24 files changed, 918 insertions, 207 deletions

diff --git a/modules/api/api.py b/modules/api/api.py
index e702c9c0..688469ad 100644
--- a/modules/api/api.py
+++ b/modules/api/api.py
@@ -1,14 +1,19 @@
+import base64
+import io
 import time
 import uvicorn
+from threading import Lock
 from gradio.processing_utils import encode_pil_to_base64, decode_base64_to_file, decode_base64_to_image
-from fastapi import APIRouter, Depends, HTTPException
+from fastapi import APIRouter, Depends, FastAPI, HTTPException
 import modules.shared as shared
-from modules import devices
 from modules.api.models import *
 from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images
 from modules.sd_samplers import all_samplers
 from modules.extras import run_extras, run_pnginfo
-
+from PIL import PngImagePlugin
+from modules.sd_models import checkpoints_list
+from modules.realesrgan_model import get_realesrgan_models
+from typing import List
 
 def upscaler_to_index(name: str):
     try:
@@ -29,8 +34,26 @@ def setUpscalers(req: dict):
     return reqDict
 
 
+def encode_pil_to_base64(image):
+    with io.BytesIO() as output_bytes:
+
+        # Copy any text-only metadata
+        use_metadata = False
+        metadata = PngImagePlugin.PngInfo()
+        for key, value in image.info.items():
+            if isinstance(key, str) and isinstance(value, str):
+                metadata.add_text(key, value)
+                use_metadata = True
+
+        image.save(
+            output_bytes, "PNG", pnginfo=(metadata if use_metadata else None)
+        )
+        bytes_data = output_bytes.getvalue()
+    return base64.b64encode(bytes_data)
+
+
 class Api:
-    def __init__(self, app, queue_lock):
+    def __init__(self, app: FastAPI, queue_lock: Lock):
         self.router = APIRouter()
         self.app = app
         self.queue_lock = queue_lock
@@ -40,7 +63,20 @@ class Api:
         self.app.add_api_route("/sdapi/v1/extra-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=ExtrasBatchImagesResponse)
         self.app.add_api_route("/sdapi/v1/png-info", self.pnginfoapi, methods=["POST"], response_model=PNGInfoResponse)
         self.app.add_api_route("/sdapi/v1/progress", self.progressapi, methods=["GET"], response_model=ProgressResponse)
+        self.app.add_api_route("/sdapi/v1/interrogate", self.interrogateapi, methods=["POST"])
         self.app.add_api_route("/sdapi/v1/interrupt", self.interruptapi, methods=["POST"])
+        self.app.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=OptionsModel)
+        self.app.add_api_route("/sdapi/v1/options", self.set_config, methods=["POST"])
+        self.app.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=FlagsModel)
+        self.app.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=List[SamplerItem])
+        self.app.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[UpscalerItem])
+        self.app.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[SDModelItem])
+        self.app.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[HypernetworkItem])
+        self.app.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[FaceRestorerItem])
+        self.app.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[RealesrganItem])
+        self.app.add_api_route("/sdapi/v1/prompt-styles", self.get_promp_styles, methods=["GET"], response_model=List[PromptStyleItem])
+        self.app.add_api_route("/sdapi/v1/artist-categories", self.get_artists_categories, methods=["GET"], response_model=List[str])
+        self.app.add_api_route("/sdapi/v1/artists", self.get_artists, methods=["GET"], response_model=List[ArtistItem])
 
     def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI):
         sampler_index = sampler_to_index(txt2imgreq.sampler_index)
@@ -171,17 +207,96 @@ class Api:
 
         progress = min(progress, 1)
 
+        shared.state.set_current_image()
+
         current_image = None
         if shared.state.current_image and not req.skip_current_image:
             current_image = encode_pil_to_base64(shared.state.current_image)
 
         return ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image)
 
+    def interrogateapi(self, interrogatereq: InterrogateRequest):
+        image_b64 = interrogatereq.image
+        if image_b64 is None:
+            raise HTTPException(status_code=404, detail="Image not found") 
+
+        img = self.__base64_to_image(image_b64)
+
+        # Override object param
+        with self.queue_lock:
+            processed = shared.interrogator.interrogate(img)
+        
+        return InterrogateResponse(caption=processed)
+
     def interruptapi(self):
         shared.state.interrupt()
 
         return {}
 
+    def get_config(self):
+        options = {}
+        for key in shared.opts.data.keys():
+            metadata = shared.opts.data_labels.get(key)
+            if(metadata is not None):
+                options.update({key: shared.opts.data.get(key, shared.opts.data_labels.get(key).default)})
+            else:
+                options.update({key: shared.opts.data.get(key, None)})
+
+        return options
+
+    def set_config(self, req: OptionsModel):
+        # currently req has all options fields even if you send a dict like { "send_seed": false }, which means it will
+        # overwrite all options with default values.
+        raise RuntimeError('Setting options via API is not supported')
+
+        reqDict = vars(req)
+        for o in reqDict:
+            setattr(shared.opts, o, reqDict[o])
+
+        shared.opts.save(shared.config_filename)
+        return
+
+    def get_cmd_flags(self):
+        return vars(shared.cmd_opts)
+
+    def get_samplers(self):
+        return [{"name":sampler[0], "aliases":sampler[2], "options":sampler[3]} for sampler in all_samplers]
+
+    def get_upscalers(self):
+        upscalers = []
+
+        for upscaler in shared.sd_upscalers:
+            u = upscaler.scaler
+            upscalers.append({"name":u.name, "model_name":u.model_name, "model_path":u.model_path, "model_url":u.model_url})
+
+        return upscalers
+
+    def get_sd_models(self):
+        return [{"title":x.title, "model_name":x.model_name, "hash":x.hash, "filename": x.filename, "config": x.config} for x in checkpoints_list.values()]
+
+    def get_hypernetworks(self):
+        return [{"name": name, "path": shared.hypernetworks[name]} for name in shared.hypernetworks]
+
+    def get_face_restorers(self):
+        return [{"name":x.name(), "cmd_dir": getattr(x, "cmd_dir", None)} for x in shared.face_restorers]
+
+    def get_realesrgan_models(self):
+        return [{"name":x.name,"path":x.data_path, "scale":x.scale} for x in get_realesrgan_models(None)]
+
+    def get_promp_styles(self):
+        styleList = []
+        for k in shared.prompt_styles.styles:
+            style = shared.prompt_styles.styles[k]
+            styleList.append({"name":style[0], "prompt": style[1], "negative_prompr": style[2]})
+
+        return styleList
+
+    def get_artists_categories(self):
+        return shared.artist_db.cats
+
+    def get_artists(self):
+        return [{"name":x[0], "score":x[1], "category":x[2]} for x in shared.artist_db.artists]
+
     def launch(self, server_name, port):
         self.app.include_router(self.router)
         uvicorn.run(self.app, host=server_name, port=port)
diff --git a/modules/api/models.py b/modules/api/models.py
index 9ee42a17..34dbfa16 100644
--- a/modules/api/models.py
+++ b/modules/api/models.py
@@ -1,11 +1,11 @@
 import inspect
-from click import prompt
 from pydantic import BaseModel, Field, create_model
 from typing import Any, Optional
 from typing_extensions import Literal
 from inflection import underscore
 from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img
-from modules.shared import sd_upscalers
+from modules.shared import sd_upscalers, opts, parser
+from typing import Dict, List
 
 API_NOT_ALLOWED = [
     "self",
@@ -65,6 +65,7 @@ class PydanticModelGenerator:
 
         self._model_name = model_name
         self._class_data = merge_class_params(class_instance)
+
         self._model_def = [
             ModelDef(
                 field=underscore(k),
@@ -109,12 +110,12 @@ StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
 ).generate_model()
 
 class TextToImageResponse(BaseModel):
-    images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
+    images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
     parameters: dict
     info: str
 
 class ImageToImageResponse(BaseModel):
-    images: list[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
+    images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
     parameters: dict
     info: str
 
@@ -131,6 +132,7 @@ class ExtrasBaseRequest(BaseModel):
     upscaler_1: str = Field(default="None", title="Main upscaler", description=f"The name of the main upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}")
     upscaler_2: str = Field(default="None", title="Secondary upscaler", description=f"The name of the secondary upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}")
     extras_upscaler_2_visibility: float = Field(default=0, title="Secondary upscaler visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of secondary upscaler, values should be between 0 and 1.")
+    upscale_first: bool = Field(default=False, title="Upscale first", description="Should the upscaler run before restoring faces?")
 
 class ExtraBaseResponse(BaseModel):
     html_info: str = Field(title="HTML info", description="A series of HTML tags containing the process info.")
@@ -146,10 +148,10 @@ class FileData(BaseModel):
     name: str = Field(title="File name")
 
 class ExtrasBatchImagesRequest(ExtrasBaseRequest):
-    imageList: list[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings")
+    imageList: List[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings")
 
 class ExtrasBatchImagesResponse(ExtraBaseResponse):
-    images: list[str] = Field(title="Images", description="The generated images in base64 format.")
+    images: List[str] = Field(title="Images", description="The generated images in base64 format.")
 
 class PNGInfoRequest(BaseModel):
     image: str = Field(title="Image", description="The base64 encoded PNG image")
@@ -165,3 +167,75 @@ class ProgressResponse(BaseModel):
     eta_relative: float = Field(title="ETA in secs")
     state: dict = Field(title="State", description="The current state snapshot")
     current_image: str = Field(default=None, title="Current image", description="The current image in base64 format. opts.show_progress_every_n_steps is required for this to work.")
+
+class InterrogateRequest(BaseModel):
+    image: str = Field(default="", title="Image", description="Image to work on, must be a Base64 string containing the image's data.")
+
+class InterrogateResponse(BaseModel):
+    caption: str = Field(default=None, title="Caption", description="The generated caption for the image.")
+
+fields = {}
+for key, value in opts.data.items():
+    metadata = opts.data_labels.get(key)
+    optType = opts.typemap.get(type(value), type(value))
+
+    if (metadata is not None):
+        fields.update({key: (Optional[optType], Field(
+            default=metadata.default ,description=metadata.label))})
+    else:
+        fields.update({key: (Optional[optType], Field())})
+
+OptionsModel = create_model("Options", **fields)
+
+flags = {}
+_options = vars(parser)['_option_string_actions']
+for key in _options:
+    if(_options[key].dest != 'help'):
+        flag = _options[key]
+        _type = str
+        if _options[key].default is not None: _type = type(_options[key].default)
+        flags.update({flag.dest: (_type,Field(default=flag.default, description=flag.help))})
+
+FlagsModel = create_model("Flags", **flags)
+
+class SamplerItem(BaseModel):
+    name: str = Field(title="Name")
+    aliases: List[str] = Field(title="Aliases")
+    options: Dict[str, str] = Field(title="Options")
+
+class UpscalerItem(BaseModel):
+    name: str = Field(title="Name")
+    model_name: Optional[str] = Field(title="Model Name")
+    model_path: Optional[str] = Field(title="Path")
+    model_url: Optional[str] = Field(title="URL")
+
+class SDModelItem(BaseModel):
+    title: str = Field(title="Title")
+    model_name: str = Field(title="Model Name")
+    hash: str = Field(title="Hash")
+    filename: str = Field(title="Filename")
+    config: str = Field(title="Config file")
+
+class HypernetworkItem(BaseModel):
+    name: str = Field(title="Name")
+    path: Optional[str] = Field(title="Path")
+
+class FaceRestorerItem(BaseModel):
+    name: str = Field(title="Name")
+    cmd_dir: Optional[str] = Field(title="Path")
+
+class RealesrganItem(BaseModel):
+    name: str = Field(title="Name")
+    path: Optional[str] = Field(title="Path")
+    scale: Optional[int] = Field(title="Scale")
+
+class PromptStyleItem(BaseModel):
+    name: str = Field(title="Name")
+    prompt: Optional[str] = Field(title="Prompt")
+    negative_prompt: Optional[str] = Field(title="Negative Prompt")
+
+class ArtistItem(BaseModel):
+    name: str = Field(title="Name")
+    score: float = Field(title="Score")
+    category: str = Field(title="Category")
+
diff --git a/modules/esrgan_model.py b/modules/esrgan_model.py
index a13cf6ac..c61669b4 100644
--- a/modules/esrgan_model.py
+++ b/modules/esrgan_model.py
@@ -50,6 +50,7 @@ def mod2normal(state_dict):
 def resrgan2normal(state_dict, nb=23):

     # this code is copied from https://github.com/victorca25/iNNfer

     if "conv_first.weight" in state_dict and "body.0.rdb1.conv1.weight" in state_dict:

+        re8x = 0

         crt_net = {}

         items = []

         for k, v in state_dict.items():

@@ -75,10 +76,18 @@ def resrgan2normal(state_dict, nb=23):
         crt_net['model.3.bias'] = state_dict['conv_up1.bias']

         crt_net['model.6.weight'] = state_dict['conv_up2.weight']

         crt_net['model.6.bias'] = state_dict['conv_up2.bias']

-        crt_net['model.8.weight'] = state_dict['conv_hr.weight']

-        crt_net['model.8.bias'] = state_dict['conv_hr.bias']

-        crt_net['model.10.weight'] = state_dict['conv_last.weight']

-        crt_net['model.10.bias'] = state_dict['conv_last.bias']

+

+        if 'conv_up3.weight' in state_dict:

+            # modification supporting: https://github.com/ai-forever/Real-ESRGAN/blob/main/RealESRGAN/rrdbnet_arch.py

+            re8x = 3

+            crt_net['model.9.weight'] = state_dict['conv_up3.weight']

+            crt_net['model.9.bias'] = state_dict['conv_up3.bias']

+

+        crt_net[f'model.{8+re8x}.weight'] = state_dict['conv_hr.weight']

+        crt_net[f'model.{8+re8x}.bias'] = state_dict['conv_hr.bias']

+        crt_net[f'model.{10+re8x}.weight'] = state_dict['conv_last.weight']

+        crt_net[f'model.{10+re8x}.bias'] = state_dict['conv_last.bias']

+

         state_dict = crt_net

     return state_dict

 

diff --git a/modules/extensions.py b/modules/extensions.py
index 897af96e..8e0977fd 100644
--- a/modules/extensions.py
+++ b/modules/extensions.py
@@ -34,8 +34,11 @@ class Extension:
         if repo is None or repo.bare:

             self.remote = None

         else:

-            self.remote = next(repo.remote().urls, None)

-            self.status = 'unknown'

+            try:

+                self.remote = next(repo.remote().urls, None)

+                self.status = 'unknown'

+            except Exception:

+                self.remote = None

 

     def list_files(self, subdir, extension):

         from modules import scripts

diff --git a/modules/extras.py b/modules/extras.py
index 8e2ab35c..71b93a06 100644
--- a/modules/extras.py
+++ b/modules/extras.py
@@ -136,12 +136,13 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
 

     def run_upscalers_blend(params: List[UpscaleParams], image: Image.Image, info: str) -> Tuple[Image.Image, str]:

         blended_result: Image.Image = None

+        image_hash: str = hash(np.array(image.getdata()).tobytes())

         for upscaler in params:

             upscale_args = (upscaler.upscaler_idx, upscaling_resize, resize_mode,

                             upscaling_resize_w, upscaling_resize_h, upscaling_crop)

-            cache_key = LruCache.Key(image_hash=hash(np.array(image.getdata()).tobytes()),

+            cache_key = LruCache.Key(image_hash=image_hash,

                                      info_hash=hash(info),

-                                     args_hash=hash((upscale_args, upscale_first)))

+                                     args_hash=hash(upscale_args))

             cached_entry = cached_images.get(cache_key)

             if cached_entry is None:

                 res = upscale(image, *upscale_args)

diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py
index a11e01d6..7f182712 100644
--- a/modules/hypernetworks/hypernetwork.py
+++ b/modules/hypernetworks/hypernetwork.py
@@ -22,6 +22,8 @@ from collections import defaultdict, deque
 from statistics import stdev, mean

 

 

+optimizer_dict = {optim_name : cls_obj for optim_name, cls_obj in inspect.getmembers(torch.optim, inspect.isclass) if optim_name != "Optimizer"}

+

 class HypernetworkModule(torch.nn.Module):

     multiplier = 1.0

     activation_dict = {

@@ -35,7 +37,8 @@ class HypernetworkModule(torch.nn.Module):
     }

     activation_dict.update({cls_name.lower(): cls_obj for cls_name, cls_obj in inspect.getmembers(torch.nn.modules.activation) if inspect.isclass(cls_obj) and cls_obj.__module__ == 'torch.nn.modules.activation'})

 

-    def __init__(self, dim, state_dict=None, layer_structure=None, activation_func=None, weight_init='Normal', add_layer_norm=False, use_dropout=False):

+    def __init__(self, dim, state_dict=None, layer_structure=None, activation_func=None, weight_init='Normal',

+                 add_layer_norm=False, use_dropout=False, activate_output=False, last_layer_dropout=True):

         super().__init__()

 

         assert layer_structure is not None, "layer_structure must not be None"

@@ -48,8 +51,8 @@ class HypernetworkModule(torch.nn.Module):
             # Add a fully-connected layer

             linears.append(torch.nn.Linear(int(dim * layer_structure[i]), int(dim * layer_structure[i+1])))

 

-            # Add an activation func

-            if activation_func == "linear" or activation_func is None:

+            # Add an activation func except last layer

+            if activation_func == "linear" or activation_func is None or (i >= len(layer_structure) - 2 and not activate_output):

                 pass

             elif activation_func in self.activation_dict:

                 linears.append(self.activation_dict[activation_func]())

@@ -60,8 +63,8 @@ class HypernetworkModule(torch.nn.Module):
             if add_layer_norm:

                 linears.append(torch.nn.LayerNorm(int(dim * layer_structure[i+1])))

 

-            # Add dropout expect last layer

-            if use_dropout and i < len(layer_structure) - 3:

+            # Add dropout except last layer

+            if use_dropout and (i < len(layer_structure) - 3 or last_layer_dropout and i < len(layer_structure) - 2):

                 linears.append(torch.nn.Dropout(p=0.3))

 

         self.linear = torch.nn.Sequential(*linears)

@@ -75,7 +78,7 @@ class HypernetworkModule(torch.nn.Module):
                     w, b = layer.weight.data, layer.bias.data

                     if weight_init == "Normal" or type(layer) == torch.nn.LayerNorm:

                         normal_(w, mean=0.0, std=0.01)

-                        normal_(b, mean=0.0, std=0.005)

+                        normal_(b, mean=0.0, std=0)

                     elif weight_init == 'XavierUniform':

                         xavier_uniform_(w)

                         zeros_(b)

@@ -127,7 +130,7 @@ class Hypernetwork:
     filename = None

     name = None

 

-    def __init__(self, name=None, enable_sizes=None, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False):

+    def __init__(self, name=None, enable_sizes=None, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False, activate_output=False, **kwargs):

         self.filename = None

         self.name = name

         self.layers = {}

@@ -139,11 +142,17 @@ class Hypernetwork:
         self.weight_init = weight_init

         self.add_layer_norm = add_layer_norm

         self.use_dropout = use_dropout

+        self.activate_output = activate_output

+        self.last_layer_dropout = kwargs['last_layer_dropout'] if 'last_layer_dropout' in kwargs else True

+        self.optimizer_name = None

+        self.optimizer_state_dict = None

 

         for size in enable_sizes or []:

             self.layers[size] = (

-                HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),

-                HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),

+                HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.weight_init,

+                                   self.add_layer_norm, self.use_dropout, self.activate_output, last_layer_dropout=self.last_layer_dropout),

+                HypernetworkModule(size, None, self.layer_structure, self.activation_func, self.weight_init,

+                                   self.add_layer_norm, self.use_dropout, self.activate_output, last_layer_dropout=self.last_layer_dropout),

             )

 

     def weights(self):

@@ -158,6 +167,7 @@ class Hypernetwork:
 

     def save(self, filename):

         state_dict = {}

+        optimizer_saved_dict = {}

 

         for k, v in self.layers.items():

             state_dict[k] = (v[0].state_dict(), v[1].state_dict())

@@ -171,8 +181,17 @@ class Hypernetwork:
         state_dict['use_dropout'] = self.use_dropout

         state_dict['sd_checkpoint'] = self.sd_checkpoint

         state_dict['sd_checkpoint_name'] = self.sd_checkpoint_name

+        state_dict['activate_output'] = self.activate_output

+        state_dict['last_layer_dropout'] = self.last_layer_dropout

+

+        if self.optimizer_name is not None:

+            optimizer_saved_dict['optimizer_name'] = self.optimizer_name

 

         torch.save(state_dict, filename)

+        if shared.opts.save_optimizer_state and self.optimizer_state_dict:

+            optimizer_saved_dict['hash'] = sd_models.model_hash(filename)

+            optimizer_saved_dict['optimizer_state_dict'] = self.optimizer_state_dict

+            torch.save(optimizer_saved_dict, filename + '.optim')

 

     def load(self, filename):

         self.filename = filename

@@ -191,12 +210,29 @@ class Hypernetwork:
         print(f"Layer norm is set to {self.add_layer_norm}")

         self.use_dropout = state_dict.get('use_dropout', False)

         print(f"Dropout usage is set to {self.use_dropout}" )

+        self.activate_output = state_dict.get('activate_output', True)

+        print(f"Activate last layer is set to {self.activate_output}")

+        self.last_layer_dropout = state_dict.get('last_layer_dropout', False)

+

+        optimizer_saved_dict = torch.load(self.filename + '.optim', map_location = 'cpu') if os.path.exists(self.filename + '.optim') else {}

+        self.optimizer_name = optimizer_saved_dict.get('optimizer_name', 'AdamW')

+        print(f"Optimizer name is {self.optimizer_name}")

+        if sd_models.model_hash(filename) == optimizer_saved_dict.get('hash', None):

+            self.optimizer_state_dict = optimizer_saved_dict.get('optimizer_state_dict', None)

+        else:

+            self.optimizer_state_dict = None

+        if self.optimizer_state_dict:

+            print("Loaded existing optimizer from checkpoint")

+        else:

+            print("No saved optimizer exists in checkpoint")

 

         for size, sd in state_dict.items():

             if type(size) == int:

                 self.layers[size] = (

-                    HypernetworkModule(size, sd[0], self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),

-                    HypernetworkModule(size, sd[1], self.layer_structure, self.activation_func, self.weight_init, self.add_layer_norm, self.use_dropout),

+                    HypernetworkModule(size, sd[0], self.layer_structure, self.activation_func, self.weight_init,

+                                       self.add_layer_norm, self.use_dropout, self.activate_output, last_layer_dropout=self.last_layer_dropout),

+                    HypernetworkModule(size, sd[1], self.layer_structure, self.activation_func, self.weight_init,

+                                       self.add_layer_norm, self.use_dropout, self.activate_output, last_layer_dropout=self.last_layer_dropout),

                 )

 

         self.name = state_dict.get('name', self.name)

@@ -207,11 +243,11 @@ class Hypernetwork:
 

 def list_hypernetworks(path):

     res = {}

-    for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True):

+    for filename in sorted(glob.iglob(os.path.join(path, '**/*.pt'), recursive=True)):

         name = os.path.splitext(os.path.basename(filename))[0]

         # Prevent a hypothetical "None.pt" from being listed.

         if name != "None":

-            res[name] = filename

+            res[name + f"({sd_models.model_hash(filename)})"] = filename

     return res

 

 

@@ -346,6 +382,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
     shared.state.textinfo = "Initializing hypernetwork training..."

     shared.state.job_count = steps

 

+    hypernetwork_name = hypernetwork_name.rsplit('(', 1)[0]

     filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork_name}.pt')

 

     log_directory = os.path.join(log_directory, datetime.datetime.now().strftime("%Y-%m-%d"), hypernetwork_name)

@@ -392,8 +429,22 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
     weights = hypernetwork.weights()

     for weight in weights:

         weight.requires_grad = True

-    # if optimizer == "AdamW": or else Adam / AdamW / SGD, etc...

-    optimizer = torch.optim.AdamW(weights, lr=scheduler.learn_rate)

+

+    # Here we use optimizer from saved HN, or we can specify as UI option.

+    if hypernetwork.optimizer_name in optimizer_dict:

+        optimizer = optimizer_dict[hypernetwork.optimizer_name](params=weights, lr=scheduler.learn_rate)

+        optimizer_name = hypernetwork.optimizer_name

+    else:

+        print(f"Optimizer type {hypernetwork.optimizer_name} is not defined!")

+        optimizer = torch.optim.AdamW(params=weights, lr=scheduler.learn_rate)

+        optimizer_name = 'AdamW'

+

+    if hypernetwork.optimizer_state_dict:  # This line must be changed if Optimizer type can be different from saved optimizer.

+        try:

+            optimizer.load_state_dict(hypernetwork.optimizer_state_dict)

+        except RuntimeError as e:

+            print("Cannot resume from saved optimizer!")

+            print(e)

 

     steps_without_grad = 0

 

@@ -455,7 +506,11 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
             # Before saving, change name to match current checkpoint.

             hypernetwork_name_every = f'{hypernetwork_name}-{steps_done}'

             last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork_name_every}.pt')

+            hypernetwork.optimizer_name = optimizer_name

+            if shared.opts.save_optimizer_state:

+                hypernetwork.optimizer_state_dict = optimizer.state_dict()

             save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, last_saved_file)

+            hypernetwork.optimizer_state_dict = None  # dereference it after saving, to save memory.

 

         textual_inversion.write_loss(log_directory, "hypernetwork_loss.csv", hypernetwork.step, len(ds), {

             "loss": f"{previous_mean_loss:.7f}",

@@ -518,8 +573,12 @@ Last saved image: {html.escape(last_saved_image)}<br/>
     report_statistics(loss_dict)

 

     filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork_name}.pt')

+    hypernetwork.optimizer_name = optimizer_name

+    if shared.opts.save_optimizer_state:

+        hypernetwork.optimizer_state_dict = optimizer.state_dict()

     save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, filename)

-

+    del optimizer

+    hypernetwork.optimizer_state_dict = None  # dereference it after saving, to save memory.

     return hypernetwork, filename

 

 def save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, filename):

diff --git a/modules/hypernetworks/ui.py b/modules/hypernetworks/ui.py
index aad09ffc..c2d4b51c 100644
--- a/modules/hypernetworks/ui.py
+++ b/modules/hypernetworks/ui.py
@@ -9,7 +9,7 @@ from modules import devices, sd_hijack, shared
 from modules.hypernetworks import hypernetwork

 

 not_available = ["hardswish", "multiheadattention"]

-keys = ["linear"] + list(x for x in hypernetwork.HypernetworkModule.activation_dict.keys() if x not in not_available)

+keys = list(x for x in hypernetwork.HypernetworkModule.activation_dict.keys() if x not in not_available)

 

 def create_hypernetwork(name, enable_sizes, overwrite_old, layer_structure=None, activation_func=None, weight_init=None, add_layer_norm=False, use_dropout=False):

     # Remove illegal characters from name.

diff --git a/modules/img2img.py b/modules/img2img.py
index 35c5df9b..be9f3653 100644
--- a/modules/img2img.py
+++ b/modules/img2img.py
@@ -81,7 +81,8 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
         mask = None

 

     # Use the EXIF orientation of photos taken by smartphones.

-    image = ImageOps.exif_transpose(image) 

+    if image is not None:

+        image = ImageOps.exif_transpose(image) 

 

     assert 0. <= denoising_strength <= 1., 'can only work with strength in [0.0, 1.0]'

 

@@ -137,6 +138,8 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
         if processed is None:

             processed = process_images(p)

 

+    p.close()

+

     shared.total_tqdm.clear()

 

     generation_info_js = processed.js()

diff --git a/modules/ldsr_model_arch.py b/modules/ldsr_model_arch.py
index 14db5076..90e0a2f0 100644
--- a/modules/ldsr_model_arch.py
+++ b/modules/ldsr_model_arch.py
@@ -101,8 +101,8 @@ class LDSR:
         down_sample_rate = target_scale / 4
         wd = width_og * down_sample_rate
         hd = height_og * down_sample_rate
-        width_downsampled_pre = int(wd)
-        height_downsampled_pre = int(hd)
+        width_downsampled_pre = int(np.ceil(wd))
+        height_downsampled_pre = int(np.ceil(hd))
 
         if down_sample_rate != 1:
             print(
@@ -110,7 +110,12 @@ class LDSR:
             im_og = im_og.resize((width_downsampled_pre, height_downsampled_pre), Image.LANCZOS)
         else:
             print(f"Down sample rate is 1 from {target_scale} / 4 (Not downsampling)")
-        logs = self.run(model["model"], im_og, diffusion_steps, eta)
+        
+        # pad width and height to multiples of 64, pads with the edge values of image to avoid artifacts
+        pad_w, pad_h = np.max(((2, 2), np.ceil(np.array(im_og.size) / 64).astype(int)), axis=0) * 64 - im_og.size
+        im_padded = Image.fromarray(np.pad(np.array(im_og), ((0, pad_h), (0, pad_w), (0, 0)), mode='edge'))
+        
+        logs = self.run(model["model"], im_padded, diffusion_steps, eta)
 
         sample = logs["sample"]
         sample = sample.detach().cpu()
@@ -120,6 +125,9 @@ class LDSR:
         sample = np.transpose(sample, (0, 2, 3, 1))
         a = Image.fromarray(sample[0])
 
+        # remove padding
+        a = a.crop((0, 0) + tuple(np.array(im_og.size) * 4))
+
         del model
         gc.collect()
         torch.cuda.empty_cache()
diff --git a/modules/localization.py b/modules/localization.py
index b1810cda..f6a6f2fb 100644
--- a/modules/localization.py
+++ b/modules/localization.py
@@ -3,6 +3,7 @@ import os
 import sys

 import traceback

 

+

 localizations = {}

 

 

@@ -16,6 +17,11 @@ def list_localizations(dirname):
 

         localizations[fn] = os.path.join(dirname, file)

 

+    from modules import scripts

+    for file in scripts.list_scripts("localizations", ".json"):

+        fn, ext = os.path.splitext(file.filename)

+        localizations[fn] = file.path

+

 

 def localization_js(current_localization_name):

     fn = localizations.get(current_localization_name, None)

diff --git a/modules/masking.py b/modules/masking.py
index fd8d9241..a5c4d2da 100644
--- a/modules/masking.py
+++ b/modules/masking.py
@@ -49,7 +49,7 @@ def expand_crop_region(crop_region, processing_width, processing_height, image_w
     ratio_processing = processing_width / processing_height

 

     if ratio_crop_region > ratio_processing:

-        desired_height = (x2 - x1) * ratio_processing

+        desired_height = (x2 - x1) / ratio_processing

         desired_height_diff = int(desired_height - (y2-y1))

         y1 -= desired_height_diff//2

         y2 += desired_height_diff - desired_height_diff//2

diff --git a/modules/modelloader.py b/modules/modelloader.py
index b0f2f33d..e4a6f8ac 100644
--- a/modules/modelloader.py
+++ b/modules/modelloader.py
@@ -85,6 +85,9 @@ def cleanup_models():
     src_path = os.path.join(root_path, "ESRGAN")
     dest_path = os.path.join(models_path, "ESRGAN")
     move_files(src_path, dest_path)
+    src_path = os.path.join(models_path, "BSRGAN")
+    dest_path = os.path.join(models_path, "ESRGAN")
+    move_files(src_path, dest_path, ".pth")
     src_path = os.path.join(root_path, "gfpgan")
     dest_path = os.path.join(models_path, "GFPGAN")
     move_files(src_path, dest_path)
diff --git a/modules/processing.py b/modules/processing.py
index db35983b..b6f726b1 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -134,11 +134,7 @@ class StableDiffusionProcessing():
             # Dummy zero conditioning if we're not using inpainting model.

             # Still takes up a bit of memory, but no encoder call.

             # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.

-            return torch.zeros(

-                x.shape[0], 5, 1, 1, 

-                dtype=x.dtype, 

-                device=x.device

-            )

+            return x.new_zeros(x.shape[0], 5, 1, 1)

 

         height = height or self.height

         width = width or self.width

@@ -156,11 +152,7 @@ class StableDiffusionProcessing():
     def img2img_image_conditioning(self, source_image, latent_image, image_mask = None):

         if self.sampler.conditioning_key not in {'hybrid', 'concat'}:

             # Dummy zero conditioning if we're not using inpainting model.

-            return torch.zeros(

-                latent_image.shape[0], 5, 1, 1,

-                dtype=latent_image.dtype,

-                device=latent_image.device

-            )

+            return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)

 

         # Handle the different mask inputs

         if image_mask is not None:

@@ -174,11 +166,11 @@ class StableDiffusionProcessing():
                 # Inpainting model uses a discretized mask as input, so we round to either 1.0 or 0.0

                 conditioning_mask = torch.round(conditioning_mask)

         else:

-            conditioning_mask = torch.ones(1, 1, *source_image.shape[-2:])

+            conditioning_mask = source_image.new_ones(1, 1, *source_image.shape[-2:])

 

         # Create another latent image, this time with a masked version of the original input.

         # Smoothly interpolate between the masked and unmasked latent conditioning image using a parameter.

-        conditioning_mask = conditioning_mask.to(source_image.device)

+        conditioning_mask = conditioning_mask.to(source_image.device).to(source_image.dtype)

         conditioning_image = torch.lerp(

             source_image,

             source_image * (1.0 - conditioning_mask),

@@ -199,9 +191,13 @@ class StableDiffusionProcessing():
     def init(self, all_prompts, all_seeds, all_subseeds):

         pass

 

-    def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):

+    def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):

         raise NotImplementedError()

 

+    def close(self):

+        self.sd_model = None

+        self.sampler = None

+

 

 class Processed:

     def __init__(self, p: StableDiffusionProcessing, images_list, seed=-1, info="", subseed=None, all_prompts=None, all_seeds=None, all_subseeds=None, index_of_first_image=0, infotexts=None):

@@ -507,6 +503,9 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             if len(prompts) == 0:

                 break

 

+            if p.scripts is not None:

+                p.scripts.process_batch(p, batch_number=n, prompts=prompts, seeds=seeds, subseeds=subseeds)

+

             with devices.autocast():

                 uc = prompt_parser.get_learned_conditioning(shared.sd_model, len(prompts) * [p.negative_prompt], p.steps)

                 c = prompt_parser.get_multicond_learned_conditioning(shared.sd_model, prompts, p.steps)

@@ -519,7 +518,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                 shared.state.job = f"Batch {n+1} out of {p.n_iter}"

 

             with devices.autocast():

-                samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength)

+                samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts)

 

             samples_ddim = samples_ddim.to(devices.dtype_vae)

             x_samples_ddim = decode_first_stage(p.sd_model, samples_ddim)

@@ -599,9 +598,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
     if p.scripts is not None:

         p.scripts.postprocess(p, res)

 

-    p.sd_model = None

-    p.sampler = None

-

     return res

 

 

@@ -650,7 +646,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             self.truncate_x = int(self.firstphase_width - firstphase_width_truncated) // opt_f

             self.truncate_y = int(self.firstphase_height - firstphase_height_truncated) // opt_f

 

-    def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):

+    def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):

         self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model)

 

         if not self.enable_hr:

@@ -663,9 +659,28 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 

         samples = samples[:, :, self.truncate_y//2:samples.shape[2]-self.truncate_y//2, self.truncate_x//2:samples.shape[3]-self.truncate_x//2]

 

+        """saves image before applying hires fix, if enabled in options; takes as an arguyment either an image or batch with latent space images"""

+        def save_intermediate(image, index):

+            if not opts.save or self.do_not_save_samples or not opts.save_images_before_highres_fix:

+                return

+

+            if not isinstance(image, Image.Image):

+                image = sd_samplers.sample_to_image(image, index)

+

+            images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix")

+

         if opts.use_scale_latent_for_hires_fix:

+            for i in range(samples.shape[0]):

+                save_intermediate(samples, i)

+

             samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")

 

+            # Avoid making the inpainting conditioning unless necessary as 

+            # this does need some extra compute to decode / encode the image again.

+            if getattr(self, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) < 1.0:

+                image_conditioning = self.img2img_image_conditioning(decode_first_stage(self.sd_model, samples), samples)

+            else:

+                image_conditioning = self.txt2img_image_conditioning(samples)

         else:

             decoded_samples = decode_first_stage(self.sd_model, samples)

             lowres_samples = torch.clamp((decoded_samples + 1.0) / 2.0, min=0.0, max=1.0)

@@ -675,6 +690,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
                 x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2)

                 x_sample = x_sample.astype(np.uint8)

                 image = Image.fromarray(x_sample)

+

+                save_intermediate(image, i)

+

                 image = images.resize_image(0, image, self.width, self.height)

                 image = np.array(image).astype(np.float32) / 255.0

                 image = np.moveaxis(image, 2, 0)

@@ -686,14 +704,14 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 

             samples = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(decoded_samples))

 

+            image_conditioning = self.img2img_image_conditioning(decoded_samples, samples)

+

         shared.state.nextjob()

 

         self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model)

 

         noise = create_random_tensors(samples.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)

 

-        image_conditioning = self.txt2img_image_conditioning(x)

-

         # GC now before running the next img2img to prevent running out of memory

         x = None

         devices.torch_gc()

@@ -832,8 +850,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
 

         self.image_conditioning = self.img2img_image_conditioning(image, self.init_latent, self.image_mask)

 

-

-    def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):

+    def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):

         x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)

 

         samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning)

@@ -844,4 +861,4 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
         del x

         devices.torch_gc()

 

-        return samples
\ No newline at end of file
+        return samples

diff --git a/modules/safe.py b/modules/safe.py
index 348a24fc..a9209e38 100644
--- a/modules/safe.py
+++ b/modules/safe.py
@@ -23,11 +23,18 @@ def encode(*args):
 

 

 class RestrictedUnpickler(pickle.Unpickler):

+    extra_handler = None

+

     def persistent_load(self, saved_id):

         assert saved_id[0] == 'storage'

         return TypedStorage()

 

     def find_class(self, module, name):

+        if self.extra_handler is not None:

+            res = self.extra_handler(module, name)

+            if res is not None:

+                return res

+

         if module == 'collections' and name == 'OrderedDict':

             return getattr(collections, name)

         if module == 'torch._utils' and name in ['_rebuild_tensor_v2', '_rebuild_parameter']:

@@ -52,7 +59,7 @@ class RestrictedUnpickler(pickle.Unpickler):
             return set

 

         # Forbid everything else.

-        raise pickle.UnpicklingError(f"global '{module}/{name}' is forbidden")

+        raise Exception(f"global '{module}/{name}' is forbidden")

 

 

 allowed_zip_names = ["archive/data.pkl", "archive/version"]

@@ -69,7 +76,7 @@ def check_zip_filenames(filename, names):
         raise Exception(f"bad file inside {filename}: {name}")

 

 

-def check_pt(filename):

+def check_pt(filename, extra_handler):

     try:

 

         # new pytorch format is a zip file

@@ -78,6 +85,7 @@ def check_pt(filename):
 

             with z.open('archive/data.pkl') as file:

                 unpickler = RestrictedUnpickler(file)

+                unpickler.extra_handler = extra_handler

                 unpickler.load()

 

     except zipfile.BadZipfile:

@@ -85,16 +93,42 @@ def check_pt(filename):
         # if it's not a zip file, it's an olf pytorch format, with five objects written to pickle

         with open(filename, "rb") as file:

             unpickler = RestrictedUnpickler(file)

+            unpickler.extra_handler = extra_handler

             for i in range(5):

                 unpickler.load()

 

 

 def load(filename, *args, **kwargs):

+    return load_with_extra(filename, *args, **kwargs)

+

+

+def load_with_extra(filename, extra_handler=None, *args, **kwargs):

+    """

+    this functon is intended to be used by extensions that want to load models with

+    some extra classes in them that the usual unpickler would find suspicious.

+

+    Use the extra_handler argument to specify a function that takes module and field name as text,

+    and returns that field's value:

+

+    ```python

+    def extra(module, name):

+        if module == 'collections' and name == 'OrderedDict':

+            return collections.OrderedDict

+

+        return None

+

+    safe.load_with_extra('model.pt', extra_handler=extra)

+    ```

+

+    The alternative to this is just to use safe.unsafe_torch_load('model.pt'), which as the name implies is

+    definitely unsafe.

+    """

+

     from modules import shared

 

     try:

         if not shared.cmd_opts.disable_safe_unpickle:

-            check_pt(filename)

+            check_pt(filename, extra_handler)

 

     except pickle.UnpicklingError:

         print(f"Error verifying pickled file from {filename}:", file=sys.stderr)

diff --git a/modules/script_callbacks.py b/modules/script_callbacks.py
index ce264690..74dfb880 100644
--- a/modules/script_callbacks.py
+++ b/modules/script_callbacks.py
@@ -2,6 +2,7 @@ import sys
 import traceback

 from collections import namedtuple

 import inspect

+from typing import Optional

 

 from fastapi import FastAPI

 from gradio import Blocks

@@ -26,25 +27,42 @@ class ImageSaveParams:
         """dictionary with parameters for image's PNG info data; infotext will have the key 'parameters'"""

 

 

+class CFGDenoiserParams:

+    def __init__(self, x, image_cond, sigma, sampling_step, total_sampling_steps):

+        self.x = x

+        """Latent image representation in the process of being denoised"""

+        

+        self.image_cond = image_cond

+        """Conditioning image"""

+        

+        self.sigma = sigma

+        """Current sigma noise step value"""

+        

+        self.sampling_step = sampling_step

+        """Current Sampling step number"""

+        

+        self.total_sampling_steps = total_sampling_steps

+        """Total number of sampling steps planned"""

+

+

 ScriptCallback = namedtuple("ScriptCallback", ["script", "callback"])

-callbacks_app_started = []

-callbacks_model_loaded = []

-callbacks_ui_tabs = []

-callbacks_ui_settings = []

-callbacks_before_image_saved = []

-callbacks_image_saved = []

+callback_map = dict(

+    callbacks_app_started=[],

+    callbacks_model_loaded=[],

+    callbacks_ui_tabs=[],

+    callbacks_ui_settings=[],

+    callbacks_before_image_saved=[],

+    callbacks_image_saved=[],

+    callbacks_cfg_denoiser=[]

+)

 

 

 def clear_callbacks():

-    callbacks_model_loaded.clear()

-    callbacks_ui_tabs.clear()

-    callbacks_ui_settings.clear()

-    callbacks_before_image_saved.clear()

-    callbacks_image_saved.clear()

-

+    for callback_list in callback_map.values():

+        callback_list.clear()

 

-def app_started_callback(demo: Blocks, app: FastAPI):

-    for c in callbacks_app_started:

+def app_started_callback(demo: Optional[Blocks], app: FastAPI):

+    for c in callback_map['callbacks_app_started']:

         try:

             c.callback(demo, app)

         except Exception:

@@ -52,7 +70,7 @@ def app_started_callback(demo: Blocks, app: FastAPI):
 

 

 def model_loaded_callback(sd_model):

-    for c in callbacks_model_loaded:

+    for c in callback_map['callbacks_model_loaded']:

         try:

             c.callback(sd_model)

         except Exception:

@@ -62,7 +80,7 @@ def model_loaded_callback(sd_model):
 def ui_tabs_callback():

     res = []

     

-    for c in callbacks_ui_tabs:

+    for c in callback_map['callbacks_ui_tabs']:

         try:

             res += c.callback() or []

         except Exception:

@@ -72,7 +90,7 @@ def ui_tabs_callback():
 

 

 def ui_settings_callback():

-    for c in callbacks_ui_settings:

+    for c in callback_map['callbacks_ui_settings']:

         try:

             c.callback()

         except Exception:

@@ -80,7 +98,7 @@ def ui_settings_callback():
 

 

 def before_image_saved_callback(params: ImageSaveParams):

-    for c in callbacks_before_image_saved:

+    for c in callback_map['callbacks_before_image_saved']:

         try:

             c.callback(params)

         except Exception:

@@ -88,30 +106,54 @@ def before_image_saved_callback(params: ImageSaveParams):
 

 

 def image_saved_callback(params: ImageSaveParams):

-    for c in callbacks_image_saved:

+    for c in callback_map['callbacks_image_saved']:

         try:

             c.callback(params)

         except Exception:

             report_exception(c, 'image_saved_callback')

 

 

+def cfg_denoiser_callback(params: CFGDenoiserParams):

+    for c in callback_map['callbacks_cfg_denoiser']:

+        try:

+            c.callback(params)

+        except Exception:

+            report_exception(c, 'cfg_denoiser_callback')

+

+

 def add_callback(callbacks, fun):

     stack = [x for x in inspect.stack() if x.filename != __file__]

     filename = stack[0].filename if len(stack) > 0 else 'unknown file'

 

     callbacks.append(ScriptCallback(filename, fun))

 

+    

+def remove_current_script_callbacks():

+    stack = [x for x in inspect.stack() if x.filename != __file__]

+    filename = stack[0].filename if len(stack) > 0 else 'unknown file'

+    if filename == 'unknown file':

+        return

+    for callback_list in callback_map.values():

+        for callback_to_remove in [cb for cb in callback_list if cb.script == filename]:

+            callback_list.remove(callback_to_remove)

+

+

+def remove_callbacks_for_function(callback_func):

+    for callback_list in callback_map.values():

+        for callback_to_remove in [cb for cb in callback_list if cb.callback == callback_func]:

+            callback_list.remove(callback_to_remove)

+

 

 def on_app_started(callback):

     """register a function to be called when the webui started, the gradio `Block` component and

     fastapi `FastAPI` object are passed as the arguments"""

-    add_callback(callbacks_app_started, callback)

+    add_callback(callback_map['callbacks_app_started'], callback)

 

 

 def on_model_loaded(callback):

     """register a function to be called when the stable diffusion model is created; the model is

     passed as an argument"""

-    add_callback(callbacks_model_loaded, callback)

+    add_callback(callback_map['callbacks_model_loaded'], callback)

 

 

 def on_ui_tabs(callback):

@@ -124,13 +166,13 @@ def on_ui_tabs(callback):
     title is tab text displayed to user in the UI

     elem_id is HTML id for the tab

     """

-    add_callback(callbacks_ui_tabs, callback)

+    add_callback(callback_map['callbacks_ui_tabs'], callback)

 

 

 def on_ui_settings(callback):

     """register a function to be called before UI settings are populated; add your settings

     by using shared.opts.add_option(shared.OptionInfo(...)) """

-    add_callback(callbacks_ui_settings, callback)

+    add_callback(callback_map['callbacks_ui_settings'], callback)

 

 

 def on_before_image_saved(callback):

@@ -138,7 +180,7 @@ def on_before_image_saved(callback):
     The callback is called with one argument:

         - params: ImageSaveParams - parameters the image is to be saved with. You can change fields in this object.

     """

-    add_callback(callbacks_before_image_saved, callback)

+    add_callback(callback_map['callbacks_before_image_saved'], callback)

 

 

 def on_image_saved(callback):

@@ -146,4 +188,12 @@ def on_image_saved(callback):
     The callback is called with one argument:

         - params: ImageSaveParams - parameters the image was saved with. Changing fields in this object does nothing.

     """

-    add_callback(callbacks_image_saved, callback)

+    add_callback(callback_map['callbacks_image_saved'], callback)

+

+

+def on_cfg_denoiser(callback):

+    """register a function to be called in the kdiffussion cfg_denoiser method after building the inner model inputs.

+    The callback is called with one argument:

+        - params: CFGDenoiserParams - parameters to be passed to the inner model and sampling state details.

+    """

+    add_callback(callback_map['callbacks_cfg_denoiser'], callback)

diff --git a/modules/scripts.py b/modules/scripts.py
index 533db45c..637b2329 100644
--- a/modules/scripts.py
+++ b/modules/scripts.py
@@ -3,7 +3,6 @@ import sys
 import traceback

 from collections import namedtuple

 

-import modules.ui as ui

 import gradio as gr

 

 from modules.processing import StableDiffusionProcessing

@@ -18,6 +17,9 @@ class Script:
     args_to = None

     alwayson = False

 

+    """A gr.Group component that has all script's UI inside it"""

+    group = None

+

     infotext_fields = None

     """if set in ui(), this is a list of pairs of gradio component + text; the text will be used when

     parsing infotext to set the value for the component; see ui.py's txt2img_paste_fields for an example

@@ -70,6 +72,19 @@ class Script:
 

         pass

 

+    def process_batch(self, p, *args, **kwargs):

+        """

+        Same as process(), but called for every batch.

+

+        **kwargs will have those items:

+          - batch_number - index of current batch, from 0 to number of batches-1

+          - prompts - list of prompts for current batch; you can change contents of this list but changing the number of entries will likely break things

+          - seeds - list of seeds for current batch

+          - subseeds - list of subseeds for current batch

+        """

+

+        pass

+

     def postprocess(self, p, processed, *args):

         """

         This function is called after processing ends for AlwaysVisible scripts.

@@ -218,8 +233,6 @@ class ScriptRunner:
 

             for control in controls:

                 control.custom_script_source = os.path.basename(script.filename)

-                if not script.alwayson:

-                    control.visible = False

 

             if script.infotext_fields is not None:

                 self.infotext_fields += script.infotext_fields

@@ -229,40 +242,41 @@ class ScriptRunner:
             script.args_to = len(inputs)

 

         for script in self.alwayson_scripts:

-            with gr.Group():

+            with gr.Group() as group:

                 create_script_ui(script, inputs, inputs_alwayson)

 

+            script.group = group

+

         dropdown = gr.Dropdown(label="Script", elem_id="script_list", choices=["None"] + self.titles, value="None", type="index")

         dropdown.save_to_config = True

         inputs[0] = dropdown

 

         for script in self.selectable_scripts:

-            create_script_ui(script, inputs, inputs_alwayson)

+            with gr.Group(visible=False) as group:

+                create_script_ui(script, inputs, inputs_alwayson)

+

+            script.group = group

 

         def select_script(script_index):

-            if 0 < script_index <= len(self.selectable_scripts):

-                script = self.selectable_scripts[script_index-1]

-                args_from = script.args_from

-                args_to = script.args_to

-            else:

-                args_from = 0

-                args_to = 0

+            selected_script = self.selectable_scripts[script_index - 1] if script_index>0 else None

 

-            return [ui.gr_show(True if i == 0 else args_from <= i < args_to or is_alwayson) for i, is_alwayson in enumerate(inputs_alwayson)]

+            return [gr.update(visible=selected_script == s) for s in self.selectable_scripts]

 

         def init_field(title):

+            """called when an initial value is set from ui-config.json to show script's UI components"""

+

             if title == 'None':

                 return

+

             script_index = self.titles.index(title)

-            script = self.selectable_scripts[script_index]

-            for i in range(script.args_from, script.args_to):

-                inputs[i].visible = True

+            self.selectable_scripts[script_index].group.visible = True

 

         dropdown.init_field = init_field

+

         dropdown.change(

             fn=select_script,

             inputs=[dropdown],

-            outputs=inputs

+            outputs=[script.group for script in self.selectable_scripts]

         )

 

         return inputs

@@ -294,6 +308,15 @@ class ScriptRunner:
                 print(f"Error running process: {script.filename}", file=sys.stderr)

                 print(traceback.format_exc(), file=sys.stderr)

 

+    def process_batch(self, p, **kwargs):

+        for script in self.alwayson_scripts:

+            try:

+                script_args = p.script_args[script.args_from:script.args_to]

+                script.process_batch(p, *script_args, **kwargs)

+            except Exception:

+                print(f"Error running process_batch: {script.filename}", file=sys.stderr)

+                print(traceback.format_exc(), file=sys.stderr)

+

     def postprocess(self, p, processed):

         for script in self.alwayson_scripts:

             try:

diff --git a/modules/sd_models.py b/modules/sd_models.py
index 90007da3..34c57bfa 100644
--- a/modules/sd_models.py
+++ b/modules/sd_models.py
@@ -9,7 +9,7 @@ from omegaconf import OmegaConf
 

 from ldm.util import instantiate_from_config

 

-from modules import shared, modelloader, devices, script_callbacks

+from modules import shared, modelloader, devices, script_callbacks, sd_vae

 from modules.paths import models_path

 from modules.sd_hijack_inpainting import do_inpainting_hijack, should_hijack_inpainting

 

@@ -159,13 +159,16 @@ def get_state_dict_from_checkpoint(pl_sd):
     return pl_sd

 

 

-vae_ignore_keys = {"model_ema.decay", "model_ema.num_updates"}

-

-

-def load_model_weights(model, checkpoint_info):

+def load_model_weights(model, checkpoint_info, vae_file="auto"):

     checkpoint_file = checkpoint_info.filename

     sd_model_hash = checkpoint_info.hash

 

+    if shared.opts.sd_checkpoint_cache > 0 and hasattr(model, "sd_checkpoint_info"):

+        sd_vae.restore_base_vae(model)

+        checkpoints_loaded[model.sd_checkpoint_info] = model.state_dict().copy()

+

+    vae_file = sd_vae.resolve_vae(checkpoint_file, vae_file=vae_file)

+

     if checkpoint_info not in checkpoints_loaded:

         print(f"Loading weights [{sd_model_hash}] from {checkpoint_file}")

 

@@ -182,37 +185,36 @@ def load_model_weights(model, checkpoint_info):
             model.to(memory_format=torch.channels_last)

 

         if not shared.cmd_opts.no_half:

+            vae = model.first_stage_model

+

+            # with --no-half-vae, remove VAE from model when doing half() to prevent its weights from being converted to float16

+            if shared.cmd_opts.no_half_vae:

+                model.first_stage_model = None

+

             model.half()

+            model.first_stage_model = vae

 

         devices.dtype = torch.float32 if shared.cmd_opts.no_half else torch.float16

         devices.dtype_vae = torch.float32 if shared.cmd_opts.no_half or shared.cmd_opts.no_half_vae else torch.float16

 

-        vae_file = os.path.splitext(checkpoint_file)[0] + ".vae.pt"

-

-        if not os.path.exists(vae_file) and shared.cmd_opts.vae_path is not None:

-            vae_file = shared.cmd_opts.vae_path

-

-        if os.path.exists(vae_file):

-            print(f"Loading VAE weights from: {vae_file}")

-            vae_ckpt = torch.load(vae_file, map_location=shared.weight_load_location)

-            vae_dict = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss" and k not in vae_ignore_keys}

-            model.first_stage_model.load_state_dict(vae_dict)

-

         model.first_stage_model.to(devices.dtype_vae)

 

-        if shared.opts.sd_checkpoint_cache > 0:

-            checkpoints_loaded[checkpoint_info] = model.state_dict().copy()

-            while len(checkpoints_loaded) > shared.opts.sd_checkpoint_cache:

-                checkpoints_loaded.popitem(last=False)  # LRU

     else:

-        print(f"Loading weights [{sd_model_hash}] from cache")

-        checkpoints_loaded.move_to_end(checkpoint_info)

+        vae_name = sd_vae.get_filename(vae_file) if vae_file else None

+        vae_message = f" with {vae_name} VAE" if vae_name else ""

+        print(f"Loading weights [{sd_model_hash}]{vae_message} from cache")

         model.load_state_dict(checkpoints_loaded[checkpoint_info])

 

+    if shared.opts.sd_checkpoint_cache > 0:

+        while len(checkpoints_loaded) > shared.opts.sd_checkpoint_cache:

+            checkpoints_loaded.popitem(last=False)  # LRU

+

     model.sd_model_hash = sd_model_hash

     model.sd_model_checkpoint = checkpoint_file

     model.sd_checkpoint_info = checkpoint_info

 

+    sd_vae.load_vae(model, vae_file)

+

 

 def load_model(checkpoint_info=None):

     from modules import lowvram, sd_hijack

@@ -263,7 +265,7 @@ def load_model(checkpoint_info=None):
 def reload_model_weights(sd_model=None, info=None):

     from modules import lowvram, devices, sd_hijack

     checkpoint_info = info or select_checkpoint()

-

+ 

     if not sd_model:

         sd_model = shared.sd_model

 

diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py
index 8772db56..783992d2 100644
--- a/modules/sd_samplers.py
+++ b/modules/sd_samplers.py
@@ -12,6 +12,7 @@ from modules import prompt_parser, devices, processing, images
 

 from modules.shared import opts, cmd_opts, state

 import modules.shared as shared

+from modules.script_callbacks import CFGDenoiserParams, cfg_denoiser_callback

 

 

 SamplerData = namedtuple('SamplerData', ['name', 'constructor', 'aliases', 'options'])

@@ -23,11 +24,15 @@ samplers_k_diffusion = [
     ('Heun', 'sample_heun', ['k_heun'], {}),

     ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {}),

     ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {}),

+    ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}),

+    ('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}),

     ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {}),

     ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {}),

     ('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}),

     ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras'}),

     ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras'}),

+    ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}),

+    ('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}),

 ]

 

 samplers_data_k_diffusion = [

@@ -92,8 +97,8 @@ def single_sample_to_image(sample):
     return Image.fromarray(x_sample)

 

 

-def sample_to_image(samples):

-    return single_sample_to_image(samples[0])

+def sample_to_image(samples, index=0):

+    return single_sample_to_image(samples[index])

 

 

 def samples_to_image_grid(samples):

@@ -280,6 +285,12 @@ class CFGDenoiser(torch.nn.Module):
         image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])

         sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])

 

+        denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps)

+        cfg_denoiser_callback(denoiser_params)

+        x_in = denoiser_params.x

+        image_cond_in = denoiser_params.image_cond

+        sigma_in = denoiser_params.sigma

+

         if tensor.shape[1] == uncond.shape[1]:

             cond_in = torch.cat([tensor, uncond])

 

diff --git a/modules/sd_vae.py b/modules/sd_vae.py
new file mode 100644
index 00000000..71e7a6e6
--- /dev/null
+++ b/modules/sd_vae.py
@@ -0,0 +1,207 @@
+import torch
+import os
+from collections import namedtuple
+from modules import shared, devices, script_callbacks
+from modules.paths import models_path
+import glob
+
+
+model_dir = "Stable-diffusion"
+model_path = os.path.abspath(os.path.join(models_path, model_dir))
+vae_dir = "VAE"
+vae_path = os.path.abspath(os.path.join(models_path, vae_dir))
+
+
+vae_ignore_keys = {"model_ema.decay", "model_ema.num_updates"}
+
+
+default_vae_dict = {"auto": "auto", "None": "None"}
+default_vae_list = ["auto", "None"]
+
+
+default_vae_values = [default_vae_dict[x] for x in default_vae_list]
+vae_dict = dict(default_vae_dict)
+vae_list = list(default_vae_list)
+first_load = True
+
+
+base_vae = None
+loaded_vae_file = None
+checkpoint_info = None
+
+
+def get_base_vae(model):
+    if base_vae is not None and checkpoint_info == model.sd_checkpoint_info and model:
+        return base_vae
+    return None
+
+
+def store_base_vae(model):
+    global base_vae, checkpoint_info
+    if checkpoint_info != model.sd_checkpoint_info:
+        base_vae = model.first_stage_model.state_dict().copy()
+        checkpoint_info = model.sd_checkpoint_info
+
+
+def delete_base_vae():
+    global base_vae, checkpoint_info
+    base_vae = None
+    checkpoint_info = None
+
+
+def restore_base_vae(model):
+    global base_vae, checkpoint_info
+    if base_vae is not None and checkpoint_info == model.sd_checkpoint_info:
+        load_vae_dict(model, base_vae)
+    delete_base_vae()
+
+
+def get_filename(filepath):
+    return os.path.splitext(os.path.basename(filepath))[0]
+
+
+def refresh_vae_list(vae_path=vae_path, model_path=model_path):
+    global vae_dict, vae_list
+    res = {}
+    candidates = [
+        *glob.iglob(os.path.join(model_path, '**/*.vae.ckpt'), recursive=True),
+        *glob.iglob(os.path.join(model_path, '**/*.vae.pt'), recursive=True),
+        *glob.iglob(os.path.join(vae_path, '**/*.ckpt'), recursive=True),
+        *glob.iglob(os.path.join(vae_path, '**/*.pt'), recursive=True)
+    ]
+    if shared.cmd_opts.vae_path is not None and os.path.isfile(shared.cmd_opts.vae_path):
+        candidates.append(shared.cmd_opts.vae_path)
+    for filepath in candidates:
+        name = get_filename(filepath)
+        res[name] = filepath
+    vae_list.clear()
+    vae_list.extend(default_vae_list)
+    vae_list.extend(list(res.keys()))
+    vae_dict.clear()
+    vae_dict.update(res)
+    vae_dict.update(default_vae_dict)
+    return vae_list
+
+
+def resolve_vae(checkpoint_file, vae_file="auto"):
+    global first_load, vae_dict, vae_list
+
+    # if vae_file argument is provided, it takes priority, but not saved
+    if vae_file and vae_file not in default_vae_list:
+        if not os.path.isfile(vae_file):
+            vae_file = "auto"
+            print("VAE provided as function argument doesn't exist")
+    # for the first load, if vae-path is provided, it takes priority, saved, and failure is reported
+    if first_load and shared.cmd_opts.vae_path is not None:
+        if os.path.isfile(shared.cmd_opts.vae_path):
+            vae_file = shared.cmd_opts.vae_path
+            shared.opts.data['sd_vae'] = get_filename(vae_file)
+        else:
+            print("VAE provided as command line argument doesn't exist")
+    # else, we load from settings
+    if vae_file == "auto" and shared.opts.sd_vae is not None:
+        # if saved VAE settings isn't recognized, fallback to auto
+        vae_file = vae_dict.get(shared.opts.sd_vae, "auto")
+        # if VAE selected but not found, fallback to auto
+        if vae_file not in default_vae_values and not os.path.isfile(vae_file):
+            vae_file = "auto"
+            print("Selected VAE doesn't exist")
+    # vae-path cmd arg takes priority for auto
+    if vae_file == "auto" and shared.cmd_opts.vae_path is not None:
+        if os.path.isfile(shared.cmd_opts.vae_path):
+            vae_file = shared.cmd_opts.vae_path
+            print("Using VAE provided as command line argument")
+    # if still not found, try look for ".vae.pt" beside model
+    model_path = os.path.splitext(checkpoint_file)[0]
+    if vae_file == "auto":
+        vae_file_try = model_path + ".vae.pt"
+        if os.path.isfile(vae_file_try):
+            vae_file = vae_file_try
+            print("Using VAE found beside selected model")
+    # if still not found, try look for ".vae.ckpt" beside model
+    if vae_file == "auto":
+        vae_file_try = model_path + ".vae.ckpt"
+        if os.path.isfile(vae_file_try):
+            vae_file = vae_file_try
+            print("Using VAE found beside selected model")
+    # No more fallbacks for auto
+    if vae_file == "auto":
+        vae_file = None
+    # Last check, just because
+    if vae_file and not os.path.exists(vae_file):
+        vae_file = None
+
+    return vae_file
+
+
+def load_vae(model, vae_file=None):
+    global first_load, vae_dict, vae_list, loaded_vae_file
+    # save_settings = False
+
+    if vae_file:
+        print(f"Loading VAE weights from: {vae_file}")
+        vae_ckpt = torch.load(vae_file, map_location=shared.weight_load_location)
+        vae_dict_1 = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss" and k not in vae_ignore_keys}
+        load_vae_dict(model, vae_dict_1)
+
+        # If vae used is not in dict, update it
+        # It will be removed on refresh though
+        vae_opt = get_filename(vae_file)
+        if vae_opt not in vae_dict:
+            vae_dict[vae_opt] = vae_file
+            vae_list.append(vae_opt)
+
+    loaded_vae_file = vae_file
+
+    """
+    # Save current VAE to VAE settings, maybe? will it work?
+    if save_settings:
+        if vae_file is None:
+            vae_opt = "None"
+
+        # shared.opts.sd_vae = vae_opt
+    """
+
+    first_load = False
+
+
+# don't call this from outside
+def load_vae_dict(model, vae_dict_1=None):
+    if vae_dict_1:
+        store_base_vae(model)
+        model.first_stage_model.load_state_dict(vae_dict_1)
+    else:
+        restore_base_vae()
+    model.first_stage_model.to(devices.dtype_vae)
+
+
+def reload_vae_weights(sd_model=None, vae_file="auto"):
+    from modules import lowvram, devices, sd_hijack
+
+    if not sd_model:
+        sd_model = shared.sd_model
+
+    checkpoint_info = sd_model.sd_checkpoint_info
+    checkpoint_file = checkpoint_info.filename
+    vae_file = resolve_vae(checkpoint_file, vae_file=vae_file)
+
+    if loaded_vae_file == vae_file:
+        return
+
+    if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
+        lowvram.send_everything_to_cpu()
+    else:
+        sd_model.to(devices.cpu)
+
+    sd_hijack.model_hijack.undo_hijack(sd_model)
+
+    load_vae(sd_model, vae_file)
+
+    sd_hijack.model_hijack.hijack(sd_model)
+    script_callbacks.model_loaded_callback(sd_model)
+
+    if not shared.cmd_opts.lowvram and not shared.cmd_opts.medvram:
+        sd_model.to(devices.device)
+
+    print(f"VAE Weights loaded.")
+    return sd_model
diff --git a/modules/shared.py b/modules/shared.py
index 1ccb269a..e8bacd3c 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -4,6 +4,7 @@ import json
 import os

 import sys

 from collections import OrderedDict

+import time

 

 import gradio as gr

 import tqdm

@@ -14,7 +15,7 @@ import modules.memmon
 import modules.sd_models

 import modules.styles

 import modules.devices as devices

-from modules import sd_samplers, sd_models, localization

+from modules import sd_samplers, sd_models, localization, sd_vae

 from modules.hypernetworks import hypernetwork

 from modules.paths import models_path, script_path, sd_path

 

@@ -43,6 +44,7 @@ parser.add_argument("--precision", type=str, help="evaluate at this precision",
 parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site")

 parser.add_argument("--ngrok", type=str, help="ngrok authtoken, alternative to gradio --share", default=None)

 parser.add_argument("--ngrok-region", type=str, help="The region in which ngrok should start.", default="us")

+parser.add_argument("--enable-insecure-extension-access", action='store_true', help="enable extensions tab regardless of other options")

 parser.add_argument("--codeformer-models-path", type=str, help="Path to directory with codeformer model file(s).", default=os.path.join(models_path, 'Codeformer'))

 parser.add_argument("--gfpgan-models-path", type=str, help="Path to directory with GFPGAN model file(s).", default=os.path.join(models_path, 'GFPGAN'))

 parser.add_argument("--esrgan-models-path", type=str, help="Path to directory with ESRGAN model file(s).", default=os.path.join(models_path, 'ESRGAN'))

@@ -84,6 +86,10 @@ parser.add_argument("--nowebui", action='store_true', help="use api=True to laun
 parser.add_argument("--ui-debug-mode", action='store_true', help="Don't load model to quickly launch UI")

 parser.add_argument("--device-id", type=str, help="Select the default CUDA device to use (export CUDA_VISIBLE_DEVICES=0,1,etc might be needed before)", default=None)

 parser.add_argument("--administrator", action='store_true', help="Administrator rights", default=False)

+parser.add_argument("--cors-allow-origins", type=str, help="Allowed CORS origins", default=None)

+parser.add_argument("--tls-keyfile", type=str, help="Partially enables TLS, requires --tls-certfile to fully function", default=None)

+parser.add_argument("--tls-certfile", type=str, help="Partially enables TLS, requires --tls-keyfile to fully function", default=None)

+parser.add_argument("--server-name", type=str, help="Sets hostname of server", default=None)

 

 cmd_opts = parser.parse_args()

 restricted_opts = {

@@ -98,7 +104,7 @@ restricted_opts = {
     "outdir_save",

 }

 

-cmd_opts.disable_extension_access = cmd_opts.share or cmd_opts.listen

+cmd_opts.disable_extension_access = (cmd_opts.share or cmd_opts.listen) and not cmd_opts.enable_insecure_extension_access

 

 devices.device, devices.device_interrogate, devices.device_gfpgan, devices.device_swinir, devices.device_esrgan, devices.device_scunet, devices.device_codeformer = \

 (devices.cpu if any(y in cmd_opts.use_cpu for y in [x, 'all']) else devices.get_optimal_device() for x in ['sd', 'interrogate', 'gfpgan', 'swinir', 'esrgan', 'scunet', 'codeformer'])

@@ -135,6 +141,7 @@ class State:
     current_image = None

     current_image_sampling_step = 0

     textinfo = None

+    time_start = None

     need_restart = False

 

     def skip(self):

@@ -144,6 +151,9 @@ class State:
         self.interrupted = True

 

     def nextjob(self):

+        if opts.show_progress_every_n_steps == -1:

+            self.do_set_current_image()

+

         self.job_no += 1

         self.sampling_step = 0

         self.current_image_sampling_step = 0

@@ -172,6 +182,7 @@ class State:
         self.skipped = False

         self.interrupted = False

         self.textinfo = None

+        self.time_start = time.time()

 

         devices.torch_gc()

 

@@ -181,6 +192,24 @@ class State:
 

         devices.torch_gc()

 

+    """sets self.current_image from self.current_latent if enough sampling steps have been made after the last call to this"""

+    def set_current_image(self):

+        if self.sampling_step - self.current_image_sampling_step >= opts.show_progress_every_n_steps and opts.show_progress_every_n_steps > 0:

+            self.do_set_current_image()

+

+    def do_set_current_image(self):

+        if not parallel_processing_allowed:

+            return

+        if self.current_latent is None:

+            return

+

+        if opts.show_progress_grid:

+            self.current_image = sd_samplers.samples_to_image_grid(self.current_latent)

+        else:

+            self.current_image = sd_samplers.sample_to_image(self.current_latent)

+

+        self.current_image_sampling_step = self.sampling_step

+

 state = State()

 

 artist_db = modules.artists.ArtistsDatabase(os.path.join(script_path, 'artists.csv'))

@@ -192,8 +221,6 @@ interrogator = modules.interrogate.InterrogateModels("interrogate")
 

 face_restorers = []

 

-localization.list_localizations(cmd_opts.localizations_dir)

-

 

 def realesrgan_models_names():

     import modules.realesrgan_model

@@ -238,6 +265,8 @@ options_templates.update(options_section(('saving-images', "Saving images/grids"
     "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"),

     "jpeg_quality": OptionInfo(80, "Quality for saved jpeg images", gr.Slider, {"minimum": 1, "maximum": 100, "step": 1}),

     "export_for_4chan": OptionInfo(True, "If PNG image is larger than 4MB or any dimension is larger than 4000, downscale and save copy as JPG"),

 

@@ -290,6 +319,7 @@ options_templates.update(options_section(('system', "System"), {
 

 options_templates.update(options_section(('training', "Training"), {

     "unload_models_when_training": OptionInfo(False, "Move VAE and CLIP to RAM when training if possible. Saves VRAM."),

+    "save_optimizer_state": OptionInfo(False, "Saves Optimizer state as separate *.optim file. Training can be resumed with HN itself and matching optim file."),

     "dataset_filename_word_regex": OptionInfo("", "Filename word regex"),

     "dataset_filename_join_string": OptionInfo(" ", "Filename join string"),

     "training_image_repeats_per_epoch": OptionInfo(1, "Number of repeats for a single input image per epoch; used only for displaying epoch number", gr.Number, {"precision": 0}),

@@ -300,11 +330,11 @@ options_templates.update(options_section(('training', "Training"), {
 options_templates.update(options_section(('sd', "Stable Diffusion"), {

     "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, refresh=sd_models.list_models),

     "sd_checkpoint_cache": OptionInfo(0, "Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),

+    "sd_vae": OptionInfo("auto", "SD VAE", gr.Dropdown, lambda: {"choices": list(sd_vae.vae_list)}, refresh=sd_vae.refresh_vae_list),

     "sd_hypernetwork": OptionInfo("None", "Hypernetwork", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}, refresh=reload_hypernetworks),

     "sd_hypernetwork_strength": OptionInfo(1.0, "Hypernetwork strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.001}),

     "inpainting_mask_weight": OptionInfo(1.0, "Inpainting conditioning mask strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),

     "img2img_color_correction": OptionInfo(False, "Apply color correction to img2img results to match original colors."),

-    "save_images_before_color_correction": OptionInfo(False, "Save a copy of image before applying color correction to img2img results"),

     "img2img_fix_steps": OptionInfo(False, "With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising)."),

     "enable_quantization": OptionInfo(False, "Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply."),

     "enable_emphasis": OptionInfo(True, "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention"),

@@ -332,7 +362,7 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"),
 

 options_templates.update(options_section(('ui', "User interface"), {

     "show_progressbar": OptionInfo(True, "Show progressbar"),

-    "show_progress_every_n_steps": OptionInfo(0, "Show image creation progress every N sampling steps. Set 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 32, "step": 1}),

+    "show_progress_every_n_steps": OptionInfo(0, "Show image creation progress every N sampling steps. Set to 0 to disable. Set to -1 to show after completion of batch.", gr.Slider, {"minimum": -1, "maximum": 32, "step": 1}),

     "show_progress_grid": OptionInfo(True, "Show previews of all images generated in a batch as a grid"),

     "return_grid": OptionInfo(True, "Show grid in results for web"),

     "do_not_show_images": OptionInfo(False, "Do not show any images in results for web"),

@@ -377,6 +407,16 @@ class Options:
     def __setattr__(self, key, value):

         if self.data is not None:

             if key in self.data or key in self.data_labels:

+                assert not cmd_opts.freeze_settings, "changing settings is disabled"

+

+                info = opts.data_labels.get(key, None)

+                comp_args = info.component_args if info else None

+                if isinstance(comp_args, dict) and comp_args.get('visible', True) is False:

+                    raise RuntimeError(f"not possible to set {key} because it is restricted")

+

+                if cmd_opts.hide_ui_dir_config and key in restricted_opts:

+                    raise RuntimeError(f"not possible to set {key} because it is restricted")

+

                 self.data[key] = value

                 return

 

@@ -393,6 +433,8 @@ class Options:
         return super(Options, self).__getattribute__(item)

 

     def save(self, filename):

+        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)

 

@@ -419,11 +461,12 @@ class Options:
         if bad_settings > 0:

             print(f"The program is likely to not work with bad settings.\nSettings file: {filename}\nEither fix the file, or delete it and restart.", file=sys.stderr)

 

-    def onchange(self, key, func):

+    def onchange(self, key, func, call=True):

         item = self.data_labels.get(key)

         item.onchange = func

 

-        func()

+        if call:

+            func()

 

     def dumpjson(self):

         d = {k: self.data.get(k, self.data_labels.get(k).default) for k in self.data_labels.keys()}

diff --git a/modules/txt2img.py b/modules/txt2img.py
index c9d5a090..8e4e8677 100644
--- a/modules/txt2img.py
+++ b/modules/txt2img.py
@@ -47,6 +47,8 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2:
     if processed is None:

         processed = process_images(p)

 

+    p.close()

+

     shared.total_tqdm.clear()

 

     generation_info_js = processed.js()

diff --git a/modules/ui.py b/modules/ui.py
index 2c15abb7..c946ad59 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -174,9 +174,9 @@ def save_pil_to_file(pil_image, dir=None):
 gr.processing_utils.save_pil_to_file = save_pil_to_file

 

 

-def wrap_gradio_call(func, extra_outputs=None):

+def wrap_gradio_call(func, extra_outputs=None, add_stats=False):

     def f(*args, extra_outputs_array=extra_outputs, **kwargs):

-        run_memmon = opts.memmon_poll_rate > 0 and not shared.mem_mon.disabled

+        run_memmon = opts.memmon_poll_rate > 0 and not shared.mem_mon.disabled and add_stats

         if run_memmon:

             shared.mem_mon.monitor()

         t = time.perf_counter()

@@ -203,11 +203,18 @@ def wrap_gradio_call(func, extra_outputs=None):
 

             res = extra_outputs_array + [f"<div class='error'>{plaintext_to_html(type(e).__name__+': '+str(e))}</div>"]

 

+        shared.state.skipped = False

+        shared.state.interrupted = False

+        shared.state.job_count = 0

+

+        if not add_stats:

+            return tuple(res)

+

         elapsed = time.perf_counter() - t

         elapsed_m = int(elapsed // 60)

         elapsed_s = elapsed % 60

         elapsed_text = f"{elapsed_s:.2f}s"

-        if (elapsed_m > 0):

+        if elapsed_m > 0:

             elapsed_text = f"{elapsed_m}m "+elapsed_text

 

         if run_memmon:

@@ -225,10 +232,6 @@ def wrap_gradio_call(func, extra_outputs=None):
         # last item is always HTML

         res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr>{elapsed_text}</p>{vram_html}</div>"

 

-        shared.state.skipped = False

-        shared.state.interrupted = False

-        shared.state.job_count = 0

-

         return tuple(res)

 

     return f

@@ -276,16 +279,8 @@ def check_progress_call(id_part):
     image = gr_show(False)

     preview_visibility = gr_show(False)

 

-    if opts.show_progress_every_n_steps > 0:

-        if shared.parallel_processing_allowed:

-

-            if shared.state.sampling_step - shared.state.current_image_sampling_step >= opts.show_progress_every_n_steps and shared.state.current_latent is not None:

-                if opts.show_progress_grid:

-                    shared.state.current_image = modules.sd_samplers.samples_to_image_grid(shared.state.current_latent)

-                else:

-                    shared.state.current_image = modules.sd_samplers.sample_to_image(shared.state.current_latent)

-                shared.state.current_image_sampling_step = shared.state.sampling_step

-

+    if opts.show_progress_every_n_steps != 0:

+        shared.state.set_current_image()

         image = shared.state.current_image

 

         if image is None:

@@ -671,6 +666,8 @@ def create_ui(wrap_gradio_gpu_call):
     import modules.img2img

     import modules.txt2img

 

+    reload_javascript()

+

     parameters_copypaste.reset()

 

     with gr.Blocks(analytics_enabled=False) as txt2img_interface:

@@ -1058,9 +1055,11 @@ def create_ui(wrap_gradio_gpu_call):
                         extras_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, placeholder="Leave blank to save images to the default path.")

                         show_extras_results = gr.Checkbox(label='Show result images', value=True)

 

+                submit = gr.Button('Generate', elem_id="extras_generate", variant='primary')

+

                 with gr.Tabs(elem_id="extras_resize_mode"):

                     with gr.TabItem('Scale by'):

-                        upscaling_resize = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Resize", value=2)

+                        upscaling_resize = gr.Slider(minimum=1.0, maximum=8.0, step=0.05, label="Resize", value=4)

                     with gr.TabItem('Scale to'):

                         with gr.Group():

                             with gr.Row():

@@ -1085,8 +1084,6 @@ def create_ui(wrap_gradio_gpu_call):
                 with gr.Group():

                     upscale_before_face_fix = gr.Checkbox(label='Upscale Before Restoring Faces', value=False)

 

-                submit = gr.Button('Generate', elem_id="extras_generate", variant='primary')

-

             result_images, html_info_x, html_info = create_output_panel("extras", opts.outdir_extras_samples)

 

         submit.click(

@@ -1188,8 +1185,8 @@ def create_ui(wrap_gradio_gpu_call):
                     new_hypernetwork_name = gr.Textbox(label="Name")

                     new_hypernetwork_sizes = gr.CheckboxGroup(label="Modules", value=["768", "320", "640", "1280"], choices=["768", "320", "640", "1280"])

                     new_hypernetwork_layer_structure = gr.Textbox("1, 2, 1", label="Enter hypernetwork layer structure", placeholder="1st and last digit must be 1. ex:'1, 2, 1'")

-                    new_hypernetwork_activation_func = gr.Dropdown(value="linear", label="Select activation function of hypernetwork", choices=modules.hypernetworks.ui.keys)

-                    new_hypernetwork_initialization_option = gr.Dropdown(value = "Normal", label="Select Layer weights initialization. relu-like - Kaiming, sigmoid-like - Xavier is recommended", choices=["Normal", "KaimingUniform", "KaimingNormal", "XavierUniform", "XavierNormal"])

+                    new_hypernetwork_activation_func = gr.Dropdown(value="linear", label="Select activation function of hypernetwork. Recommended : Swish / Linear(none)", choices=modules.hypernetworks.ui.keys)

+                    new_hypernetwork_initialization_option = gr.Dropdown(value = "Normal", label="Select Layer weights initialization. Recommended: Kaiming for relu-like, Xavier for sigmoid-like, Normal otherwise", choices=["Normal", "KaimingUniform", "KaimingNormal", "XavierUniform", "XavierNormal"])

                     new_hypernetwork_add_layer_norm = gr.Checkbox(label="Add layer normalization")

                     new_hypernetwork_use_dropout = gr.Checkbox(label="Use dropout")

                     overwrite_old_hypernetwork = gr.Checkbox(value=False, label="Overwrite Old Hypernetwork")

@@ -1442,50 +1439,41 @@ def create_ui(wrap_gradio_gpu_call):
     opts.reorder()

 

     def run_settings(*args):

-        changed = 0

-

-        assert not shared.cmd_opts.freeze_settings, "changing settings is disabled"

+        changed = []

 

         for key, value, comp in zip(opts.data_labels.keys(), args, components):

-            if comp != dummy_component and not opts.same_type(value, opts.data_labels[key].default):

-                return f"Bad value for setting {key}: {value}; expecting {type(opts.data_labels[key].default).__name__}", opts.dumpjson()

+            assert comp == dummy_component or opts.same_type(value, opts.data_labels[key].default), f"Bad value for setting {key}: {value}; expecting {type(opts.data_labels[key].default).__name__}"

 

         for key, value, comp in zip(opts.data_labels.keys(), args, components):

             if comp == dummy_component:

                 continue

 

-            comp_args = opts.data_labels[key].component_args

-            if comp_args and isinstance(comp_args, dict) and comp_args.get('visible') is False:

-                continue

-

-            if cmd_opts.hide_ui_dir_config and key in restricted_opts:

-                continue

-

             oldval = opts.data.get(key, None)

-            opts.data[key] = value

-

+            try:

+                setattr(opts, key, value)

+            except RuntimeError:

+                continue

             if oldval != value:

                 if opts.data_labels[key].onchange is not None:

                     opts.data_labels[key].onchange()

 

-                changed += 1

-

-        opts.save(shared.config_filename)

-

-        return f'{changed} settings changed.', opts.dumpjson()

+                changed.append(key)

+        try:

+            opts.save(shared.config_filename)

+        except RuntimeError:

+            return opts.dumpjson(), f'{len(changed)} settings changed without save: {", ".join(changed)}.'

+        return opts.dumpjson(), f'{len(changed)} settings changed: {", ".join(changed)}.'

 

     def run_settings_single(value, key):

-        assert not shared.cmd_opts.freeze_settings, "changing settings is disabled"

-

         if not opts.same_type(value, opts.data_labels[key].default):

             return gr.update(visible=True), opts.dumpjson()

 

         oldval = opts.data.get(key, None)

-        if cmd_opts.hide_ui_dir_config and key in restricted_opts:

+        try:

+            setattr(opts, key, value)

+        except Exception:

             return gr.update(value=oldval), opts.dumpjson()

 

-        opts.data[key] = value

-

         if oldval != value:

             if opts.data_labels[key].onchange is not None:

                 opts.data_labels[key].onchange()

@@ -1570,8 +1558,7 @@ def create_ui(wrap_gradio_gpu_call):
         reload_script_bodies.click(

             fn=reload_scripts,

             inputs=[],

-            outputs=[],

-            _js='function(){}'

+            outputs=[]

         )

 

         def request_restart():

@@ -1579,11 +1566,10 @@ def create_ui(wrap_gradio_gpu_call):
             shared.state.need_restart = True

 

         restart_gradio.click(

-

             fn=request_restart,

+            _js='restart_reload',

             inputs=[],

             outputs=[],

-            _js='function(){restart_reload()}'

         )

 

         if column is not None:

@@ -1639,9 +1625,9 @@ def create_ui(wrap_gradio_gpu_call):
 

         text_settings = gr.Textbox(elem_id="settings_json", value=lambda: opts.dumpjson(), visible=False)

         settings_submit.click(

-            fn=run_settings,

+            fn=wrap_gradio_call(run_settings, extra_outputs=[gr.update()]),

             inputs=components,

-            outputs=[result, text_settings],

+            outputs=[text_settings, result],

         )

 

         for i, k, item in quicksettings_list:

@@ -1782,4 +1768,3 @@ def load_javascript(raw_response):
 

 

 reload_javascript = partial(load_javascript, gradio.routes.templates.TemplateResponse)

-reload_javascript()

diff --git a/modules/ui_extensions.py b/modules/ui_extensions.py
index ab807722..02ab9643 100644
--- a/modules/ui_extensions.py
+++ b/modules/ui_extensions.py
@@ -86,7 +86,7 @@ def extension_table():
         code += f"""

             <tr>

                 <td><label><input class="gr-check-radio gr-checkbox" name="enable_{html.escape(ext.name)}" type="checkbox" {'checked="checked"' if ext.enabled else ''}>{html.escape(ext.name)}</label></td>

-                <td><a href="{html.escape(ext.remote or '')}">{html.escape(ext.remote or '')}</a></td>

+                <td><a href="{html.escape(ext.remote or '')}" target="_blank">{html.escape(ext.remote or '')}</a></td>

                 <td{' class="extension_status"' if ext.remote is not None else ''}>{ext_status}</td>

             </tr>

     """

@@ -140,13 +140,15 @@ def install_extension_from_url(dirname, url):
         shutil.rmtree(tmpdir, True)

 

 

-def install_extension_from_index(url):

+def install_extension_from_index(url, hide_tags):

     ext_table, message = install_extension_from_url(None, url)

 

-    return refresh_available_extensions_from_data(), ext_table, message

+    code, _ = refresh_available_extensions_from_data(hide_tags)

 

+    return code, ext_table, message

 

-def refresh_available_extensions(url):

+

+def refresh_available_extensions(url, hide_tags):

     global available_extensions

 

     import urllib.request

@@ -155,13 +157,25 @@ def refresh_available_extensions(url):
 

     available_extensions = json.loads(text)

 

-    return url, refresh_available_extensions_from_data(), ''

+    code, tags = refresh_available_extensions_from_data(hide_tags)

+

+    return url, code, gr.CheckboxGroup.update(choices=tags), ''

+

+

+def refresh_available_extensions_for_tags(hide_tags):

+    code, _ = refresh_available_extensions_from_data(hide_tags)

 

+    return code, ''

 

-def refresh_available_extensions_from_data():

+

+def refresh_available_extensions_from_data(hide_tags):

     extlist = available_extensions["extensions"]

     installed_extension_urls = {normalize_git_url(extension.remote): extension.name for extension in extensions.extensions}

 

+    tags = available_extensions.get("tags", {})

+    tags_to_hide = set(hide_tags)

+    hidden = 0

+

     code = f"""<!-- {time.time()} -->

     <table id="available_extensions">

         <thead>

@@ -178,17 +192,24 @@ def refresh_available_extensions_from_data():
         name = ext.get("name", "noname")

         url = ext.get("url", None)

         description = ext.get("description", "")

+        extension_tags = ext.get("tags", [])

 

         if url is None:

             continue

 

+        if len([x for x in extension_tags if x in tags_to_hide]) > 0:

+            hidden += 1

+            continue

+

         existing = installed_extension_urls.get(normalize_git_url(url), None)

 

         install_code = f"""<input onclick="install_extension_from_index(this, '{html.escape(url)}')" type="button" value="{"Install" if not existing else "Installed"}" {"disabled=disabled" if existing else ""} class="gr-button gr-button-lg gr-button-secondary">"""

 

+        tags_text = ", ".join([f"<span class='extension-tag' title='{tags.get(x, '')}'>{x}</span>" for x in extension_tags])

+

         code += f"""

             <tr>

-                <td><a href="{html.escape(url)}">{html.escape(name)}</a></td>

+                <td><a href="{html.escape(url)}" target="_blank">{html.escape(name)}</a><br />{tags_text}</td>

                 <td>{html.escape(description)}</td>

                 <td>{install_code}</td>

             </tr>

@@ -199,7 +220,10 @@ def refresh_available_extensions_from_data():
     </table>

     """

 

-    return code

+    if hidden > 0:

+        code += f"<p>Extension hidden: {hidden}</p>"

+

+    return code, list(tags)

 

 

 def create_ui():

@@ -238,21 +262,30 @@ def create_ui():
                     extension_to_install = gr.Text(elem_id="extension_to_install", visible=False)

                     install_extension_button = gr.Button(elem_id="install_extension_button", visible=False)

 

+                with gr.Row():

+                    hide_tags = gr.CheckboxGroup(value=["ads", "localization"], label="Hide extensions with tags", choices=["script", "ads", "localization"])

+

                 install_result = gr.HTML()

                 available_extensions_table = gr.HTML()

 

                 refresh_available_extensions_button.click(

-                    fn=modules.ui.wrap_gradio_call(refresh_available_extensions, extra_outputs=[gr.update(), gr.update()]),

-                    inputs=[available_extensions_index],

-                    outputs=[available_extensions_index, available_extensions_table, install_result],

+                    fn=modules.ui.wrap_gradio_call(refresh_available_extensions, extra_outputs=[gr.update(), gr.update(), gr.update()]),

+                    inputs=[available_extensions_index, hide_tags],

+                    outputs=[available_extensions_index, available_extensions_table, hide_tags, install_result],

                 )

 

                 install_extension_button.click(

                     fn=modules.ui.wrap_gradio_call(install_extension_from_index, extra_outputs=[gr.update(), gr.update()]),

-                    inputs=[extension_to_install],

+                    inputs=[extension_to_install, hide_tags],

                     outputs=[available_extensions_table, extensions_table, install_result],

                 )

 

+                hide_tags.change(

+                    fn=modules.ui.wrap_gradio_call(refresh_available_extensions_for_tags, extra_outputs=[gr.update()]),

+                    inputs=[hide_tags],

+                    outputs=[available_extensions_table, install_result]

+                )

+

             with gr.TabItem("Install from URL"):

                 install_url = gr.Text(label="URL for extension's git repository")

                 install_dirname = gr.Text(label="Local directory name", placeholder="Leave empty for auto")

diff --git a/modules/upscaler.py b/modules/upscaler.py
index 6ab2fb40..c4e6e6bd 100644
--- a/modules/upscaler.py
+++ b/modules/upscaler.py
@@ -10,6 +10,7 @@ import modules.shared
 from modules import modelloader, shared
 
 LANCZOS = (Image.Resampling.LANCZOS if hasattr(Image, 'Resampling') else Image.LANCZOS)
+NEAREST = (Image.Resampling.NEAREST if hasattr(Image, 'Resampling') else Image.NEAREST)
 from modules.paths import models_path
 
 
@@ -56,10 +57,18 @@ class Upscaler:
         self.scale = scale
         dest_w = img.width * scale
         dest_h = img.height * scale
+
         for i in range(3):
+            shape = (img.width, img.height)
+
+            img = self.do_upscale(img, selected_model)
+
+            if shape == (img.width, img.height):
+                break
+
             if img.width >= dest_w and img.height >= dest_h:
                 break
-            img = self.do_upscale(img, selected_model)
+
         if img.width != dest_w or img.height != dest_h:
             img = img.resize((int(dest_w), int(dest_h)), resample=LANCZOS)
 
@@ -120,3 +129,17 @@ class UpscalerLanczos(Upscaler):
         self.name = "Lanczos"
         self.scalers = [UpscalerData("Lanczos", None, self)]
 
+
+class UpscalerNearest(Upscaler):
+    scalers = []
+
+    def do_upscale(self, img, selected_model=None):
+        return img.resize((int(img.width * self.scale), int(img.height * self.scale)), resample=NEAREST)
+
+    def load_model(self, _):
+        pass
+
+    def __init__(self, dirname=None):
+        super().__init__(False)
+        self.name = "Nearest"
+        self.scalers = [UpscalerData("Nearest", None, self)]
\ No newline at end of file