Merge remote-tracking branch 'upstream/master'

launch.py

@@ -142,7 +142,7 @@ def prepare_enviroment():
 
     stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc")
     taming_transformers_commit_hash = os.environ.get('TAMING_TRANSFORMERS_COMMIT_HASH', "24268930bf1dce879235a7fddd0b2355b84d7ea6")
-    k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "f4e99857772fc3a126ba886aadf795a332774878")
+    k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "60e5042ca0da89c14d1dd59d73883280f8fce991")
     codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
     blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
 

localizations/ko_KR.json

@@ -16,6 +16,7 @@
   "A merger of the two checkpoints will be generated in your": "체크포인트들이 병합된 결과물이 당신의",
   "A value that determines the output of random number generator - if you create an image with same parameters and seed as another image, you'll get the same result": "난수 생성기의 결과물을 지정하는 값 - 동일한 설정값과 동일한 시드를 적용 시, 완전히 똑같은 결과물을 얻게 됩니다.",
   "Action": "작업",
+  "Add a button to convert the prompts used in NovelAI for use in the WebUI. In addition, add a button that allows you to recall a previously used prompt.": "NovelAI에서 사용되는 프롬프트를 WebUI에서 사용할 수 있게 변환하는 버튼을 추가합니다. 덤으로 이전에 사용한 프롬프트를 불러오는 버튼도 추가됩니다.",
   "Add a random artist to the prompt.": "프롬프트에 랜덤한 작가 추가",
   "Add a second progress bar to the console that shows progress for an entire job.": "콘솔에 전체 작업의 진행도를 보여주는 2번째 프로그레스 바 추가하기",
   "Add difference": "차이점 추가",
@@ -24,6 +25,7 @@
   "Add model hash to generation information": "생성 정보에 모델 해시 추가",
   "Add model name to generation information": "생성 정보에 모델 이름 추가",
   "Add number to filename when saving": "이미지를 저장할 때 파일명에 숫자 추가하기",
+  "Adds a tab that lets you preview how CLIP model would tokenize your text.": "CLIP 모델이 텍스트를 어떻게 토큰화할지 미리 보여주는 탭을 추가합니다.",
   "Adds a tab to the webui that allows the user to automatically extract keyframes from video, and manually extract 512x512 crops of those frames for use in model training.": "WebUI에 비디오로부터 자동으로 키프레임을 추출하고, 그 키프레임으로부터 모델 훈련에 사용될 512x512 이미지를 잘라낼 수 있는 탭을 추가합니다.",
   "Aesthetic Gradients": "스타일 그라디언트",
   "Aesthetic Image Scorer": "스타일 이미지 스코어러",
@@ -33,6 +35,7 @@
   "Aesthetic text for imgs": "스타일 텍스트",
   "Aesthetic weight": "스타일 가중치",
   "Allowed categories for random artists selection when using the Roll button": "랜덤 버튼을 눌러 무작위 작가를 선택할 때 허용된 카테고리",
+  "Allows you to include various shortcodes in your prompts. You can pull text from files, set up your own variables, process text through conditional functions, and so much more - it's like wildcards on steroids.": "프롬프트에 다양한 숏코드를 추가할 수 있게 해줍니다. 파일로부터 텍스트 추출, 변수 설정, 조건 함수로 텍스트 처리 등등 - 스테로이드를 맞은 와일드카드라 할 수 있죠.",
   "Always print all generation info to standard output": "기본 아웃풋에 모든 생성 정보 항상 출력하기",
   "Always save all generated image grids": "생성된 이미지 그리드 항상 저장하기",
   "Always save all generated images": "생성된 이미지 항상 저장하기",
@@ -54,6 +57,7 @@
   "Batch Process": "이미지 여러장 처리",
   "Batch size": "배치 크기",
   "behind": "최신 아님",
+  "Booru tag autocompletion": "Booru 태그 자동완성",
   "BSRGAN 4x": "BSRGAN 4x",
   "built with gradio": "gradio로 제작되었습니다",
   "Calculates aesthetic score for generated images using CLIP+MLP Aesthetic Score Predictor based on Chad Scorer": "Chad 스코어러를 기반으로 한 CLIP+MLP 스타일 점수 예측기를 이용해 생성된 이미지의 스타일 점수를 계산합니다.",
@@ -114,6 +118,7 @@
   "Directory for saving images using the Save button": "저장 버튼을 이용해 저장하는 이미지들의 저장 경로",
   "Directory name pattern": "디렉토리명 패턴",
   "directory.": "저장 경로에 저장됩니다.",
+  "Displays autocompletion hints for tags from image booru boards such as Danbooru. Uses local tag CSV files and includes a config for customization.": "Danbooru 같은 이미지 booru 보드의 태그에 대한 자동완성 힌트를 보여줍니다. 로컬 환경에 저장된 CSV 파일을 사용하고 조정 가능한 설정 파일이 포함되어 있습니다.",
   "Do not add watermark to images": "이미지에 워터마크 추가하지 않기",
   "Do not do anything special": "아무것도 하지 않기",
   "Do not save grids consisting of one picture": "이미지가 1개뿐인 그리드는 저장하지 않기",
@@ -317,6 +322,7 @@
   "None": "없음",
   "Nothing": "없음",
   "Nothing found in the image.": "Nothing found in the image.",
+  "novelai-2-local-prompt": "NovelAI 프롬프트 변환기",
   "Number of columns on the page": "각 페이지마다 표시할 가로줄 수",
   "Number of grids in each row": "각 세로줄마다 표시될 그리드 수",
   "number of images to delete consecutively next": "연속적으로 삭제할 이미지 수",
@@ -431,6 +437,7 @@
   "Save images with embedding in PNG chunks": "PNG 청크로 이미지에 임베딩을 포함시켜 저장",
   "Save style": "스타일 저장",
   "Save text information about generation parameters as chunks to png files": "이미지 생성 설정값을 PNG 청크에 텍스트로 저장",
+  "Saves Optimizer state as separate *.optim file. Training can be resumed with HN itself and matching optim file.": "옵티마이저 상태를 별개의 *.optim 파일로 저장하기. 하이퍼네트워크 파일과 일치하는 optim 파일로부터 훈련을 재개할 수 있습니다.",
   "Saving images/grids": "이미지/그리드 저장",
   "Saving to a directory": "디렉토리에 저장",
   "Scale by": "스케일링 배수 지정",
@@ -515,6 +522,7 @@
   "Tile size for ESRGAN upscalers. 0 = no tiling.": "ESRGAN 업스케일러들의 타일 사이즈. 0 = 타일링 없음.",
   "Tiling": "타일링",
   "Time taken:": "소요 시간 : ",
+  "tokenizer": "토크나이저",
   "Torch active/reserved:": "활성화/예약된 Torch 양 : ",
   "Torch active: Peak amount of VRAM used by Torch during generation, excluding cached data.\nTorch reserved: Peak amount of VRAM allocated by Torch, including all active and cached data.\nSys VRAM: Peak amount of VRAM allocation across all applications / total GPU VRAM (peak utilization%).": "활성화된 Torch : 생성 도중 캐시된 데이터를 포함해 사용된 VRAM의 최대량\n예약된 Torch : 활성화되고 캐시된 모든 데이터를 포함해 Torch에게 할당된 VRAM의 최대량\n시스템 VRAM : 모든 어플리케이션에 할당된 VRAM 최대량 / 총 GPU VRAM (최고 이용도%)",
   "Train": "훈련",

modules/api/api.py

@@ -10,6 +10,7 @@ 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
@@ -34,9 +35,21 @@ def setUpscalers(req: dict):
 
 
 def encode_pil_to_base64(image):
-    buffer = io.BytesIO()
+    with io.BytesIO() as output_bytes:
-    image.save(buffer, format="png")
+
-    return base64.b64encode(buffer.getvalue())
+        # 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:
@@ -205,7 +218,7 @@ class Api:
         shared.state.interrupt()
 
         return {}
-        
+
     def get_config(self):
         options = {}
         for key in shared.opts.data.keys():
@@ -214,10 +227,14 @@ class Api:
                 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])
@@ -233,13 +250,13 @@ class Api:
 
     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()]
 
@@ -251,11 +268,11 @@ class Api:
 
     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] 
+            style = shared.prompt_styles.styles[k]
             styleList.append({"name":style[0], "prompt": style[1], "negative_prompr": style[2]})
 
         return styleList

modules/api/models.py

@@ -1,11 +1,11 @@
 import inspect
 from pydantic import BaseModel, Field, create_model
-from typing import Any, Optional, Union
+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, opts, parser
-from typing import List
+from typing import Dict, List
 
 API_NOT_ALLOWED = [
     "self",
@@ -185,22 +185,22 @@ _options = vars(parser)['_option_string_actions']
 for key in _options:
     if(_options[key].dest != 'help'):
         flag = _options[key]
-        _type = str 
+        _type = str
-        if(_options[key].default != None): _type = type(_options[key].default) 
+        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")
+    aliases: List[str] = Field(title="Aliases")
-    options: dict[str, str] = Field(title="Options")
+    options: Dict[str, str] = Field(title="Options")
 
 class UpscalerItem(BaseModel):
     name: str = Field(title="Name")
-    model_name: str | None = Field(title="Model Name")
+    model_name: Optional[str] = Field(title="Model Name")
-    model_path: str | None = Field(title="Path")
+    model_path: Optional[str] = Field(title="Path")
-    model_url: str | None = Field(title="URL")
+    model_url: Optional[str] = Field(title="URL")
 
 class SDModelItem(BaseModel):
     title: str = Field(title="Title")
@@ -211,23 +211,23 @@ class SDModelItem(BaseModel):
 
 class HypernetworkItem(BaseModel):
     name: str = Field(title="Name")
-    path: str | None = Field(title="Path")
+    path: Optional[str] = Field(title="Path")
 
 class FaceRestorerItem(BaseModel):
     name: str = Field(title="Name")
-    cmd_dir: str | None = Field(title="Path")
+    cmd_dir: Optional[str] = Field(title="Path")
 
 class RealesrganItem(BaseModel):
     name: str = Field(title="Name")
-    path: str | None = Field(title="Path")
+    path: Optional[str] = Field(title="Path")
-    scale: int | None = Field(title="Scale")
+    scale: Optional[int] = Field(title="Scale")
 
 class PromptStyleItem(BaseModel):
     name: str = Field(title="Name")
-    prompt: str | None = Field(title="Prompt")
+    prompt: Optional[str] = Field(title="Prompt")
-    negative_prompt: str | None = Field(title="Negative 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")
+    category: str = Field(title="Category")

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)
+            try:
-            self.status = 'unknown'
+                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

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 = {
@@ -142,6 +144,8 @@ class Hypernetwork:
         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] = (
@@ -163,6 +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())
@@ -178,8 +183,15 @@ class Hypernetwork:
         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
@@ -202,6 +214,18 @@ class Hypernetwork:
         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] = (
@@ -219,11 +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
 
 
@@ -358,6 +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)
@@ -404,8 +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
 
@@ -467,7 +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}",
@@ -530,8 +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):

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.

modules/sd_samplers.py

@@ -24,11 +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 = [

modules/shared.py

@@ -86,6 +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 = {
@@ -147,9 +151,9 @@ class State:
         self.interrupted = True
 
     def nextjob(self):
-        if opts.show_progress_every_n_steps == -1: 
+        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
@@ -198,7 +202,7 @@ class State:
             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:
@@ -317,6 +321,7 @@ 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}),
@@ -406,7 +411,8 @@ class Options:
             if key in self.data or key in self.data_labels:
                 assert not cmd_opts.freeze_settings, "changing settings is disabled"
 
-                comp_args = opts.data_labels[key].component_args
+                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")
 

modules/ui.py

@@ -1446,17 +1446,19 @@ def create_ui(wrap_gradio_gpu_call):
                 continue
 
             oldval = opts.data.get(key, None)
-
+            try:
-            setattr(opts, key, value)
+                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
-
+        try:
-        opts.save(shared.config_filename)
+            opts.save(shared.config_filename)
-
+        except RuntimeError:
+            return opts.dumpjson(), f'{changed} settings changed without save.'
         return opts.dumpjson(), f'{changed} settings changed.'
 
     def run_settings_single(value, key):

modules/ui_extensions.py

@@ -188,7 +188,7 @@ def refresh_available_extensions_from_data():
 
         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></td>
                 <td>{html.escape(description)}</td>
                 <td>{install_code}</td>
             </tr>

modules/upscaler.py

@@ -57,10 +57,18 @@ class Upscaler:
         self.scale = scale
         dest_w = img.width * scale
         dest_h = img.height * scale
+
         for i in range(3):
-            if img.width > dest_w and img.height > dest_h:
+            shape = (img.width, img.height)
-                break
+
             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
+
         if img.width != dest_w or img.height != dest_h:
             img = img.resize((int(dest_w), int(dest_h)), resample=LANCZOS)
 

webui.py

@@ -5,6 +5,7 @@ import importlib
 import signal
 import threading
 from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
 from fastapi.middleware.gzip import GZipMiddleware
 
 from modules.paths import script_path
@@ -34,7 +35,7 @@ from modules.shared import cmd_opts
 import modules.hypernetworks.hypernetwork
 
 queue_lock = threading.Lock()
-
+server_name = "0.0.0.0" if cmd_opts.listen else cmd_opts.server_name
 
 def wrap_queued_call(func):
     def f(*args, **kwargs):
@@ -85,6 +86,20 @@ def initialize():
     shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetworks.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)))
     shared.opts.onchange("sd_hypernetwork_strength", modules.hypernetworks.hypernetwork.apply_strength)
 
+    if cmd_opts.tls_keyfile is not None and cmd_opts.tls_keyfile is not None:
+
+        try:
+            if not os.path.exists(cmd_opts.tls_keyfile):
+                print("Invalid path to TLS keyfile given")
+            if not os.path.exists(cmd_opts.tls_certfile):
+                print(f"Invalid path to TLS certfile: '{cmd_opts.tls_certfile}'")
+        except TypeError:
+            cmd_opts.tls_keyfile = cmd_opts.tls_certfile = None
+            print("TLS setup invalid, running webui without TLS")
+        else:
+            print("Running with TLS")
+
+
     # make the program just exit at ctrl+c without waiting for anything
     def sigint_handler(sig, frame):
         print(f'Interrupted with signal {sig} in {frame}')
@@ -93,6 +108,11 @@ def initialize():
     signal.signal(signal.SIGINT, sigint_handler)
 
 
+def setup_cors(app):
+    if cmd_opts.cors_allow_origins:
+        app.add_middleware(CORSMiddleware, allow_origins=cmd_opts.cors_allow_origins.split(','), allow_methods=['*'])
+
+
 def create_api(app):
     from modules.api.api import Api
     api = Api(app, queue_lock)
@@ -114,6 +134,7 @@ def api_only():
     initialize()
 
     app = FastAPI()
+    setup_cors(app)
     app.add_middleware(GZipMiddleware, minimum_size=1000)
     api = create_api(app)
 
@@ -131,8 +152,10 @@ def webui():
 
         app, local_url, share_url = demo.launch(
             share=cmd_opts.share,
-            server_name="0.0.0.0" if cmd_opts.listen else None,
+            server_name=server_name,
             server_port=cmd_opts.port,
+            ssl_keyfile=cmd_opts.tls_keyfile,
+            ssl_certfile=cmd_opts.tls_certfile,
             debug=cmd_opts.gradio_debug,
             auth=[tuple(cred.split(':')) for cred in cmd_opts.gradio_auth.strip('"').split(',')] if cmd_opts.gradio_auth else None,
             inbrowser=cmd_opts.autolaunch,
@@ -147,6 +170,8 @@ def webui():
         # runnnig its code. We disable this here. Suggested by RyotaK.
         app.user_middleware = [x for x in app.user_middleware if x.cls.__name__ != 'CORSMiddleware']
 
+        setup_cors(app)
+
         app.add_middleware(GZipMiddleware, minimum_size=1000)
 
         if launch_api: