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_edges_weight")
-                        process_focal_crop_debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug")
-
-                    with gr.Column(visible=False) as process_multicrop_col:
-                        gr.Markdown('Each image is center-cropped with an automatically chosen width and height.')
-                        with gr.Row():
-                            process_multicrop_mindim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension lower bound", value=384, elem_id="train_process_multicrop_mindim")
-                            process_multicrop_maxdim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension upper bound", value=768, elem_id="train_process_multicrop_maxdim")
-                        with gr.Row():
-                            process_multicrop_minarea = gr.Slider(minimum=64*64, maximum=2048*2048, step=1, label="Area lower bound", value=64*64, elem_id="train_process_multicrop_minarea")
-                            process_multicrop_maxarea = gr.Slider(minimum=64*64, maximum=2048*2048, step=1, label="Area upper bound", value=640*640, elem_id="train_process_multicrop_maxarea")
-                        with gr.Row():
-                            process_multicrop_objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="train_process_multicrop_objective")
-                            process_multicrop_threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="train_process_multicrop_threshold")
-
-                    with gr.Row():
-                        with gr.Column(scale=3):
-                            gr.HTML(value="")
-
-                        with gr.Column():
-                            with gr.Row():
-                                interrupt_preprocessing = gr.Button("Interrupt", elem_id="train_interrupt_preprocessing")
-                            run_preprocess = gr.Button(value="Preprocess", variant='primary', elem_id="train_run_preprocess")
-
-                    process_split.change(
-                        fn=lambda show: gr_show(show),
-                        inputs=[process_split],
-                        outputs=[process_split_extra_row],
-                    )
-
-                    process_focal_crop.change(
-                        fn=lambda show: gr_show(show),
-                        inputs=[process_focal_crop],
-                        outputs=[process_focal_crop_row],
-                    )
-
-                    process_multicrop.change(
-                        fn=lambda show: gr_show(show),
-                        inputs=[process_multicrop],
-                        outputs=[process_multicrop_col],
-                    )
-
                 def get_textual_inversion_template_names():
                     return sorted(textual_inversion.textual_inversion_templates)
 
@@ -1077,42 +1012,6 @@ def create_ui():
             ]
         )
 
-        run_preprocess.click(
-            fn=wrap_gradio_gpu_call(textual_inversion_ui.preprocess, extra_outputs=[gr.update()]),
-            _js="start_training_textual_inversion",
-            inputs=[
-                dummy_component,
-                process_src,
-                process_dst,
-                process_width,
-                process_height,
-                preprocess_txt_action,
-                process_keep_original_size,
-                process_flip,
-                process_split,
-                process_caption,
-                process_caption_deepbooru,
-                process_split_threshold,
-                process_overlap_ratio,
-                process_focal_crop,
-                process_focal_crop_face_weight,
-                process_focal_crop_entropy_weight,
-                process_focal_crop_edges_weight,
-                process_focal_crop_debug,
-                process_multicrop,
-                process_multicrop_mindim,
-                process_multicrop_maxdim,
-                process_multicrop_minarea,
-                process_multicrop_maxarea,
-                process_multicrop_objective,
-                process_multicrop_threshold,
-            ],
-            outputs=[
-                ti_output,
-                ti_outcome,
-            ],
-        )
-
         train_embedding.click(
             fn=wrap_gradio_gpu_call(textual_inversion_ui.train_embedding, extra_outputs=[gr.update()]),
             _js="start_training_textual_inversion",
@@ -1186,12 +1085,6 @@ def create_ui():
             outputs=[],
         )
 
-        interrupt_preprocessing.click(
-            fn=lambda: shared.state.interrupt(),
-            inputs=[],
-            outputs=[],
-        )
-
     loadsave = ui_loadsave.UiLoadsave(cmd_opts.ui_config_file)
 
     settings = ui_settings.UiSettings()

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())
@@ -335,6 +335,11 @@ def normalize_git_url(url):
     return url
 
 
+def get_extension_dirname_from_url(url):
+    *parts, last_part = url.split('/')
+    return normalize_git_url(last_part)
+
+
 def install_extension_from_url(dirname, url, branch_name=None):
     check_access()
 
@@ -346,10 +351,7 @@ def install_extension_from_url(dirname, url, branch_name=None):
     assert url, 'No URL specified'
 
     if dirname is None or dirname == "":
-        *parts, last_part = url.split('/')
-        last_part = normalize_git_url(last_part)
-
-        dirname = last_part
+        dirname = get_extension_dirname_from_url(url)
 
     target_dir = os.path.join(extensions.extensions_dir, dirname)
     assert not os.path.exists(target_dir), f'Extension directory already exists: {target_dir}'
@@ -449,7 +451,8 @@ def get_date(info: dict, key):
 
 def refresh_available_extensions_from_data(hide_tags, sort_column, filter_text=""):
     extlist = available_extensions["extensions"]
-    installed_extension_urls = {normalize_git_url(extension.remote): extension.name for extension in extensions.extensions}
+    installed_extensions = {extension.name for extension in extensions.extensions}
+    installed_extension_urls = {normalize_git_url(extension.remote) for extension in extensions.extensions if extension.remote is not None}
 
     tags = available_extensions.get("tags", {})
     tags_to_hide = set(hide_tags)
@@ -482,7 +485,7 @@ def refresh_available_extensions_from_data(hide_tags, sort_column, filter_text="
         if url is None:
             continue
 
-        existing = installed_extension_urls.get(normalize_git_url(url), None)
+        existing = get_extension_dirname_from_url(url) in installed_extensions or normalize_git_url(url) in installed_extension_urls
         extension_tags = extension_tags + ["installed"] if existing else extension_tags
 
         if any(x for x in extension_tags if x in tags_to_hide):

modules/ui_extra_networks.py

@@ -151,8 +151,13 @@ class ExtraNetworksPage:
                         continue
 
                     subdir = os.path.abspath(x)[len(parentdir):].replace("\\", "/")
-                    while subdir.startswith("/"):
-                        subdir = subdir[1:]
+
+                    if shared.opts.extra_networks_dir_button_function:
+                        if not subdir.startswith("/"):
+                            subdir = "/" + subdir
+                    else:
+                        while subdir.startswith("/"):
+                            subdir = subdir[1:]
 
                     is_empty = len(os.listdir(x)) == 0
                     if not is_empty and not subdir.endswith("/"):
@@ -370,6 +375,9 @@ 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 +408,7 @@ 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)
 

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)

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"""

modules/ui_postprocessing.py

 import gradio as gr
-from modules import scripts, shared, ui_common, postprocessing, call_queue
+from modules import scripts, shared, ui_common, postprocessing, call_queue, ui_toprow
 import modules.generation_parameters_copypaste as parameters_copypaste
 
 
 def create_ui():
+    dummy_component = gr.Label(visible=False)
     tab_index = gr.State(value=0)
 
     with gr.Row(equal_height=False, variant='compact'):
@@ -20,11 +21,13 @@ def create_ui():
                     extras_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, placeholder="Leave blank to save images to the default path.", elem_id="extras_batch_output_dir")
                     show_extras_results = gr.Checkbox(label='Show result images', value=True, elem_id="extras_show_extras_results")
 
-            submit = gr.Button('Generate', elem_id="extras_generate", variant='primary')
-
             script_inputs = scripts.scripts_postproc.setup_ui()
 
         with gr.Column():
+            toprow = ui_toprow.Toprow(is_compact=True, is_img2img=False, id_part="extras")
+            toprow.create_inline_toprow_image()
+            submit = toprow.submit
+
             result_images, html_info_x, html_info, html_log = ui_common.create_output_panel("extras", shared.opts.outdir_extras_samples)
 
     tab_single.select(fn=lambda: 0, inputs=[], outputs=[tab_index])
@@ -32,8 +35,10 @@ def create_ui():
     tab_batch_dir.select(fn=lambda: 2, inputs=[], outputs=[tab_index])
 
     submit.click(
-        fn=call_queue.wrap_gradio_gpu_call(postprocessing.run_postprocessing, extra_outputs=[None, '']),
+        fn=call_queue.wrap_gradio_gpu_call(postprocessing.run_postprocessing_webui, extra_outputs=[None, '']),
+        _js="submit_extras",
         inputs=[
+            dummy_component,
             tab_index,
             extras_image,
             image_batch,
@@ -45,8 +50,9 @@ def create_ui():
         outputs=[
             result_images,
             html_info_x,
-            html_info,
-        ]
+            html_log,
+        ],
+        show_progress=False,
     )
 
     parameters_copypaste.add_paste_fields("extras", extras_image, None)

modules/ui_toprow.py

@@ -34,8 +34,10 @@ class Toprow:
 
     submit_box = None
 
-    def __init__(self, is_img2img, is_compact=False):
-        id_part = "img2img" if is_img2img else "txt2img"
+    def __init__(self, is_img2img, is_compact=False, id_part=None):
+        if id_part is None:
+            id_part = "img2img" if is_img2img else "txt2img"
+
         self.id_part = id_part
         self.is_img2img = is_img2img
         self.is_compact = is_compact
@@ -77,11 +79,11 @@ class Toprow:
     def create_prompts(self):
         with gr.Column(elem_id=f"{self.id_part}_prompt_container", elem_classes=["prompt-container-compact"] if self.is_compact else [], scale=6):
             with gr.Row(elem_id=f"{self.id_part}_prompt_row", elem_classes=["prompt-row"]):
-                self.prompt = gr.Textbox(label="Prompt", elem_id=f"{self.id_part}_prompt", show_label=False, lines=3, placeholder="Prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
+                self.prompt = gr.Textbox(label="Prompt", elem_id=f"{self.id_part}_prompt", show_label=False, lines=3, placeholder="Prompt\n(Press Ctrl+Enter to generate, Alt+Enter to skip, Esc to interrupt)", elem_classes=["prompt"])
                 self.prompt_img = gr.File(label="", elem_id=f"{self.id_part}_prompt_image", file_count="single", type="binary", visible=False)
 
             with gr.Row(elem_id=f"{self.id_part}_neg_prompt_row", elem_classes=["prompt-row"]):
-                self.negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{self.id_part}_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
+                self.negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{self.id_part}_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt\n(Press Ctrl+Enter to generate, Alt+Enter to skip, Esc to interrupt)", elem_classes=["prompt"])
 
         self.prompt_img.change(
             fn=modules.images.image_data,

modules/upscaler.py

@@ -57,6 +57,9 @@ class Upscaler:
         dest_h = int((img.height * scale) // 8 * 8)
 
         for _ in range(3):
+            if img.width >= dest_w and img.height >= dest_h:
+                break
+
             shape = (img.width, img.height)
 
             img = self.do_upscale(img, selected_model)
@@ -64,9 +67,6 @@ class Upscaler:
             if shape == (img.width, img.height):
                 break
 
-            if img.width >= dest_w and img.height >= dest_h:
-                break
-
         if img.width != dest_w or img.height != dest_h:
             img = img.resize((int(dest_w), int(dest_h)), resample=LANCZOS)
 

modules/xpu_specific.py

+from modules import shared
+from modules.sd_hijack_utils import CondFunc
+
+has_ipex = False
+try:
+    import torch
+    import intel_extension_for_pytorch as ipex # noqa: F401
+    has_ipex = True
+except Exception:
+    pass
+
+
+def check_for_xpu():
+    return has_ipex and hasattr(torch, 'xpu') and torch.xpu.is_available()
+
+
+def get_xpu_device_string():
+    if shared.cmd_opts.device_id is not None:
+        return f"xpu:{shared.cmd_opts.device_id}"
+    return "xpu"
+
+
+def torch_xpu_gc():
+    with torch.xpu.device(get_xpu_device_string()):
+        torch.xpu.empty_cache()
+
+
+has_xpu = check_for_xpu()
+
+if has_xpu:
+    # W/A for https://github.com/intel/intel-extension-for-pytorch/issues/452: torch.Generator API doesn't support XPU device
+    CondFunc('torch.Generator',
+        lambda orig_func, device=None: torch.xpu.Generator(device),
+        lambda orig_func, device=None: device is not None and device.type == "xpu")
+
+    # W/A for some OPs that could not handle different input dtypes
+    CondFunc('torch.nn.functional.layer_norm',
+        lambda orig_func, input, normalized_shape=None, weight=None, *args, **kwargs:
+        orig_func(input.to(weight.data.dtype), normalized_shape, weight, *args, **kwargs),
+        lambda orig_func, input, normalized_shape=None, weight=None, *args, **kwargs:
+        weight is not None and input.dtype != weight.data.dtype)
+    CondFunc('torch.nn.modules.GroupNorm.forward',
+        lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
+        lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
+    CondFunc('torch.nn.modules.linear.Linear.forward',
+        lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
+        lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
+    CondFunc('torch.nn.modules.conv.Conv2d.forward',
+        lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
+        lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
+    CondFunc('torch.bmm',
+        lambda orig_func, input, mat2, out=None: orig_func(input.to(mat2.dtype), mat2, out=out),
+        lambda orig_func, input, mat2, out=None: input.dtype != mat2.dtype)
+    CondFunc('torch.cat',
+        lambda orig_func, tensors, dim=0, out=None: orig_func([t.to(tensors[0].dtype) for t in tensors], dim=dim, out=out),
+        lambda orig_func, tensors, dim=0, out=None: not all(t.dtype == tensors[0].dtype for t in tensors))
+    CondFunc('torch.nn.functional.scaled_dot_product_attention',
+        lambda orig_func, query, key, value, attn_mask=None, dropout_p=0.0, is_causal=False: orig_func(query, key.to(query.dtype), value.to(query.dtype), attn_mask, dropout_p, is_causal),
+        lambda orig_func, query, key, value, attn_mask=None, dropout_p=0.0, is_causal=False: query.dtype != key.dtype or query.dtype != value.dtype)

script.js

@@ -121,16 +121,22 @@ document.addEventListener("DOMContentLoaded", function() {
 });
 
 /**
- * Add a ctrl+enter as a shortcut to start a generation
+ * Add keyboard shortcuts:
+ * Ctrl+Enter to start/restart a generation
+ * Alt/Option+Enter to skip a generation
+ * Esc to interrupt a generation
  */
 document.addEventListener('keydown', function(e) {
     const isEnter = e.key === 'Enter' || e.keyCode === 13;
-    const isModifierKey = e.metaKey || e.ctrlKey || e.altKey;
+    const isCtrlKey = e.metaKey || e.ctrlKey;
+    const isAltKey = e.altKey;
+    const isEsc = e.key === 'Escape';
 
-    const interruptButton = get_uiCurrentTabContent().querySelector('button[id$=_interrupt]');
     const generateButton = get_uiCurrentTabContent().querySelector('button[id$=_generate]');
+    const interruptButton = get_uiCurrentTabContent().querySelector('button[id$=_interrupt]');
+    const skipButton = get_uiCurrentTabContent().querySelector('button[id$=_skip]');
 
-    if (isEnter && isModifierKey) {
+    if (isCtrlKey && isEnter) {
         if (interruptButton.style.display === 'block') {
             interruptButton.click();
             const callback = (mutationList) => {
@@ -150,6 +156,21 @@ document.addEventListener('keydown', function(e) {
         }
         e.preventDefault();
     }
+
+    if (isAltKey && isEnter) {
+        skipButton.click();
+        e.preventDefault();
+    }
+
+    if (isEsc) {
+        const globalPopup = document.querySelector('.global-popup');
+        const lightboxModal = document.querySelector('#lightboxModal');
+        if (!globalPopup || globalPopup.style.display === 'none') {
+            if (document.activeElement === lightboxModal) return;
+            interruptButton.click();
+            e.preventDefault();
+        }
+    }
 });
 
 /**

scripts/postprocessing_caption.py

+from modules import scripts_postprocessing, ui_components, deepbooru, shared
+import gradio as gr
+
+
+class ScriptPostprocessingCeption(scripts_postprocessing.ScriptPostprocessing):
+    name = "Caption"
+    order = 4000
+
+    def ui(self):
+        with ui_components.InputAccordion(False, label="Caption") as enable:
+            option = gr.CheckboxGroup(value=["Deepbooru"], choices=["Deepbooru", "BLIP"], show_label=False)
+
+        return {
+            "enable": enable,
+            "option": option,
+        }
+
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, option):
+        if not enable:
+            return
+
+        captions = [pp.caption]
+
+        if "Deepbooru" in option:
+            captions.append(deepbooru.model.tag(pp.image))
+
+        if "BLIP" in option:
+            captions.append(shared.interrogator.generate_caption(pp.image))
+
+        pp.caption = ", ".join([x for x in captions if x])

scripts/postprocessing_codeformer.py

 from PIL import Image
 import numpy as np
 
-from modules import scripts_postprocessing, codeformer_model
+from modules import scripts_postprocessing, codeformer_model, ui_components
 import gradio as gr
 
-from modules.ui_components import FormRow
-
 
 class ScriptPostprocessingCodeFormer(scripts_postprocessing.ScriptPostprocessing):
     name = "CodeFormer"
     order = 3000
 
     def ui(self):
-        with FormRow():
-            codeformer_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="CodeFormer visibility", value=0, elem_id="extras_codeformer_visibility")
-            codeformer_weight = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="CodeFormer weight (0 = maximum effect, 1 = minimum effect)", value=0, elem_id="extras_codeformer_weight")
+        with ui_components.InputAccordion(False, label="CodeFormer") as enable:
+            with gr.Row():
+                codeformer_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Visibility", value=1.0, elem_id="extras_codeformer_visibility")
+                codeformer_weight = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Weight (0 = maximum effect, 1 = minimum effect)", value=0, elem_id="extras_codeformer_weight")
 
         return {
+            "enable": enable,
             "codeformer_visibility": codeformer_visibility,
             "codeformer_weight": codeformer_weight,
         }
 
-    def process(self, pp: scripts_postprocessing.PostprocessedImage, codeformer_visibility, codeformer_weight):
-        if codeformer_visibility == 0:
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, codeformer_visibility, codeformer_weight):
+        if codeformer_visibility == 0 or not enable:
             return
 
         restored_img = codeformer_model.codeformer.restore(np.array(pp.image, dtype=np.uint8), w=codeformer_weight)

scripts/postprocessing_create_flipped_copies.py

+from PIL import ImageOps, Image
+
+from modules import scripts_postprocessing, ui_components
+import gradio as gr
+
+
+class ScriptPostprocessingCreateFlippedCopies(scripts_postprocessing.ScriptPostprocessing):
+    name = "Create flipped copies"
+    order = 4000
+
+    def ui(self):
+        with ui_components.InputAccordion(False, label="Create flipped copies") as enable:
+            with gr.Row():
+                option = gr.CheckboxGroup(value=["Horizontal"], choices=["Horizontal", "Vertical", "Both"], show_label=False)
+
+        return {
+            "enable": enable,
+            "option": option,
+        }
+
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, option):
+        if not enable:
+            return
+
+        if "Horizontal" in option:
+            pp.extra_images.append(ImageOps.mirror(pp.image))
+
+        if "Vertical" in option:
+            pp.extra_images.append(pp.image.transpose(Image.Transpose.FLIP_TOP_BOTTOM))
+
+        if "Both" in option:
+            pp.extra_images.append(pp.image.transpose(Image.Transpose.FLIP_TOP_BOTTOM).transpose(Image.Transpose.FLIP_LEFT_RIGHT))

scripts/postprocessing_focal_crop.py

+
+from modules import scripts_postprocessing, ui_components, errors
+import gradio as gr
+
+from modules.textual_inversion import autocrop
+
+
+class ScriptPostprocessingFocalCrop(scripts_postprocessing.ScriptPostprocessing):
+    name = "Auto focal point crop"
+    order = 4000
+
+    def ui(self):
+        with ui_components.InputAccordion(False, label="Auto focal point crop") as enable:
+            face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_face_weight")
+            entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_entropy_weight")
+            edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_edges_weight")
+            debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug")
+
+        return {
+            "enable": enable,
+            "face_weight": face_weight,
+            "entropy_weight": entropy_weight,
+            "edges_weight": edges_weight,
+            "debug": debug,
+        }
+
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, face_weight, entropy_weight, edges_weight, debug):
+        if not enable:
+            return
+
+        if not pp.shared.target_width or not pp.shared.target_height:
+            return
+
+        dnn_model_path = None
+        try:
+            dnn_model_path = autocrop.download_and_cache_models()
+        except Exception:
+            errors.report("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", exc_info=True)
+
+        autocrop_settings = autocrop.Settings(
+            crop_width=pp.shared.target_width,
+            crop_height=pp.shared.target_height,
+            face_points_weight=face_weight,
+            entropy_points_weight=entropy_weight,
+            corner_points_weight=edges_weight,
+            annotate_image=debug,
+            dnn_model_path=dnn_model_path,
+        )
+
+        result, *others = autocrop.crop_image(pp.image, autocrop_settings)
+
+        pp.image = result
+        pp.extra_images = [pp.create_copy(x, nametags=["focal-crop-debug"], disable_processing=True) for x in others]
+

scripts/postprocessing_gfpgan.py

 from PIL import Image
 import numpy as np
 
-from modules import scripts_postprocessing, gfpgan_model
+from modules import scripts_postprocessing, gfpgan_model, ui_components
 import gradio as gr
 
-from modules.ui_components import FormRow
-
 
 class ScriptPostprocessingGfpGan(scripts_postprocessing.ScriptPostprocessing):
     name = "GFPGAN"
     order = 2000
 
     def ui(self):
-        with FormRow():
-            gfpgan_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="GFPGAN visibility", value=0, elem_id="extras_gfpgan_visibility")
+        with ui_components.InputAccordion(False, label="GFPGAN") as enable:
+            gfpgan_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Visibility", value=1.0, elem_id="extras_gfpgan_visibility")
 
         return {
+            "enable": enable,
             "gfpgan_visibility": gfpgan_visibility,
         }
 
-    def process(self, pp: scripts_postprocessing.PostprocessedImage, gfpgan_visibility):
-        if gfpgan_visibility == 0:
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, gfpgan_visibility):
+        if gfpgan_visibility == 0 or not enable:
             return
 
         restored_img = gfpgan_model.gfpgan_fix_faces(np.array(pp.image, dtype=np.uint8))

scripts/postprocessing_split_oversized.py

+import math
+
+from modules import scripts_postprocessing, ui_components
+import gradio as gr
+
+
+def split_pic(image, inverse_xy, width, height, overlap_ratio):
+    if inverse_xy:
+        from_w, from_h = image.height, image.width
+        to_w, to_h = height, width
+    else:
+        from_w, from_h = image.width, image.height
+        to_w, to_h = width, height
+    h = from_h * to_w // from_w
+    if inverse_xy:
+        image = image.resize((h, to_w))
+    else:
+        image = image.resize((to_w, h))
+
+    split_count = math.ceil((h - to_h * overlap_ratio) / (to_h * (1.0 - overlap_ratio)))
+    y_step = (h - to_h) / (split_count - 1)
+    for i in range(split_count):
+        y = int(y_step * i)
+        if inverse_xy:
+            splitted = image.crop((y, 0, y + to_h, to_w))
+        else:
+            splitted = image.crop((0, y, to_w, y + to_h))
+        yield splitted
+
+
+class ScriptPostprocessingSplitOversized(scripts_postprocessing.ScriptPostprocessing):
+    name = "Split oversized images"
+    order = 4000
+
+    def ui(self):
+        with ui_components.InputAccordion(False, label="Split oversized images") as enable:
+            with gr.Row():
+                split_threshold = gr.Slider(label='Threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_split_threshold")
+                overlap_ratio = gr.Slider(label='Overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05, elem_id="postprocess_overlap_ratio")
+
+        return {
+            "enable": enable,
+            "split_threshold": split_threshold,
+            "overlap_ratio": overlap_ratio,
+        }
+
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, split_threshold, overlap_ratio):
+        if not enable:
+            return
+
+        width = pp.shared.target_width
+        height = pp.shared.target_height
+
+        if not width or not height:
+            return
+
+        if pp.image.height > pp.image.width:
+            ratio = (pp.image.width * height) / (pp.image.height * width)
+            inverse_xy = False
+        else:
+            ratio = (pp.image.height * width) / (pp.image.width * height)
+            inverse_xy = True
+
+        if ratio >= 1.0 and ratio > split_threshold:
+            return
+
+        result, *others = split_pic(pp.image, inverse_xy, width, height, overlap_ratio)
+
+        pp.image = result
+        pp.extra_images = [pp.create_copy(x) for x in others]
+

scripts/postprocessing_upscale.py

@@ -81,6 +81,14 @@ class ScriptPostprocessingUpscale(scripts_postprocessing.ScriptPostprocessing):
 
         return image
 
+    def process_firstpass(self, pp: scripts_postprocessing.PostprocessedImage, upscale_mode=1, upscale_by=2.0, upscale_to_width=None, upscale_to_height=None, upscale_crop=False, upscaler_1_name=None, upscaler_2_name=None, upscaler_2_visibility=0.0):
+        if upscale_mode == 1:
+            pp.shared.target_width = upscale_to_width
+            pp.shared.target_height = upscale_to_height
+        else:
+            pp.shared.target_width = int(pp.image.width * upscale_by)
+            pp.shared.target_height = int(pp.image.height * upscale_by)
+
     def process(self, pp: scripts_postprocessing.PostprocessedImage, upscale_mode=1, upscale_by=2.0, upscale_to_width=None, upscale_to_height=None, upscale_crop=False, upscaler_1_name=None, upscaler_2_name=None, upscaler_2_visibility=0.0):
         if upscaler_1_name == "None":
             upscaler_1_name = None
@@ -126,6 +134,10 @@ class ScriptPostprocessingUpscaleSimple(ScriptPostprocessingUpscale):
             "upscaler_name": upscaler_name,
         }
 
+    def process_firstpass(self, pp: scripts_postprocessing.PostprocessedImage, upscale_by=2.0, upscaler_name=None):
+        pp.shared.target_width = int(pp.image.width * upscale_by)
+        pp.shared.target_height = int(pp.image.height * upscale_by)
+
     def process(self, pp: scripts_postprocessing.PostprocessedImage, upscale_by=2.0, upscaler_name=None):
         if upscaler_name is None or upscaler_name == "None":
             return

scripts/processing_autosized_crop.py

+from PIL import Image
+
+from modules import scripts_postprocessing, ui_components
+import gradio as gr
+
+
+def center_crop(image: Image, w: int, h: int):
+    iw, ih = image.size
+    if ih / h < iw / w:
+        sw = w * ih / h
+        box = (iw - sw) / 2, 0, iw - (iw - sw) / 2, ih
+    else:
+        sh = h * iw / w
+        box = 0, (ih - sh) / 2, iw, ih - (ih - sh) / 2
+    return image.resize((w, h), Image.Resampling.LANCZOS, box)
+
+
+def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, threshold):
+    iw, ih = image.size
+    err = lambda w, h: 1 - (lambda x: x if x < 1 else 1 / x)(iw / ih / (w / h))
+    wh = max(((w, h) for w in range(mindim, maxdim + 1, 64) for h in range(mindim, maxdim + 1, 64)
+              if minarea <= w * h <= maxarea and err(w, h) <= threshold),
+             key=lambda wh: (wh[0] * wh[1], -err(*wh))[::1 if objective == 'Maximize area' else -1],
+             default=None
+             )
+    return wh and center_crop(image, *wh)
+
+
+class ScriptPostprocessingAutosizedCrop(scripts_postprocessing.ScriptPostprocessing):
+    name = "Auto-sized crop"
+    order = 4000
+
+    def ui(self):
+        with ui_components.InputAccordion(False, label="Auto-sized crop") as enable:
+            gr.Markdown('Each image is center-cropped with an automatically chosen width and height.')
+            with gr.Row():
+                mindim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension lower bound", value=384, elem_id="postprocess_multicrop_mindim")
+                maxdim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension upper bound", value=768, elem_id="postprocess_multicrop_maxdim")
+            with gr.Row():
+                minarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area lower bound", value=64 * 64, elem_id="postprocess_multicrop_minarea")
+                maxarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area upper bound", value=640 * 640, elem_id="postprocess_multicrop_maxarea")
+            with gr.Row():
+                objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="postprocess_multicrop_objective")
+                threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="postprocess_multicrop_threshold")
+
+        return {
+            "enable": enable,
+            "mindim": mindim,
+            "maxdim": maxdim,
+            "minarea": minarea,
+            "maxarea": maxarea,
+            "objective": objective,
+            "threshold": threshold,
+        }
+
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, mindim, maxdim, minarea, maxarea, objective, threshold):
+        if not enable:
+            return
+
+        cropped = multicrop_pic(pp.image, mindim, maxdim, minarea, maxarea, objective, threshold)
+        if cropped is not None:
+            pp.image = cropped
+        else:
+            print(f"skipped {pp.image.width}x{pp.image.height} image (can't find suitable size within error threshold)")

style.css

@@ -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{

webui.sh

@@ -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
@@ -133,7 +133,7 @@ case "$gpu_info" in
             if [[ $(bc <<< "$pyv <= 3.10") -eq 1 ]] 
             then
                 # Navi users will still use torch 1.13 because 2.0 does not seem to work.
-                export TORCH_COMMAND="pip install torch==1.13.1+rocm5.2 torchvision==0.14.1+rocm5.2 --index-url https://download.pytorch.org/whl/rocm5.2"
+                export TORCH_COMMAND="pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/rocm5.6"
             else
                 printf "\e[1m\e[31mERROR: RX 5000 series GPUs must be using at max python 3.10, aborting...\e[0m"
                 exit 1
@@ -143,8 +143,7 @@ case "$gpu_info" in
     *"Navi 2"*) export HSA_OVERRIDE_GFX_VERSION=10.3.0
     ;;
     *"Navi 3"*) [[ -z "${TORCH_COMMAND}" ]] && \
-         export TORCH_COMMAND="pip install torch torchvision --index-url https://download.pytorch.org/whl/test/rocm5.6"
-        # Navi 3 needs at least 5.5 which is only on the torch 2.1.0 release candidates right now
+         export TORCH_COMMAND="pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/rocm5.7"
     ;;
     *"Renoir"*) export HSA_OVERRIDE_GFX_VERSION=9.0.0
         printf "\n%s\n" "${delimiter}"
@@ -223,7 +222,7 @@ fi
 # Try using TCMalloc on Linux
 prepare_tcmalloc() {
     if [[ "${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}"