Merge branch 'dev' into torch210

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

@@ -1,3 +1,4 @@
+from __future__ import annotations
 import base64
 import io
 import json
@@ -15,9 +16,6 @@ re_imagesize = re.compile(r"^(\d+)x(\d+)$")
 re_hypernet_hash = re.compile("\(([0-9a-f]+)\)$")
 type_of_gr_update = type(gr.update())
 
-paste_fields = {}
-registered_param_bindings = []
-
 
 class ParamBinding:
     def __init__(self, paste_button, tabname, source_text_component=None, source_image_component=None, source_tabname=None, override_settings_component=None, paste_field_names=None):
@@ -30,6 +28,10 @@ class ParamBinding:
         self.paste_field_names = paste_field_names or []
 
 
+paste_fields: dict[str, dict] = {}
+registered_param_bindings: list[ParamBinding] = []
+
+
 def reset():
     paste_fields.clear()
     registered_param_bindings.clear()
@@ -113,7 +115,6 @@ def register_paste_params_button(binding: ParamBinding):
 
 
 def connect_paste_params_buttons():
-    binding: ParamBinding
     for binding in registered_param_bindings:
         destination_image_component = paste_fields[binding.tabname]["init_img"]
         fields = paste_fields[binding.tabname]["fields"]
@@ -313,6 +314,9 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
     if "VAE Decoder" not in res:
         res["VAE Decoder"] = "Full"
 
+    skip = set(shared.opts.infotext_skip_pasting)
+    res = {k: v for k, v in res.items() if k not in skip}
+
     return res
 
 
@@ -443,3 +447,4 @@ def connect_paste(button, paste_fields, input_comp, override_settings_component,
         outputs=[],
         show_progress=False,
     )
+

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

@@ -1,6 +1,7 @@
 import logging
 
 import torch
+from torch import Tensor
 import platform
 from modules.sd_hijack_utils import CondFunc
 from packaging import version
@@ -51,6 +52,17 @@ def cumsum_fix(input, cumsum_func, *args, **kwargs):
     return cumsum_func(input, *args, **kwargs)
 
 
+# MPS workaround for https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046
+def interpolate_with_fp32_fallback(orig_func, *args, **kwargs) -> Tensor:
+    try:
+        return orig_func(*args, **kwargs)
+    except RuntimeError as e:
+        if "not implemented for" in str(e) and "Half" in str(e):
+            input_tensor = args[0]
+            return orig_func(input_tensor.to(torch.float32), *args[1:], **kwargs).to(input_tensor.dtype)
+        else:
+            print(f"An unexpected RuntimeError occurred: {str(e)}")
+
 if has_mps:
     if platform.mac_ver()[0].startswith("13.2."):
         # MPS workaround for https://github.com/pytorch/pytorch/issues/95188, thanks to danieldk (https://github.com/explosion/curated-transformers/pull/124)
@@ -77,6 +89,9 @@ if has_mps:
         # MPS workaround for https://github.com/pytorch/pytorch/issues/96113
         CondFunc('torch.nn.functional.layer_norm', lambda orig_func, x, normalized_shape, weight, bias, eps, **kwargs: orig_func(x.float(), normalized_shape, weight.float() if weight is not None else None, bias.float() if bias is not None else bias, eps).to(x.dtype), lambda _, input, *args, **kwargs: len(args) == 4 and input.device.type == 'mps')
 
+        # MPS workaround for https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046
+        CondFunc('torch.nn.functional.interpolate', interpolate_with_fp32_fallback, None)
+
         # MPS workaround for https://github.com/pytorch/pytorch/issues/92311
         if platform.processor() == 'i386':
             for funcName in ['torch.argmax', 'torch.Tensor.argmax']:

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

@@ -1,5 +1,6 @@
 import json
 import sys
+from dataclasses import dataclass
 
 import gradio as gr
 
@@ -8,13 +9,14 @@ from modules.shared_cmd_options import cmd_opts
 
 
 class OptionInfo:
-    def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, section=None, refresh=None, comment_before='', comment_after='', infotext=None, restrict_api=False):
+    def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, section=None, refresh=None, comment_before='', comment_after='', infotext=None, restrict_api=False, category_id=None):
         self.default = default
         self.label = label
         self.component = component
         self.component_args = component_args
         self.onchange = onchange
         self.section = section
+        self.category_id = category_id
         self.refresh = refresh
         self.do_not_save = False
 
@@ -63,7 +65,11 @@ class OptionHTML(OptionInfo):
 
 def options_section(section_identifier, options_dict):
     for v in options_dict.values():
-        v.section = section_identifier
+        if len(section_identifier) == 2:
+            v.section = section_identifier
+        elif len(section_identifier) == 3:
+            v.section = section_identifier[0:2]
+            v.category_id = section_identifier[2]
 
     return options_dict
 
@@ -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
 
-        self.data_labels = dict(sorted(settings_items, key=lambda x: section_ids[x[1].section]))
+        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)
+
+        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
 
-        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])
+        used_suffixes = {}
+        for pp in [initial_pp, *initial_pp.extra_images]:
+            suffix = pp.get_suffix(used_suffixes)
 
-        if opts.enable_pnginfo:
-            pp.image.info = existing_pnginfo
-            pp.image.info["postprocessing"] = infotext
+            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 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)
+            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 extras_mode != 2 or show_extras_results:
-            outputs.append(pp.image)
+            if opts.enable_pnginfo:
+                pp.image.info = existing_pnginfo
+                pp.image.info["postprocessing"] = infotext
+
+            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/processing.py

@@ -62,18 +62,22 @@ def apply_color_correction(correction, original_image):
     return image.convert('RGB')
 
 
-def apply_overlay(image, paste_loc, index, overlays):
-    if overlays is None or index >= len(overlays):
+def uncrop(image, dest_size, paste_loc):
+    x, y, w, h = paste_loc
+    base_image = Image.new('RGBA', dest_size)
+    image = images.resize_image(1, image, w, h)
+    base_image.paste(image, (x, y))
+    image = base_image
+
+    return image
+
+
+def apply_overlay(image, paste_loc, overlay):
+    if overlay is None:
         return image
 
-    overlay = overlays[index]
-
     if paste_loc is not None:
-        x, y, w, h = paste_loc
-        base_image = Image.new('RGBA', (overlay.width, overlay.height))
-        image = images.resize_image(1, image, w, h)
-        base_image.paste(image, (x, y))
-        image = base_image
+        image = uncrop(image, (overlay.width, overlay.height), paste_loc)
 
     image = image.convert('RGBA')
     image.alpha_composite(overlay)
@@ -81,9 +85,12 @@ def apply_overlay(image, paste_loc, index, overlays):
 
     return image
 
-def create_binary_mask(image):
+def create_binary_mask(image, round=True):
     if image.mode == 'RGBA' and image.getextrema()[-1] != (255, 255):
-        image = image.split()[-1].convert("L").point(lambda x: 255 if x > 128 else 0)
+        if round:
+            image = image.split()[-1].convert("L").point(lambda x: 255 if x > 128 else 0)
+        else:
+            image = image.split()[-1].convert("L")
     else:
         image = image.convert('L')
     return image
@@ -308,7 +315,7 @@ class StableDiffusionProcessing:
             c_adm = torch.cat((c_adm, noise_level_emb), 1)
         return c_adm
 
-    def inpainting_image_conditioning(self, source_image, latent_image, image_mask=None):
+    def inpainting_image_conditioning(self, source_image, latent_image, image_mask=None, round_image_mask=True):
         self.is_using_inpainting_conditioning = True
 
         # Handle the different mask inputs
@@ -320,8 +327,10 @@ class StableDiffusionProcessing:
                 conditioning_mask = conditioning_mask.astype(np.float32) / 255.0
                 conditioning_mask = torch.from_numpy(conditioning_mask[None, None])
 
-                # Inpainting model uses a discretized mask as input, so we round to either 1.0 or 0.0
-                conditioning_mask = torch.round(conditioning_mask)
+                if round_image_mask:
+                    # Caller is requesting a discretized mask as input, so we round to either 1.0 or 0.0
+                    conditioning_mask = torch.round(conditioning_mask)
+
         else:
             conditioning_mask = source_image.new_ones(1, 1, *source_image.shape[-2:])
 
@@ -345,7 +354,7 @@ class StableDiffusionProcessing:
 
         return image_conditioning
 
-    def img2img_image_conditioning(self, source_image, latent_image, image_mask=None):
+    def img2img_image_conditioning(self, source_image, latent_image, image_mask=None, round_image_mask=True):
         source_image = devices.cond_cast_float(source_image)
 
         # HACK: Using introspection as the Depth2Image model doesn't appear to uniquely
@@ -357,7 +366,7 @@ class StableDiffusionProcessing:
             return self.edit_image_conditioning(source_image)
 
         if self.sampler.conditioning_key in {'hybrid', 'concat'}:
-            return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
+            return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask, round_image_mask=round_image_mask)
 
         if self.sampler.conditioning_key == "crossattn-adm":
             return self.unclip_image_conditioning(source_image)
@@ -679,8 +688,8 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
         "Size": f"{p.width}x{p.height}",
         "Model hash": p.sd_model_hash if opts.add_model_hash_to_info else None,
         "Model": p.sd_model_name if opts.add_model_name_to_info else None,
-        "VAE hash": p.sd_vae_hash if opts.add_model_hash_to_info else None,
-        "VAE": p.sd_vae_name if opts.add_model_name_to_info else None,
+        "VAE hash": p.sd_vae_hash if opts.add_vae_hash_to_info else None,
+        "VAE": p.sd_vae_name if opts.add_vae_name_to_info else None,
         "Variation seed": (None if p.subseed_strength == 0 else (p.all_subseeds[0] if use_main_prompt else all_subseeds[index])),
         "Variation seed strength": (None if p.subseed_strength == 0 else p.subseed_strength),
         "Seed resize from": (None if p.seed_resize_from_w <= 0 or p.seed_resize_from_h <= 0 else f"{p.seed_resize_from_w}x{p.seed_resize_from_h}"),
@@ -867,6 +876,11 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             with devices.without_autocast() if devices.unet_needs_upcast else devices.autocast():
                 samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
 
+            if p.scripts is not None:
+                ps = scripts.PostSampleArgs(samples_ddim)
+                p.scripts.post_sample(p, ps)
+                samples_ddim = ps.samples
+
             if getattr(samples_ddim, 'already_decoded', False):
                 x_samples_ddim = samples_ddim
             else:
@@ -922,13 +936,31 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                     pp = scripts.PostprocessImageArgs(image)
                     p.scripts.postprocess_image(p, pp)
                     image = pp.image
+
+                mask_for_overlay = getattr(p, "mask_for_overlay", None)
+                overlay_image = p.overlay_images[i] if getattr(p, "overlay_images", None) is not None and i < len(p.overlay_images) else None
+
+                if p.scripts is not None:
+                    ppmo = scripts.PostProcessMaskOverlayArgs(i, mask_for_overlay, overlay_image)
+                    p.scripts.postprocess_maskoverlay(p, ppmo)
+                    mask_for_overlay, overlay_image = ppmo.mask_for_overlay, ppmo.overlay_image
+
                 if p.color_corrections is not None and i < len(p.color_corrections):
                     if save_samples and opts.save_images_before_color_correction:
-                        image_without_cc = apply_overlay(image, p.paste_to, i, p.overlay_images)
+                        image_without_cc = apply_overlay(image, p.paste_to, overlay_image)
                         images.save_image(image_without_cc, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-before-color-correction")
                     image = apply_color_correction(p.color_corrections[i], image)
 
-                image = apply_overlay(image, p.paste_to, i, p.overlay_images)
+                # If the intention is to show the output from the model
+                # that is being composited over the original image,
+                # we need to keep the original image around
+                # and use it in the composite step.
+                original_denoised_image = image.copy()
+
+                if p.paste_to is not None:
+                    original_denoised_image = uncrop(original_denoised_image, (overlay_image.width, overlay_image.height), p.paste_to)
+
+                image = apply_overlay(image, p.paste_to, overlay_image)
 
                 if save_samples:
                     images.save_image(image, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p)
@@ -938,21 +970,21 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                 if opts.enable_pnginfo:
                     image.info["parameters"] = text
                 output_images.append(image)
-                if save_samples and hasattr(p, 'mask_for_overlay') and p.mask_for_overlay and any([opts.save_mask, opts.save_mask_composite, opts.return_mask, opts.return_mask_composite]):
-                    image_mask = p.mask_for_overlay.convert('RGB')
-                    image_mask_composite = Image.composite(image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), images.resize_image(2, p.mask_for_overlay, image.width, image.height).convert('L')).convert('RGBA')
 
-                    if opts.save_mask:
-                        images.save_image(image_mask, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-mask")
+                if mask_for_overlay is not None:
+                    if opts.return_mask or opts.save_mask:
+                        image_mask = mask_for_overlay.convert('RGB')
+                        if save_samples and opts.save_mask:
+                            images.save_image(image_mask, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-mask")
+                        if opts.return_mask:
+                            output_images.append(image_mask)
 
-                    if opts.save_mask_composite:
-                        images.save_image(image_mask_composite, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-mask-composite")
-
-                    if opts.return_mask:
-                        output_images.append(image_mask)
-
-                    if opts.return_mask_composite:
-                        output_images.append(image_mask_composite)
+                    if opts.return_mask_composite or opts.save_mask_composite:
+                        image_mask_composite = Image.composite(original_denoised_image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), images.resize_image(2, mask_for_overlay, image.width, image.height).convert('L')).convert('RGBA')
+                        if save_samples and opts.save_mask_composite:
+                            images.save_image(image_mask_composite, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-mask-composite")
+                        if opts.return_mask_composite:
+                            output_images.append(image_mask_composite)
 
             del x_samples_ddim
 
@@ -1352,6 +1384,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
     mask_blur_x: int = 4
     mask_blur_y: int = 4
     mask_blur: int = None
+    mask_round: bool = True
     inpainting_fill: int = 0
     inpaint_full_res: bool = True
     inpaint_full_res_padding: int = 0
@@ -1397,7 +1430,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
         if image_mask is not None:
             # image_mask is passed in as RGBA by Gradio to support alpha masks,
             # but we still want to support binary masks.
-            image_mask = create_binary_mask(image_mask)
+            image_mask = create_binary_mask(image_mask, round=self.mask_round)
 
             if self.inpainting_mask_invert:
                 image_mask = ImageOps.invert(image_mask)
@@ -1504,7 +1537,8 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             latmask = init_mask.convert('RGB').resize((self.init_latent.shape[3], self.init_latent.shape[2]))
             latmask = np.moveaxis(np.array(latmask, dtype=np.float32), 2, 0) / 255
             latmask = latmask[0]
-            latmask = np.around(latmask)
+            if self.mask_round:
+                latmask = np.around(latmask)
             latmask = np.tile(latmask[None], (4, 1, 1))
 
             self.mask = torch.asarray(1.0 - latmask).to(shared.device).type(self.sd_model.dtype)
@@ -1516,7 +1550,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             elif self.inpainting_fill == 3:
                 self.init_latent = self.init_latent * self.mask
 
-        self.image_conditioning = self.img2img_image_conditioning(image * 2 - 1, self.init_latent, image_mask)
+        self.image_conditioning = self.img2img_image_conditioning(image * 2 - 1, self.init_latent, image_mask, self.mask_round)
 
     def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):
         x = self.rng.next()
@@ -1528,7 +1562,14 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
         samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning)
 
         if self.mask is not None:
-            samples = samples * self.nmask + self.init_latent * self.mask
+            blended_samples = samples * self.nmask + self.init_latent * self.mask
+
+            if self.scripts is not None:
+                mba = scripts.MaskBlendArgs(samples, self.nmask, self.init_latent, self.mask, blended_samples)
+                self.scripts.on_mask_blend(self, mba)
+                blended_samples = mba.blended_latent
+
+            samples = blended_samples
 
         del x
         devices.torch_gc()

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

@@ -1,13 +1,56 @@
+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):
+    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/shared_options.py

@@ -3,7 +3,7 @@ import gradio as gr
 from modules import localization, ui_components, shared_items, shared, interrogate, shared_gradio_themes
 from modules.paths_internal import models_path, script_path, data_path, sd_configs_path, sd_default_config, sd_model_file, default_sd_model_file, extensions_dir, extensions_builtin_dir  # noqa: F401
 from modules.shared_cmd_options import cmd_opts
-from modules.options import options_section, OptionInfo, OptionHTML
+from modules.options import options_section, OptionInfo, OptionHTML, categories
 
 options_templates = {}
 hide_dirs = shared.hide_dirs
@@ -21,7 +21,14 @@ restricted_opts = {
     "outdir_init_images"
 }
 
-options_templates.update(options_section(('saving-images', "Saving images/grids"), {
+categories.register_category("saving", "Saving images")
+categories.register_category("sd", "Stable Diffusion")
+categories.register_category("ui", "User Interface")
+categories.register_category("system", "System")
+categories.register_category("postprocessing", "Postprocessing")
+categories.register_category("training", "Training")
+
+options_templates.update(options_section(('saving-images', "Saving images/grids", "saving"), {
     "samples_save": OptionInfo(True, "Always save all generated images"),
     "samples_format": OptionInfo('png', 'File format for images'),
     "samples_filename_pattern": OptionInfo("", "Images filename pattern", component_args=hide_dirs).link("wiki", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Images-Filename-Name-and-Subdirectory"),
@@ -39,8 +46,6 @@ options_templates.update(options_section(('saving-images', "Saving images/grids"
     "grid_text_inactive_color": OptionInfo("#999999", "Inactive text color for image grids", ui_components.FormColorPicker, {}),
     "grid_background_color": OptionInfo("#ffffff", "Background color for image grids", ui_components.FormColorPicker, {}),
 
-    "enable_pnginfo": OptionInfo(True, "Save text information about generation parameters as chunks to png files"),
-    "save_txt": OptionInfo(False, "Create a text file next to every image with generation parameters."),
     "save_images_before_face_restoration": OptionInfo(False, "Save a copy of image before doing face restoration."),
     "save_images_before_highres_fix": OptionInfo(False, "Save a copy of image before applying highres fix."),
     "save_images_before_color_correction": OptionInfo(False, "Save a copy of image before applying color correction to img2img results"),
@@ -67,7 +72,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids"
     "notification_volume": OptionInfo(100, "Notification sound volume", gr.Slider, {"minimum": 0, "maximum": 100, "step": 1}).info("in %"),
 }))
 
-options_templates.update(options_section(('saving-paths', "Paths for saving"), {
+options_templates.update(options_section(('saving-paths', "Paths for saving", "saving"), {
     "outdir_samples": OptionInfo("", "Output directory for images; if empty, defaults to three directories below", component_args=hide_dirs),
     "outdir_txt2img_samples": OptionInfo("outputs/txt2img-images", 'Output directory for txt2img images', component_args=hide_dirs),
     "outdir_img2img_samples": OptionInfo("outputs/img2img-images", 'Output directory for img2img images', component_args=hide_dirs),
@@ -79,7 +84,7 @@ options_templates.update(options_section(('saving-paths', "Paths for saving"), {
     "outdir_init_images": OptionInfo("outputs/init-images", "Directory for saving init images when using img2img", component_args=hide_dirs),
 }))
 
-options_templates.update(options_section(('saving-to-dirs', "Saving to a directory"), {
+options_templates.update(options_section(('saving-to-dirs', "Saving to a directory", "saving"), {
     "save_to_dirs": OptionInfo(True, "Save images to a subdirectory"),
     "grid_save_to_dirs": OptionInfo(True, "Save grids to a subdirectory"),
     "use_save_to_dirs_for_ui": OptionInfo(False, "When using \"Save\" button, save images to a subdirectory"),
@@ -87,21 +92,21 @@ options_templates.update(options_section(('saving-to-dirs', "Saving to a directo
     "directories_max_prompt_words": OptionInfo(8, "Max prompt words for [prompt_words] pattern", gr.Slider, {"minimum": 1, "maximum": 20, "step": 1, **hide_dirs}),
 }))
 
-options_templates.update(options_section(('upscaling', "Upscaling"), {
+options_templates.update(options_section(('upscaling', "Upscaling", "postprocessing"), {
     "ESRGAN_tile": OptionInfo(192, "Tile size for ESRGAN upscalers.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}).info("0 = no tiling"),
     "ESRGAN_tile_overlap": OptionInfo(8, "Tile overlap for ESRGAN upscalers.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}).info("Low values = visible seam"),
     "realesrgan_enabled_models": OptionInfo(["R-ESRGAN 4x+", "R-ESRGAN 4x+ Anime6B"], "Select which Real-ESRGAN models to show in the web UI.", gr.CheckboxGroup, lambda: {"choices": shared_items.realesrgan_models_names()}),
     "upscaler_for_img2img": OptionInfo(None, "Upscaler for img2img", gr.Dropdown, lambda: {"choices": [x.name for x in shared.sd_upscalers]}),
 }))
 
-options_templates.update(options_section(('face-restoration', "Face restoration"), {
+options_templates.update(options_section(('face-restoration', "Face restoration", "postprocessing"), {
     "face_restoration": OptionInfo(False, "Restore faces", infotext='Face restoration').info("will use a third-party model on generation result to reconstruct faces"),
     "face_restoration_model": OptionInfo("CodeFormer", "Face restoration model", gr.Radio, lambda: {"choices": [x.name() for x in shared.face_restorers]}),
     "code_former_weight": OptionInfo(0.5, "CodeFormer weight", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.01}).info("0 = maximum effect; 1 = minimum effect"),
     "face_restoration_unload": OptionInfo(False, "Move face restoration model from VRAM into RAM after processing"),
 }))
 
-options_templates.update(options_section(('system', "System"), {
+options_templates.update(options_section(('system', "System", "system"), {
     "auto_launch_browser": OptionInfo("Local", "Automatically open webui in browser on startup", gr.Radio, lambda: {"choices": ["Disable", "Local", "Remote"]}),
     "enable_console_prompts": OptionInfo(shared.cmd_opts.enable_console_prompts, "Print prompts to console when generating with txt2img and img2img."),
     "show_warnings": OptionInfo(False, "Show warnings in console.").needs_reload_ui(),
@@ -116,13 +121,13 @@ options_templates.update(options_section(('system', "System"), {
     "dump_stacks_on_signal": OptionInfo(False, "Print stack traces before exiting the program with ctrl+c."),
 }))
 
-options_templates.update(options_section(('API', "API"), {
+options_templates.update(options_section(('API', "API", "system"), {
     "api_enable_requests": OptionInfo(True, "Allow http:// and https:// URLs for input images in API", restrict_api=True),
     "api_forbid_local_requests": OptionInfo(True, "Forbid URLs to local resources", restrict_api=True),
     "api_useragent": OptionInfo("", "User agent for requests", restrict_api=True),
 }))
 
-options_templates.update(options_section(('training', "Training"), {
+options_templates.update(options_section(('training', "Training", "training"), {
     "unload_models_when_training": OptionInfo(False, "Move VAE and CLIP to RAM when training if possible. Saves VRAM."),
     "pin_memory": OptionInfo(False, "Turn on pin_memory for DataLoader. Makes training slightly faster but can increase memory usage."),
     "save_optimizer_state": OptionInfo(False, "Saves Optimizer state as separate *.optim file. Training of embedding or HN can be resumed with the matching optim file."),
@@ -137,7 +142,7 @@ options_templates.update(options_section(('training', "Training"), {
     "training_tensorboard_flush_every": OptionInfo(120, "How often, in seconds, to flush the pending tensorboard events and summaries to disk."),
 }))
 
-options_templates.update(options_section(('sd', "Stable Diffusion"), {
+options_templates.update(options_section(('sd', "Stable Diffusion", "sd"), {
     "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": shared_items.list_checkpoint_tiles(shared.opts.sd_checkpoint_dropdown_use_short)}, refresh=shared_items.refresh_checkpoints, infotext='Model hash'),
     "sd_checkpoints_limit": OptionInfo(1, "Maximum number of checkpoints loaded at the same time", gr.Slider, {"minimum": 1, "maximum": 10, "step": 1}),
     "sd_checkpoints_keep_in_cpu": OptionInfo(True, "Only keep one model on device").info("will keep models other than the currently used one in RAM rather than VRAM"),
@@ -154,14 +159,14 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), {
     "hires_fix_refiner_pass": OptionInfo("second pass", "Hires fix: which pass to enable refiner for", gr.Radio, {"choices": ["first pass", "second pass", "both passes"]}, infotext="Hires refiner"),
 }))
 
-options_templates.update(options_section(('sdxl', "Stable Diffusion XL"), {
+options_templates.update(options_section(('sdxl', "Stable Diffusion XL", "sd"), {
     "sdxl_crop_top": OptionInfo(0, "crop top coordinate"),
     "sdxl_crop_left": OptionInfo(0, "crop left coordinate"),
     "sdxl_refiner_low_aesthetic_score": OptionInfo(2.5, "SDXL low aesthetic score", gr.Number).info("used for refiner model negative prompt"),
     "sdxl_refiner_high_aesthetic_score": OptionInfo(6.0, "SDXL high aesthetic score", gr.Number).info("used for refiner model prompt"),
 }))
 
-options_templates.update(options_section(('vae', "VAE"), {
+options_templates.update(options_section(('vae', "VAE", "sd"), {
     "sd_vae_explanation": OptionHTML("""
 <abbr title='Variational autoencoder'>VAE</abbr> is a neural network that transforms a standard <abbr title='red/green/blue'>RGB</abbr>
 image into latent space representation and back. Latent space representation is what stable diffusion is working on during sampling
@@ -176,7 +181,7 @@ For img2img, VAE is used to process user's input image before the sampling, and
     "sd_vae_decode_method": OptionInfo("Full", "VAE type for decode", gr.Radio, {"choices": ["Full", "TAESD"]}, infotext='VAE Decoder').info("method to decode latent to image"),
 }))
 
-options_templates.update(options_section(('img2img', "img2img"), {
+options_templates.update(options_section(('img2img', "img2img", "sd"), {
     "inpainting_mask_weight": OptionInfo(1.0, "Inpainting conditioning mask strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Conditional mask weight'),
     "initial_noise_multiplier": OptionInfo(1.0, "Noise multiplier for img2img", gr.Slider, {"minimum": 0.0, "maximum": 1.5, "step": 0.001}, infotext='Noise multiplier'),
     "img2img_extra_noise": OptionInfo(0.0, "Extra noise multiplier for img2img and hires fix", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Extra noise').info("0 = disabled (default); should be lower than denoising strength"),
@@ -192,7 +197,7 @@ options_templates.update(options_section(('img2img', "img2img"), {
     "img2img_batch_show_results_limit": OptionInfo(32, "Show the first N batch img2img results in UI", gr.Slider, {"minimum": -1, "maximum": 1000, "step": 1}).info('0: disable, -1: show all images. Too many images can cause lag'),
 }))
 
-options_templates.update(options_section(('optimizations', "Optimizations"), {
+options_templates.update(options_section(('optimizations', "Optimizations", "sd"), {
     "cross_attention_optimization": OptionInfo("Automatic", "Cross attention optimization", gr.Dropdown, lambda: {"choices": shared_items.cross_attention_optimizations()}),
     "s_min_uncond": OptionInfo(0.0, "Negative Guidance minimum sigma", gr.Slider, {"minimum": 0.0, "maximum": 15.0, "step": 0.01}).link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9177").info("skip negative prompt for some steps when the image is almost ready; 0=disable, higher=faster"),
     "token_merging_ratio": OptionInfo(0.0, "Token merging ratio", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}, infotext='Token merging ratio').link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9256").info("0=disable, higher=faster"),
@@ -203,7 +208,7 @@ options_templates.update(options_section(('optimizations', "Optimizations"), {
     "batch_cond_uncond": OptionInfo(True, "Batch cond/uncond").info("do both conditional and unconditional denoising in one batch; uses a bit more VRAM during sampling, but improves speed; previously this was controlled by --always-batch-cond-uncond comandline argument"),
 }))
 
-options_templates.update(options_section(('compatibility', "Compatibility"), {
+options_templates.update(options_section(('compatibility', "Compatibility", "sd"), {
     "use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
     "use_old_karras_scheduler_sigmas": OptionInfo(False, "Use old karras scheduler sigmas (0.1 to 10)."),
     "no_dpmpp_sde_batch_determinism": OptionInfo(False, "Do not make DPM++ SDE deterministic across different batch sizes."),
@@ -228,8 +233,9 @@ options_templates.update(options_section(('interrogate', "Interrogate"), {
     "deepbooru_filter_tags": OptionInfo("", "deepbooru: filter out those tags").info("separate by comma"),
 }))
 
-options_templates.update(options_section(('extra_networks', "Extra Networks"), {
+options_templates.update(options_section(('extra_networks', "Extra Networks", "sd"), {
     "extra_networks_show_hidden_directories": OptionInfo(True, "Show hidden directories").info("directory is hidden if its name starts with \".\"."),
+    "extra_networks_dir_button_function": OptionInfo(False, "Add a '/' to the beginning of directory buttons").info("Buttons will display the contents of the selected directory without acting as a search filter."),
     "extra_networks_hidden_models": OptionInfo("When searched", "Show cards for models in hidden directories", gr.Radio, {"choices": ["Always", "When searched", "Never"]}).info('"When searched" option will only show the item when the search string has 4 characters or more'),
     "extra_networks_default_multiplier": OptionInfo(1.0, "Default multiplier for extra networks", gr.Slider, {"minimum": 0.0, "maximum": 2.0, "step": 0.01}),
     "extra_networks_card_width": OptionInfo(0, "Card width for Extra Networks").info("in pixels"),
@@ -245,47 +251,66 @@ options_templates.update(options_section(('extra_networks', "Extra Networks"), {
     "sd_hypernetwork": OptionInfo("None", "Add hypernetwork to prompt", gr.Dropdown, lambda: {"choices": ["None", *shared.hypernetworks]}, refresh=shared_items.reload_hypernetworks),
 }))
 
-options_templates.update(options_section(('ui', "User interface"), {
-    "localization": OptionInfo("None", "Localization", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)).needs_reload_ui(),
-    "gradio_theme": OptionInfo("Default", "Gradio theme", ui_components.DropdownEditable, lambda: {"choices": ["Default"] + shared_gradio_themes.gradio_hf_hub_themes}).info("you can also manually enter any of themes from the <a href='https://huggingface.co/spaces/gradio/theme-gallery'>gallery</a>.").needs_reload_ui(),
-    "gradio_themes_cache": OptionInfo(True, "Cache gradio themes locally").info("disable to update the selected Gradio theme"),
-    "gallery_height": OptionInfo("", "Gallery height", gr.Textbox).info("an be any valid CSS value").needs_reload_ui(),
-    "return_grid": OptionInfo(True, "Show grid in results for web"),
-    "do_not_show_images": OptionInfo(False, "Do not show any images in results for web"),
-    "send_seed": OptionInfo(True, "Send seed when sending prompt or image to other interface"),
-    "send_size": OptionInfo(True, "Send size when sending prompt or image to another interface"),
-    "js_modal_lightbox": OptionInfo(True, "Enable full page image viewer"),
-    "js_modal_lightbox_initially_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),
-    "js_modal_lightbox_gamepad": OptionInfo(False, "Navigate image viewer with gamepad"),
-    "js_modal_lightbox_gamepad_repeat": OptionInfo(250, "Gamepad repeat period, in milliseconds"),
-    "show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
-    "samplers_in_dropdown": OptionInfo(True, "Use dropdown for sampler selection instead of radio group").needs_reload_ui(),
-    "dimensions_and_batch_together": OptionInfo(True, "Show Width/Height and Batch sliders in same row").needs_reload_ui(),
-    "keyedit_precision_attention": OptionInfo(0.1, "Ctrl+up/down precision when editing (attention:1.1)", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
-    "keyedit_precision_extra": OptionInfo(0.05, "Ctrl+up/down precision when editing <extra networks:0.9>", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
-    "keyedit_delimiters": OptionInfo(r".,\/!?%^*;:{}=`~() ", "Ctrl+up/down word delimiters"),
+options_templates.update(options_section(('ui_prompt_editing', "Prompt editing", "ui"), {
+    "keyedit_precision_attention": OptionInfo(0.1, "Precision for (attention:1.1) when editing the prompt with Ctrl+up/down", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
+    "keyedit_precision_extra": OptionInfo(0.05, "Precision for <extra networks:0.9> when editing the prompt with Ctrl+up/down", gr.Slider, {"minimum": 0.01, "maximum": 0.2, "step": 0.001}),
+    "keyedit_delimiters": OptionInfo(r".,\/!?%^*;:{}=`~() ", "Word delimiters when editing the prompt with Ctrl+up/down"),
     "keyedit_delimiters_whitespace": OptionInfo(["Tab", "Carriage Return", "Line Feed"], "Ctrl+up/down whitespace delimiters", gr.CheckboxGroup, lambda: {"choices": ["Tab", "Carriage Return", "Line Feed"]}),
     "keyedit_move": OptionInfo(True, "Alt+left/right moves prompt elements"),
-    "quicksettings_list": OptionInfo(["sd_model_checkpoint"], "Quicksettings list", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that appear at the top of page rather than in settings tab").needs_reload_ui(),
-    "ui_tab_order": OptionInfo([], "UI tab order", ui_components.DropdownMulti, lambda: {"choices": list(shared.tab_names)}).needs_reload_ui(),
-    "hidden_tabs": OptionInfo([], "Hidden UI tabs", ui_components.DropdownMulti, lambda: {"choices": list(shared.tab_names)}).needs_reload_ui(),
-    "ui_reorder_list": OptionInfo([], "txt2img/img2img UI item order", ui_components.DropdownMulti, lambda: {"choices": list(shared_items.ui_reorder_categories())}).info("selected items appear first").needs_reload_ui(),
+    "disable_token_counters": OptionInfo(False, "Disable prompt token counters").needs_reload_ui(),
+}))
+
+options_templates.update(options_section(('ui_gallery', "Gallery", "ui"), {
+    "return_grid": OptionInfo(True, "Show grid in gallery"),
+    "do_not_show_images": OptionInfo(False, "Do not show any images in gallery"),
+    "js_modal_lightbox": OptionInfo(True, "Full page image viewer: enable"),
+    "js_modal_lightbox_initially_zoomed": OptionInfo(True, "Full page image viewer: show images zoomed in by default"),
+    "js_modal_lightbox_gamepad": OptionInfo(False, "Full page image viewer: navigate with gamepad"),
+    "js_modal_lightbox_gamepad_repeat": OptionInfo(250, "Full page image viewer: gamepad repeat period").info("in milliseconds"),
+    "gallery_height": OptionInfo("", "Gallery height", gr.Textbox).info("can be any valid CSS value, for example 768px or 20em").needs_reload_ui(),
+}))
+
+options_templates.update(options_section(('ui_alternatives', "UI alternatives", "ui"), {
+    "compact_prompt_box": OptionInfo(False, "Compact prompt layout").info("puts prompt and negative prompt inside the Generate tab, leaving more vertical space for the image on the right").needs_reload_ui(),
+    "samplers_in_dropdown": OptionInfo(True, "Use dropdown for sampler selection instead of radio group").needs_reload_ui(),
+    "dimensions_and_batch_together": OptionInfo(True, "Show Width/Height and Batch sliders in same row").needs_reload_ui(),
     "sd_checkpoint_dropdown_use_short": OptionInfo(False, "Checkpoint dropdown: use filenames without paths").info("models in subdirectories like photo/sd15.ckpt will be listed as just sd15.ckpt"),
     "hires_fix_show_sampler": OptionInfo(False, "Hires fix: show hires checkpoint and sampler selection").needs_reload_ui(),
     "hires_fix_show_prompts": OptionInfo(False, "Hires fix: show hires prompt and negative prompt").needs_reload_ui(),
-    "disable_token_counters": OptionInfo(False, "Disable prompt token counters").needs_reload_ui(),
     "txt2img_settings_accordion": OptionInfo(False, "Settings in txt2img hidden under Accordion").needs_reload_ui(),
     "img2img_settings_accordion": OptionInfo(False, "Settings in img2img hidden under Accordion").needs_reload_ui(),
-    "compact_prompt_box": OptionInfo(False, "Compact prompt layout").info("puts prompt and negative prompt inside the Generate tab, leaving more vertical space for the image on the right").needs_reload_ui(),
+}))
+
+options_templates.update(options_section(('ui', "User interface", "ui"), {
+    "localization": OptionInfo("None", "Localization", gr.Dropdown, lambda: {"choices": ["None"] + list(localization.localizations.keys())}, refresh=lambda: localization.list_localizations(cmd_opts.localizations_dir)).needs_reload_ui(),
+    "quicksettings_list": OptionInfo(["sd_model_checkpoint"], "Quicksettings list", ui_components.DropdownMulti, lambda: {"choices": list(shared.opts.data_labels.keys())}).js("info", "settingsHintsShowQuicksettings").info("setting entries that appear at the top of page rather than in settings tab").needs_reload_ui(),
+    "ui_tab_order": OptionInfo([], "UI tab order", ui_components.DropdownMulti, lambda: {"choices": list(shared.tab_names)}).needs_reload_ui(),
+    "hidden_tabs": OptionInfo([], "Hidden UI tabs", ui_components.DropdownMulti, lambda: {"choices": list(shared.tab_names)}).needs_reload_ui(),
+    "ui_reorder_list": OptionInfo([], "UI item order for txt2img/img2img tabs", ui_components.DropdownMulti, lambda: {"choices": list(shared_items.ui_reorder_categories())}).info("selected items appear first").needs_reload_ui(),
+    "gradio_theme": OptionInfo("Default", "Gradio theme", ui_components.DropdownEditable, lambda: {"choices": ["Default"] + shared_gradio_themes.gradio_hf_hub_themes}).info("you can also manually enter any of themes from the <a href='https://huggingface.co/spaces/gradio/theme-gallery'>gallery</a>.").needs_reload_ui(),
+    "gradio_themes_cache": OptionInfo(True, "Cache gradio themes locally").info("disable to update the selected Gradio theme"),
+    "show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
+    "send_seed": OptionInfo(True, "Send seed when sending prompt or image to other interface"),
+    "send_size": OptionInfo(True, "Send size when sending prompt or image to another interface"),
 }))
 
 
-options_templates.update(options_section(('infotext', "Infotext"), {
-    "add_model_hash_to_info": OptionInfo(True, "Add model hash to generation information"),
-    "add_model_name_to_info": OptionInfo(True, "Add model name to generation information"),
-    "add_user_name_to_info": OptionInfo(False, "Add user name to generation information when authenticated"),
-    "add_version_to_infotext": OptionInfo(True, "Add program version to generation information"),
+options_templates.update(options_section(('infotext', "Infotext", "ui"), {
+    "infotext_explanation": OptionHTML("""
+Infotext is what this software calls the text that contains generation parameters and can be used to generate the same picture again.
+It is displayed in UI below the image. To use infotext, paste it into the prompt and click the ↙️ paste button.
+"""),
+    "enable_pnginfo": OptionInfo(True, "Write infotext to metadata of the generated image"),
+    "save_txt": OptionInfo(False, "Create a text file with infotext next to every generated image"),
+
+    "add_model_name_to_info": OptionInfo(True, "Add model name to infotext"),
+    "add_model_hash_to_info": OptionInfo(True, "Add model hash to infotext"),
+    "add_vae_name_to_info": OptionInfo(True, "Add VAE name to infotext"),
+    "add_vae_hash_to_info": OptionInfo(True, "Add VAE hash to infotext"),
+    "add_user_name_to_info": OptionInfo(False, "Add user name to infotext when authenticated"),
+    "add_version_to_infotext": OptionInfo(True, "Add program version to infotext"),
     "disable_weights_auto_swap": OptionInfo(True, "Disregard checkpoint information from pasted infotext").info("when reading generation parameters from text into UI"),
+    "infotext_skip_pasting": OptionInfo([], "Disregard fields from pasted infotext", ui_components.DropdownMulti, lambda: {"choices": shared_items.get_infotext_names()}),
     "infotext_styles": OptionInfo("Apply if any", "Infer styles from prompts of pasted infotext", gr.Radio, {"choices": ["Ignore", "Apply", "Discard", "Apply if any"]}).info("when reading generation parameters from text into UI)").html("""<ul style='margin-left: 1.5em'>
 <li>Ignore: keep prompt and styles dropdown as it is.</li>
 <li>Apply: remove style text from prompt, always replace styles dropdown value with found styles (even if none are found).</li>
@@ -295,7 +320,7 @@ options_templates.update(options_section(('infotext', "Infotext"), {
 
 }))
 
-options_templates.update(options_section(('ui', "Live previews"), {
+options_templates.update(options_section(('ui', "Live previews", "ui"), {
     "show_progressbar": OptionInfo(True, "Show progressbar"),
     "live_previews_enable": OptionInfo(True, "Show live previews of the created image"),
     "live_previews_image_format": OptionInfo("png", "Live preview file format", gr.Radio, {"choices": ["jpeg", "png", "webp"]}),
@@ -306,9 +331,10 @@ options_templates.update(options_section(('ui', "Live previews"), {
     "live_preview_content": OptionInfo("Prompt", "Live preview subject", gr.Radio, {"choices": ["Combined", "Prompt", "Negative prompt"]}),
     "live_preview_refresh_period": OptionInfo(1000, "Progressbar and preview update period").info("in milliseconds"),
     "live_preview_fast_interrupt": OptionInfo(False, "Return image with chosen live preview method on interrupt").info("makes interrupts faster"),
+    "js_live_preview_in_modal_lightbox": OptionInfo(False, "Show Live preview in full page image viewer"),
 }))
 
-options_templates.update(options_section(('sampler-params', "Sampler parameters"), {
+options_templates.update(options_section(('sampler-params', "Sampler parameters", "sd"), {
     "hide_samplers": OptionInfo([], "Hide samplers in user interface", gr.CheckboxGroup, lambda: {"choices": [x.name for x in shared_items.list_samplers()]}).needs_reload_ui(),
     "eta_ddim": OptionInfo(0.0, "Eta for DDIM", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Eta DDIM').info("noise multiplier; higher = more unpredictable results"),
     "eta_ancestral": OptionInfo(1.0, "Eta for k-diffusion samplers", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext='Eta').info("noise multiplier; currently only applies to ancestral samplers (i.e. Euler a) and SDE samplers"),
@@ -330,10 +356,11 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters"
     'uni_pc_lower_order_final': OptionInfo(True, "UniPC lower order final", infotext='UniPC lower order final'),
 }))
 
-options_templates.update(options_section(('postprocessing', "Postprocessing"), {
+options_templates.update(options_section(('postprocessing', "Postprocessing", "postprocessing"), {
     'postprocessing_enable_in_main_ui': OptionInfo([], "Enable postprocessing operations in txt2img and img2img tabs", ui_components.DropdownMulti, lambda: {"choices": [x.name for x in shared_items.postprocessing_scripts()]}),
     'postprocessing_operation_order': OptionInfo([], "Postprocessing operation order", ui_components.DropdownMulti, lambda: {"choices": [x.name for x in shared_items.postprocessing_scripts()]}),
     'upscaling_max_images_in_cache': OptionInfo(5, "Maximum number of images in upscaling cache", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),
+    'postprocessing_existing_caption_action': OptionInfo("Ignore", "Action for existing captions", gr.Radio, {"choices": ["Ignore", "Keep", "Prepend", "Append"]}).info("when generating captions using postprocessing; Ignore = use generated; Keep = use original; Prepend/Append = combine both"),
 }))
 
 options_templates.update(options_section((None, "Hidden options"), {

modules/styles.py

@@ -1,7 +1,7 @@
 import csv
+import fnmatch
 import os
 import os.path
-import re
 import typing
 import shutil
 
@@ -10,6 +10,7 @@ class PromptStyle(typing.NamedTuple):
     name: str
     prompt: str
     negative_prompt: str
+    path: str = None
 
 
 def merge_prompts(style_prompt: str, prompt: str) -> str:
@@ -29,38 +30,61 @@ def apply_styles_to_prompt(prompt, styles):
     return prompt
 
 
-re_spaces = re.compile("  +")
+def unwrap_style_text_from_prompt(style_text, prompt):
+    """
+    Checks the prompt to see if the style text is wrapped around it. If so,
+    returns True plus the prompt text without the style text. Otherwise, returns
+    False with the original prompt.
 
-
-def extract_style_text_from_prompt(style_text, prompt):
-    stripped_prompt = re.sub(re_spaces, " ", prompt.strip())
-    stripped_style_text = re.sub(re_spaces, " ", style_text.strip())
+    Note that the "cleaned" version of the style text is only used for matching
+    purposes here. It isn't returned; the original style text is not modified.
+    """
+    stripped_prompt = prompt
+    stripped_style_text = style_text
     if "{prompt}" in stripped_style_text:
-        left, right = stripped_style_text.split("{prompt}", 2)
+        # Work out whether the prompt is wrapped in the style text. If so, we
+        # return True and the "inner" prompt text that isn't part of the style.
+        try:
+            left, right = stripped_style_text.split("{prompt}", 2)
+        except ValueError as e:
+            # If the style text has multple "{prompt}"s, we can't split it into
+            # two parts. This is an error, but we can't do anything about it.
+            print(f"Unable to compare style text to prompt:\n{style_text}")
+            print(f"Error: {e}")
+            return False, prompt
         if stripped_prompt.startswith(left) and stripped_prompt.endswith(right):
-            prompt = stripped_prompt[len(left):len(stripped_prompt)-len(right)]
+            prompt = stripped_prompt[len(left) : len(stripped_prompt) - len(right)]
             return True, prompt
     else:
+        # Work out whether the given prompt ends with the style text. If so, we
+        # return True and the prompt text up to where the style text starts.
         if stripped_prompt.endswith(stripped_style_text):
-            prompt = stripped_prompt[:len(stripped_prompt)-len(stripped_style_text)]
-
-            if prompt.endswith(', '):
+            prompt = stripped_prompt[: len(stripped_prompt) - len(stripped_style_text)]
+            if prompt.endswith(", "):
                 prompt = prompt[:-2]
-
             return True, prompt
 
     return False, prompt
 
 
-def extract_style_from_prompts(style: PromptStyle, prompt, negative_prompt):
+def extract_original_prompts(style: PromptStyle, prompt, negative_prompt):
+    """
+    Takes a style and compares it to the prompt and negative prompt. If the style
+    matches, returns True plus the prompt and negative prompt with the style text
+    removed. Otherwise, returns False with the original prompt and negative prompt.
+    """
     if not style.prompt and not style.negative_prompt:
         return False, prompt, negative_prompt
 
-    match_positive, extracted_positive = extract_style_text_from_prompt(style.prompt, prompt)
+    match_positive, extracted_positive = unwrap_style_text_from_prompt(
+        style.prompt, prompt
+    )
     if not match_positive:
         return False, prompt, negative_prompt
 
-    match_negative, extracted_negative = extract_style_text_from_prompt(style.negative_prompt, negative_prompt)
+    match_negative, extracted_negative = unwrap_style_text_from_prompt(
+        style.negative_prompt, negative_prompt
+    )
     if not match_negative:
         return False, prompt, negative_prompt
 
@@ -69,25 +93,84 @@ def extract_style_from_prompts(style: PromptStyle, prompt, negative_prompt):
 
 class StyleDatabase:
     def __init__(self, path: str):
-        self.no_style = PromptStyle("None", "", "")
+        self.no_style = PromptStyle("None", "", "", None)
         self.styles = {}
         self.path = path
 
+        folder, file = os.path.split(self.path)
+        filename, _, ext = file.partition('*')
+        self.default_path = os.path.join(folder, filename + ext)
+
+        self.prompt_fields = [field for field in PromptStyle._fields if field != "path"]
+
         self.reload()
 
     def reload(self):
+        """
+        Clears the style database and reloads the styles from the CSV file(s)
+        matching the path used to initialize the database.
+        """
         self.styles.clear()
 
-        if not os.path.exists(self.path):
-            return
+        path, filename = os.path.split(self.path)
 
-        with open(self.path, "r", encoding="utf-8-sig", newline='') as file:
+        if "*" in filename:
+            fileglob = filename.split("*")[0] + "*.csv"
+            filelist = []
+            for file in os.listdir(path):
+                if fnmatch.fnmatch(file, fileglob):
+                    filelist.append(file)
+                    # Add a visible divider to the style list
+                    half_len = round(len(file) / 2)
+                    divider = f"{'-' * (20 - half_len)} {file.upper()}"
+                    divider = f"{divider} {'-' * (40 - len(divider))}"
+                    self.styles[divider] = PromptStyle(
+                        f"{divider}", None, None, "do_not_save"
+                    )
+                    # Add styles from this CSV file
+                    self.load_from_csv(os.path.join(path, file))
+            if len(filelist) == 0:
+                print(f"No styles found in {path} matching {fileglob}")
+                return
+        elif not os.path.exists(self.path):
+            print(f"Style database not found: {self.path}")
+            return
+        else:
+            self.load_from_csv(self.path)
+
+    def load_from_csv(self, path: str):
+        with open(path, "r", encoding="utf-8-sig", newline="") as file:
             reader = csv.DictReader(file, skipinitialspace=True)
             for row in reader:
+                # Ignore empty rows or rows starting with a comment
+                if not row or row["name"].startswith("#"):
+                    continue
                 # Support loading old CSV format with "name, text"-columns
                 prompt = row["prompt"] if "prompt" in row else row["text"]
                 negative_prompt = row.get("negative_prompt", "")
-                self.styles[row["name"]] = PromptStyle(row["name"], prompt, negative_prompt)
+                # Add style to database
+                self.styles[row["name"]] = PromptStyle(
+                    row["name"], prompt, negative_prompt, path
+                )
+
+    def get_style_paths(self) -> set:
+        """Returns a set of all distinct paths of files that styles are loaded from."""
+        # Update any styles without a path to the default path
+        for style in list(self.styles.values()):
+            if not style.path:
+                self.styles[style.name] = style._replace(path=self.default_path)
+
+        # Create a list of all distinct paths, including the default path
+        style_paths = set()
+        style_paths.add(self.default_path)
+        for _, style in self.styles.items():
+            if style.path:
+                style_paths.add(style.path)
+
+        # Remove any paths for styles that are just list dividers
+        style_paths.discard("do_not_save")
+
+        return style_paths
 
     def get_style_prompts(self, styles):
         return [self.styles.get(x, self.no_style).prompt for x in styles]
@@ -96,20 +179,40 @@ class StyleDatabase:
         return [self.styles.get(x, self.no_style).negative_prompt for x in styles]
 
     def apply_styles_to_prompt(self, prompt, styles):
-        return apply_styles_to_prompt(prompt, [self.styles.get(x, self.no_style).prompt for x in styles])
+        return apply_styles_to_prompt(
+            prompt, [self.styles.get(x, self.no_style).prompt for x in styles]
+        )
 
     def apply_negative_styles_to_prompt(self, prompt, styles):
-        return apply_styles_to_prompt(prompt, [self.styles.get(x, self.no_style).negative_prompt for x in styles])
+        return apply_styles_to_prompt(
+            prompt, [self.styles.get(x, self.no_style).negative_prompt for x in styles]
+        )
 
-    def save_styles(self, path: str) -> None:
-        # Always keep a backup file around
-        if os.path.exists(path):
-            shutil.copy(path, f"{path}.bak")
+    def save_styles(self, path: str = None) -> None:
+        # The path argument is deprecated, but kept for backwards compatibility
+        _ = path
 
-        with open(path, "w", encoding="utf-8-sig", newline='') as file:
-            writer = csv.DictWriter(file, fieldnames=PromptStyle._fields)
-            writer.writeheader()
-            writer.writerows(style._asdict() for k, style in self.styles.items())
+        style_paths = self.get_style_paths()
+
+        csv_names = [os.path.split(path)[1].lower() for path in style_paths]
+
+        for style_path in style_paths:
+            # Always keep a backup file around
+            if os.path.exists(style_path):
+                shutil.copy(style_path, f"{style_path}.bak")
+
+            # Write the styles to the CSV file
+            with open(style_path, "w", encoding="utf-8-sig", newline="") as file:
+                writer = csv.DictWriter(file, fieldnames=self.prompt_fields)
+                writer.writeheader()
+                for style in (s for s in self.styles.values() if s.path == style_path):
+                    # Skip style list dividers, e.g. "STYLES.CSV"
+                    if style.name.lower().strip("# ") in csv_names:
+                        continue
+                    # Write style fields, ignoring the path field
+                    writer.writerow(
+                        {k: v for k, v in style._asdict().items() if k != "path"}
+                    )
 
     def extract_styles_from_prompt(self, prompt, negative_prompt):
         extracted = []
@@ -120,7 +223,9 @@ class StyleDatabase:
             found_style = None
 
             for style in applicable_styles:
-                is_match, new_prompt, new_neg_prompt = extract_style_from_prompts(style, prompt, negative_prompt)
+                is_match, new_prompt, new_neg_prompt = extract_original_prompts(
+                    style, prompt, negative_prompt
+                )
                 if is_match:
                     found_style = style
                     prompt = new_prompt

modules/textual_inversion/autocrop.py

@@ -3,6 +3,8 @@ import requests
 import os
 import numpy as np
 from PIL import ImageDraw
+from modules import paths_internal
+from pkg_resources import parse_version
 
 GREEN = "#0F0"
 BLUE = "#00F"
@@ -25,7 +27,6 @@ def crop_image(im, settings):
         elif is_portrait(settings.crop_width, settings.crop_height):
             scale_by = settings.crop_height / im.height
 
-
     im = im.resize((int(im.width * scale_by), int(im.height * scale_by)))
     im_debug = im.copy()
 
@@ -69,6 +70,7 @@ def crop_image(im, settings):
 
     return results
 
+
 def focal_point(im, settings):
     corner_points = image_corner_points(im, settings) if settings.corner_points_weight > 0 else []
     entropy_points = image_entropy_points(im, settings) if settings.entropy_points_weight > 0 else []
@@ -78,118 +80,120 @@ def focal_point(im, settings):
 
     weight_pref_total = 0
     if corner_points:
-      weight_pref_total += settings.corner_points_weight
+        weight_pref_total += settings.corner_points_weight
     if entropy_points:
-      weight_pref_total += settings.entropy_points_weight
+        weight_pref_total += settings.entropy_points_weight
     if face_points:
-      weight_pref_total += settings.face_points_weight
+        weight_pref_total += settings.face_points_weight
 
     corner_centroid = None
     if corner_points:
-      corner_centroid = centroid(corner_points)
-      corner_centroid.weight = settings.corner_points_weight / weight_pref_total
-      pois.append(corner_centroid)
+        corner_centroid = centroid(corner_points)
+        corner_centroid.weight = settings.corner_points_weight / weight_pref_total
+        pois.append(corner_centroid)
 
     entropy_centroid = None
     if entropy_points:
-      entropy_centroid = centroid(entropy_points)
-      entropy_centroid.weight = settings.entropy_points_weight / weight_pref_total
-      pois.append(entropy_centroid)
+        entropy_centroid = centroid(entropy_points)
+        entropy_centroid.weight = settings.entropy_points_weight / weight_pref_total
+        pois.append(entropy_centroid)
 
     face_centroid = None
     if face_points:
-      face_centroid = centroid(face_points)
-      face_centroid.weight = settings.face_points_weight / weight_pref_total
-      pois.append(face_centroid)
+        face_centroid = centroid(face_points)
+        face_centroid.weight = settings.face_points_weight / weight_pref_total
+        pois.append(face_centroid)
 
     average_point = poi_average(pois, settings)
 
     if settings.annotate_image:
-      d = ImageDraw.Draw(im)
-      max_size = min(im.width, im.height) * 0.07
-      if corner_centroid is not None:
-        color = BLUE
-        box = corner_centroid.bounding(max_size * corner_centroid.weight)
-        d.text((box[0], box[1]-15), f"Edge: {corner_centroid.weight:.02f}", fill=color)
-        d.ellipse(box, outline=color)
-        if len(corner_points) > 1:
-          for f in corner_points:
-            d.rectangle(f.bounding(4), outline=color)
-      if entropy_centroid is not None:
-        color = "#ff0"
-        box = entropy_centroid.bounding(max_size * entropy_centroid.weight)
-        d.text((box[0], box[1]-15), f"Entropy: {entropy_centroid.weight:.02f}", fill=color)
-        d.ellipse(box, outline=color)
-        if len(entropy_points) > 1:
-          for f in entropy_points:
-            d.rectangle(f.bounding(4), outline=color)
-      if face_centroid is not None:
-        color = RED
-        box = face_centroid.bounding(max_size * face_centroid.weight)
-        d.text((box[0], box[1]-15), f"Face: {face_centroid.weight:.02f}", fill=color)
-        d.ellipse(box, outline=color)
-        if len(face_points) > 1:
-          for f in face_points:
-            d.rectangle(f.bounding(4), outline=color)
+        d = ImageDraw.Draw(im)
+        max_size = min(im.width, im.height) * 0.07
+        if corner_centroid is not None:
+            color = BLUE
+            box = corner_centroid.bounding(max_size * corner_centroid.weight)
+            d.text((box[0], box[1] - 15), f"Edge: {corner_centroid.weight:.02f}", fill=color)
+            d.ellipse(box, outline=color)
+            if len(corner_points) > 1:
+                for f in corner_points:
+                    d.rectangle(f.bounding(4), outline=color)
+        if entropy_centroid is not None:
+            color = "#ff0"
+            box = entropy_centroid.bounding(max_size * entropy_centroid.weight)
+            d.text((box[0], box[1] - 15), f"Entropy: {entropy_centroid.weight:.02f}", fill=color)
+            d.ellipse(box, outline=color)
+            if len(entropy_points) > 1:
+                for f in entropy_points:
+                    d.rectangle(f.bounding(4), outline=color)
+        if face_centroid is not None:
+            color = RED
+            box = face_centroid.bounding(max_size * face_centroid.weight)
+            d.text((box[0], box[1] - 15), f"Face: {face_centroid.weight:.02f}", fill=color)
+            d.ellipse(box, outline=color)
+            if len(face_points) > 1:
+                for f in face_points:
+                    d.rectangle(f.bounding(4), outline=color)
 
-      d.ellipse(average_point.bounding(max_size), outline=GREEN)
+        d.ellipse(average_point.bounding(max_size), outline=GREEN)
 
     return average_point
 
 
 def image_face_points(im, settings):
     if settings.dnn_model_path is not None:
-      detector = cv2.FaceDetectorYN.create(
-          settings.dnn_model_path,
-          "",
-          (im.width, im.height),
-          0.9, # score threshold
-          0.3, # nms threshold
-          5000 # keep top k before nms
-      )
-      faces = detector.detect(np.array(im))
-      results = []
-      if faces[1] is not None:
-        for face in faces[1]:
-          x = face[0]
-          y = face[1]
-          w = face[2]
-          h = face[3]
-          results.append(
-            PointOfInterest(
-              int(x + (w * 0.5)), # face focus left/right is center
-              int(y + (h * 0.33)), # face focus up/down is close to the top of the head
-              size = w,
-              weight = 1/len(faces[1])
-            )
-          )
-      return results
+        detector = cv2.FaceDetectorYN.create(
+            settings.dnn_model_path,
+            "",
+            (im.width, im.height),
+            0.9,  # score threshold
+            0.3,  # nms threshold
+            5000  # keep top k before nms
+        )
+        faces = detector.detect(np.array(im))
+        results = []
+        if faces[1] is not None:
+            for face in faces[1]:
+                x = face[0]
+                y = face[1]
+                w = face[2]
+                h = face[3]
+                results.append(
+                    PointOfInterest(
+                        int(x + (w * 0.5)),  # face focus left/right is center
+                        int(y + (h * 0.33)),  # face focus up/down is close to the top of the head
+                        size=w,
+                        weight=1 / len(faces[1])
+                    )
+                )
+        return results
     else:
-      np_im = np.array(im)
-      gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY)
+        np_im = np.array(im)
+        gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY)
 
-      tries = [
-        [ f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01 ],
-        [ f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05 ],
-        [ f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05 ],
-        [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05 ],
-        [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05 ],
-        [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05 ],
-        [ f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05 ],
-        [ f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05 ]
-      ]
-      for t in tries:
-        classifier = cv2.CascadeClassifier(t[0])
-        minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side
-        try:
-          faces = classifier.detectMultiScale(gray, scaleFactor=1.1,
-            minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE)
-        except Exception:
-          continue
+        tries = [
+            [f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01],
+            [f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05],
+            [f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05],
+            [f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05],
+            [f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05],
+            [f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05],
+            [f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05],
+            [f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05]
+        ]
+        for t in tries:
+            classifier = cv2.CascadeClassifier(t[0])
+            minsize = int(min(im.width, im.height) * t[1])  # at least N percent of the smallest side
+            try:
+                faces = classifier.detectMultiScale(gray, scaleFactor=1.1,
+                                                    minNeighbors=7, minSize=(minsize, minsize),
+                                                    flags=cv2.CASCADE_SCALE_IMAGE)
+            except Exception:
+                continue
 
-        if faces:
-          rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces]
-          return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0]-r[2]), weight=1/len(rects)) for r in rects]
+            if faces:
+                rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces]
+                return [PointOfInterest((r[0] + r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0] - r[2]),
+                                        weight=1 / len(rects)) for r in rects]
     return []
 
 
@@ -198,7 +202,7 @@ def image_corner_points(im, settings):
 
     # naive attempt at preventing focal points from collecting at watermarks near the bottom
     gd = ImageDraw.Draw(grayscale)
-    gd.rectangle([0, im.height*.9, im.width, im.height], fill="#999")
+    gd.rectangle([0, im.height * .9, im.width, im.height], fill="#999")
 
     np_im = np.array(grayscale)
 
@@ -206,7 +210,7 @@ def image_corner_points(im, settings):
         np_im,
         maxCorners=100,
         qualityLevel=0.04,
-        minDistance=min(grayscale.width, grayscale.height)*0.06,
+        minDistance=min(grayscale.width, grayscale.height) * 0.06,
         useHarrisDetector=False,
     )
 
@@ -215,8 +219,8 @@ def image_corner_points(im, settings):
 
     focal_points = []
     for point in points:
-      x, y = point.ravel()
-      focal_points.append(PointOfInterest(x, y, size=4, weight=1/len(points)))
+        x, y = point.ravel()
+        focal_points.append(PointOfInterest(x, y, size=4, weight=1 / len(points)))
 
     return focal_points
 
@@ -225,13 +229,13 @@ def image_entropy_points(im, settings):
     landscape = im.height < im.width
     portrait = im.height > im.width
     if landscape:
-      move_idx = [0, 2]
-      move_max = im.size[0]
+        move_idx = [0, 2]
+        move_max = im.size[0]
     elif portrait:
-      move_idx = [1, 3]
-      move_max = im.size[1]
+        move_idx = [1, 3]
+        move_max = im.size[1]
     else:
-      return []
+        return []
 
     e_max = 0
     crop_current = [0, 0, settings.crop_width, settings.crop_height]
@@ -241,14 +245,14 @@ def image_entropy_points(im, settings):
         e = image_entropy(crop)
 
         if (e > e_max):
-          e_max = e
-          crop_best = list(crop_current)
+            e_max = e
+            crop_best = list(crop_current)
 
         crop_current[move_idx[0]] += 4
         crop_current[move_idx[1]] += 4
 
-    x_mid = int(crop_best[0] + settings.crop_width/2)
-    y_mid = int(crop_best[1] + settings.crop_height/2)
+    x_mid = int(crop_best[0] + settings.crop_width / 2)
+    y_mid = int(crop_best[1] + settings.crop_height / 2)
 
     return [PointOfInterest(x_mid, y_mid, size=25, weight=1.0)]
 
@@ -294,22 +298,23 @@ def is_square(w, h):
     return w == h
 
 
-def download_and_cache_models(dirname):
-    download_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true'
-    model_file_name = 'face_detection_yunet.onnx'
+model_dir_opencv = os.path.join(paths_internal.models_path, 'opencv')
+if parse_version(cv2.__version__) >= parse_version('4.8'):
+    model_file_path = os.path.join(model_dir_opencv, 'face_detection_yunet_2023mar.onnx')
+    model_url = 'https://github.com/opencv/opencv_zoo/blob/b6e370b10f641879a87890d44e42173077154a05/models/face_detection_yunet/face_detection_yunet_2023mar.onnx?raw=true'
+else:
+    model_file_path = os.path.join(model_dir_opencv, 'face_detection_yunet.onnx')
+    model_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true'
 
-    os.makedirs(dirname, exist_ok=True)
 
-    cache_file = os.path.join(dirname, model_file_name)
-    if not os.path.exists(cache_file):
-        print(f"downloading face detection model from '{download_url}' to '{cache_file}'")
-        response = requests.get(download_url)
-        with open(cache_file, "wb") as f:
+def download_and_cache_models():
+    if not os.path.exists(model_file_path):
+        os.makedirs(model_dir_opencv, exist_ok=True)
+        print(f"downloading face detection model from '{model_url}' to '{model_file_path}'")
+        response = requests.get(model_url)
+        with open(model_file_path, "wb") as f:
             f.write(response.content)
-
-    if os.path.exists(cache_file):
-        return cache_file
-    return None
+    return model_file_path
 
 
 class PointOfInterest:

modules/textual_inversion/preprocess.py

@@ -1,232 +0,0 @@
-import os
-from PIL import Image, ImageOps
-import math
-import tqdm
-
-from modules import paths, shared, images, deepbooru
-from modules.textual_inversion import autocrop
-
-
-def preprocess(id_task, process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.15, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None):
-    try:
-        if process_caption:
-            shared.interrogator.load()
-
-        if process_caption_deepbooru:
-            deepbooru.model.start()
-
-        preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, 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)
-
-    finally:
-
-        if process_caption:
-            shared.interrogator.send_blip_to_ram()
-
-        if process_caption_deepbooru:
-            deepbooru.model.stop()
-
-
-def listfiles(dirname):
-    return os.listdir(dirname)
-
-
-class PreprocessParams:
-    src = None
-    dstdir = None
-    subindex = 0
-    flip = False
-    process_caption = False
-    process_caption_deepbooru = False
-    preprocess_txt_action = None
-
-
-def save_pic_with_caption(image, index, params: PreprocessParams, existing_caption=None):
-    caption = ""
-
-    if params.process_caption:
-        caption += shared.interrogator.generate_caption(image)
-
-    if params.process_caption_deepbooru:
-        if caption:
-            caption += ", "
-        caption += deepbooru.model.tag_multi(image)
-
-    filename_part = params.src
-    filename_part = os.path.splitext(filename_part)[0]
-    filename_part = os.path.basename(filename_part)
-
-    basename = f"{index:05}-{params.subindex}-{filename_part}"
-    image.save(os.path.join(params.dstdir, f"{basename}.png"))
-
-    if params.preprocess_txt_action == 'prepend' and existing_caption:
-        caption = f"{existing_caption} {caption}"
-    elif params.preprocess_txt_action == 'append' and existing_caption:
-        caption = f"{caption} {existing_caption}"
-    elif params.preprocess_txt_action == 'copy' and existing_caption:
-        caption = existing_caption
-
-    caption = caption.strip()
-
-    if caption:
-        with open(os.path.join(params.dstdir, f"{basename}.txt"), "w", encoding="utf8") as file:
-            file.write(caption)
-
-    params.subindex += 1
-
-
-def save_pic(image, index, params, existing_caption=None):
-    save_pic_with_caption(image, index, params, existing_caption=existing_caption)
-
-    if params.flip:
-        save_pic_with_caption(ImageOps.mirror(image), index, params, existing_caption=existing_caption)
-
-
-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
-
-# not using torchvision.transforms.CenterCrop because it doesn't allow float regions
-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)
-
-
-def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None):
-    width = process_width
-    height = process_height
-    src = os.path.abspath(process_src)
-    dst = os.path.abspath(process_dst)
-    split_threshold = max(0.0, min(1.0, split_threshold))
-    overlap_ratio = max(0.0, min(0.9, overlap_ratio))
-
-    assert src != dst, 'same directory specified as source and destination'
-
-    os.makedirs(dst, exist_ok=True)
-
-    files = listfiles(src)
-
-    shared.state.job = "preprocess"
-    shared.state.textinfo = "Preprocessing..."
-    shared.state.job_count = len(files)
-
-    params = PreprocessParams()
-    params.dstdir = dst
-    params.flip = process_flip
-    params.process_caption = process_caption
-    params.process_caption_deepbooru = process_caption_deepbooru
-    params.preprocess_txt_action = preprocess_txt_action
-
-    pbar = tqdm.tqdm(files)
-    for index, imagefile in enumerate(pbar):
-        params.subindex = 0
-        filename = os.path.join(src, imagefile)
-        try:
-            img = Image.open(filename)
-            img = ImageOps.exif_transpose(img)
-            img = img.convert("RGB")
-        except Exception:
-            continue
-
-        description = f"Preprocessing [Image {index}/{len(files)}]"
-        pbar.set_description(description)
-        shared.state.textinfo = description
-
-        params.src = filename
-
-        existing_caption = None
-        existing_caption_filename = f"{os.path.splitext(filename)[0]}.txt"
-        if os.path.exists(existing_caption_filename):
-            with open(existing_caption_filename, 'r', encoding="utf8") as file:
-                existing_caption = file.read()
-
-        if shared.state.interrupted:
-            break
-
-        if img.height > img.width:
-            ratio = (img.width * height) / (img.height * width)
-            inverse_xy = False
-        else:
-            ratio = (img.height * width) / (img.width * height)
-            inverse_xy = True
-
-        process_default_resize = True
-
-        if process_split and ratio < 1.0 and ratio <= split_threshold:
-            for splitted in split_pic(img, inverse_xy, width, height, overlap_ratio):
-                save_pic(splitted, index, params, existing_caption=existing_caption)
-            process_default_resize = False
-
-        if process_focal_crop and img.height != img.width:
-
-            dnn_model_path = None
-            try:
-                dnn_model_path = autocrop.download_and_cache_models(os.path.join(paths.models_path, "opencv"))
-            except Exception as e:
-                print("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", e)
-
-            autocrop_settings = autocrop.Settings(
-                crop_width = width,
-                crop_height = height,
-                face_points_weight = process_focal_crop_face_weight,
-                entropy_points_weight = process_focal_crop_entropy_weight,
-                corner_points_weight = process_focal_crop_edges_weight,
-                annotate_image = process_focal_crop_debug,
-                dnn_model_path = dnn_model_path,
-            )
-            for focal in autocrop.crop_image(img, autocrop_settings):
-                save_pic(focal, index, params, existing_caption=existing_caption)
-            process_default_resize = False
-
-        if process_multicrop:
-            cropped = multicrop_pic(img, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold)
-            if cropped is not None:
-                save_pic(cropped, index, params, existing_caption=existing_caption)
-            else:
-                print(f"skipped {img.width}x{img.height} image {filename} (can't find suitable size within error threshold)")
-            process_default_resize = False
-
-        if process_keep_original_size:
-            save_pic(img, index, params, existing_caption=existing_caption)
-            process_default_resize = False
-
-        if process_default_resize:
-            img = images.resize_image(1, img, width, height)
-            save_pic(img, index, params, existing_caption=existing_caption)
-
-        shared.state.nextjob()

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

@@ -1,9 +1,10 @@
 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

@@ -0,0 +1,59 @@
+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)