Merge branch 'master' of...

Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui into TI_optimizations

.gitignore

@@ -29,3 +29,5 @@ notification.mp3
 /textual_inversion
 .vscode
 /extensions
+/test/stdout.txt
+/test/stderr.txt

launch.py

@@ -128,10 +128,12 @@ def prepare_enviroment():
     blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
 
     sys.argv += shlex.split(commandline_args)
+    test_argv = [x for x in sys.argv if x != '--tests']
 
     sys.argv, skip_torch_cuda_test = extract_arg(sys.argv, '--skip-torch-cuda-test')
     sys.argv, reinstall_xformers = extract_arg(sys.argv, '--reinstall-xformers')
     sys.argv, update_check = extract_arg(sys.argv, '--update-check')
+    sys.argv, run_tests = extract_arg(sys.argv, '--tests')
     xformers = '--xformers' in sys.argv
     deepdanbooru = '--deepdanbooru' in sys.argv
     ngrok = '--ngrok' in sys.argv
@@ -194,6 +196,26 @@ def prepare_enviroment():
         print("Exiting because of --exit argument")
         exit(0)
 
+    if run_tests:
+        tests(test_argv)
+        exit(0)
+
+
+def tests(argv):
+    if "--api" not in argv:
+        argv.append("--api")
+
+    print(f"Launching Web UI in another process for testing with arguments: {' '.join(argv[1:])}")
+
+    with open('test/stdout.txt', "w", encoding="utf8") as stdout, open('test/stderr.txt', "w", encoding="utf8") as stderr:
+        proc = subprocess.Popen([sys.executable, *argv], stdout=stdout, stderr=stderr)
+
+    import test.server_poll
+    test.server_poll.run_tests()
+
+    print(f"Stopping Web UI process with id {proc.pid}")
+    proc.kill()
+
 
 def start_webui():
     print(f"Launching Web UI with arguments: {' '.join(sys.argv[1:])}")

localizations/ar_AR.json

@@ -26,8 +26,21 @@
   "Sampling Steps": "عدد الخطوات",
   "Sampling method": "أسلوب الخطو",
   "Which algorithm to use to produce the image": "Sampler: اسم نظام تحديد طريقة تغيير المسافات بين الخطوات",
+  "Euler a": "Euler a",
   "Euler Ancestral - very creative, each can get a completely different picture depending on step count, setting steps to higher than 30-40 does not help": "Euler Ancestral: طريقة مبدعة يمكن أن تنتج صور مختلفة على حسب عدد الخطوات، لا تتغير بعد 30-40 خطوة",
+  "Euler": "Euler",
+  "LMS": "LMS",
+  "Heun": "Heun",
+  "DPM2": "DPM2",
+  "DPM2 a": "DPM2 a",
+  "DPM fast": "DPM fast",
+  "DPM adaptive": "DPM adaptive",
+  "LMS Karras": "LMS Karras",
+  "DPM2 Karras": "DPM2 Karras",
+  "DPM2 a Karras": "DPM2 a Karras",
+  "DDIM": "DDIM",
   "Denoising Diffusion Implicit Models - best at inpainting": "Denoising Diffusion Implicit Models: الأفضل في الإنتاج الجزئي",
+  "PLMS": "PLMS",
   "Width": "العرض",
   "Height": "الإرتفاع",
   "Restore faces": "تحسين الوجوه",
@@ -58,6 +71,7 @@
   "Resize seed from height": "إرتفاع الممزوج",
   "Make an attempt to produce a picture similar to what would have been produced with same seed at specified resolution": "Seed resize from: حدد دقة صورة الممزوج (0: نفس دقة الإنتاج)",
   "Open for Clip Aesthetic!": "تضمين تجميلي",
+  "▼": "▼",
   "Aesthetic weight": "أثر التضمين",
   "Aesthetic steps": "عدد الخطوات",
   "Aesthetic learning rate": "معدل التعلم",
@@ -79,7 +93,6 @@
   "-": "-",
   "or": "أو",
   "Click to Upload": "انقر للرفع",
-  "Prompts": "قائمة الطلبات",
   "X/Y plot": "مصفوفة عوامل",
   "X type": "العامل الأول",
   "Nothing": "لا شيء",
@@ -92,6 +105,8 @@
   "Checkpoint name": "ملف الأوزان",
   "Hypernetwork": "الشبكة الفائقة",
   "Hypernet str.": "قوة الشبكة الفائقة",
+  "Inpainting conditioning mask strength": "قوة قناع الإنتاج الجزئي",
+  "Only applies to inpainting models. Determines how strongly to mask off the original image for inpainting and img2img. 1.0 means fully masked, which is the default behaviour. 0.0 means a fully unmasked conditioning. Lower values will help preserve the overall composition of the image, but will struggle with large changes.": "حدد مدى صرامة قناع الإنتاج، يصبح القناع شفاف إذا قوته 0 (لا يعمل إلا مع ملفات أوزان الإنتاج الجزئي: inpainting)",
   "Sigma Churn": "العشوائية (Schurn)",
   "Sigma min": "أدنى تشويش (Stmin)",
   "Sigma max": "أقصى تشويش (Stmax)",
@@ -99,6 +114,7 @@
   "Eta": "العامل Eta η",
   "Clip skip": "تخطي آخر طبقات CLIP",
   "Denoising": "المدى",
+  "Cond. Image Mask Weight": "قوة قناع الإنتاج الجزئي",
   "X values": "قيم العامل الأول",
   "Separate values for X axis using commas.": "افصل القيم بفواصل (,) من اليسار إلى اليمين",
   "Y type": "العامل الثاني",
@@ -168,6 +184,12 @@
   "Tile overlap": "تداخل النافذة",
   "For SD upscale, how much overlap in pixels should there be between tiles. Tiles overlap so that when they are merged back into one picture, there is no clearly visible seam.": "المكبر ينظر إلى أجزاء الصورة من خلال نافذة لتكبير المحتوى ثم ينتقل إلى الجزء المجاور، يفضل أن يكون هناك تداخل بين كل رقعة لكي لا يكون هناك اختلاف واضح بينهم",
   "Upscaler": "طريقة التكبير",
+  "Lanczos": "Lanczos",
+  "LDSR": "LDSR",
+  "ScuNET GAN": "ScuNET GAN",
+  "ScuNET PSNR": "ScuNET PSNR",
+  "ESRGAN_4x": "ESRGAN_4x",
+  "SwinIR 4x": "SwinIR 4x",
   "Inpaint": "إنتاج جزئي",
   "Draw mask": "ارسم القناع",
   "Upload mask": "ارفع القناع",
@@ -192,6 +214,7 @@
   "GFPGAN visibility": "أثر GFPGAN (محسن وجوه)",
   "CodeFormer visibility": "أثر CodeFormer (محسن وجوه)",
   "CodeFormer weight (0 = maximum effect, 1 = minimum effect)": "وزن CodeFormer (يزيد التفاصيل على حساب الجودة)",
+  "Upscale Before Restoring Faces": "كبر قبل تحسين الوجوه",
   "Scale to": "دقة محددة",
   "Crop to fit": "قص الأطراف الزائدة إذا لم تتناسب الأبعاد",
   "Batch Process": "حزمة صور",
@@ -199,7 +222,6 @@
   "A directory on the same machine where the server is running.": "مسار مجلد صور موجود في جهاز الخادم",
   "Leave blank to save images to the default path.": "اتركه فارغا لاستخدام المسار الإفتراضي",
   "Show result images": "اعرض الصور الناتجة",
-  "Open output directory": "افتح مجلد المخرجات",
   "PNG Info": "عوامل الصورة",
   "Send to txt2img": "أرسل لنص إلى صورة",
   "Checkpoint Merger": "مزج الأوزان",
@@ -232,7 +254,41 @@
   "Enter hypernetwork layer structure": "ترتيب مضاعفات عرض الطبقات",
   "1st and last digit must be 1. ex:'1, 2, 1'": "المضاعفين الأول والأخير يجب أن يكونا 1، مثال: 1, 2, 1",
   "Select activation function of hypernetwork": "دالة التنشيط",
+  "linear": "linear",
+  "relu": "relu",
+  "leakyrelu": "leakyrelu",
+  "elu": "elu",
+  "swish": "swish",
+  "tanh": "tanh",
+  "sigmoid": "sigmoid",
+  "celu": "celu",
+  "gelu": "gelu",
+  "glu": "glu",
+  "hardshrink": "hardshrink",
+  "hardsigmoid": "hardsigmoid",
+  "hardtanh": "hardtanh",
+  "logsigmoid": "logsigmoid",
+  "logsoftmax": "logsoftmax",
+  "mish": "mish",
+  "prelu": "prelu",
+  "rrelu": "rrelu",
+  "relu6": "relu6",
+  "selu": "selu",
+  "silu": "silu",
+  "softmax": "softmax",
+  "softmax2d": "softmax2d",
+  "softmin": "softmin",
+  "softplus": "softplus",
+  "softshrink": "softshrink",
+  "softsign": "softsign",
+  "tanhshrink": "tanhshrink",
+  "threshold": "threshold",
   "Select Layer weights initialization. relu-like - Kaiming, sigmoid-like - Xavier is recommended": "تهيئة الأوزان (استخدم Kaiming مع relu وأمثالها وXavier مع sigmoid وأمثالها)",
+  "Normal": "Normal",
+  "KaimingUniform": "KaimingUniform",
+  "KaimingNormal": "KaimingNormal",
+  "XavierUniform": "XavierUniform",
+  "XavierNormal": "XavierNormal",
   "Add layer normalization": "أضف تسوية الطبقات (LayerNorm)",
   "Use dropout": "استخدم الإسقاط (Dropout)",
   "Overwrite Old Hypernetwork": "استبدل الشبكة الفائقة القديمة",
@@ -393,6 +449,7 @@
   "Add model hash to generation information": "أضف رمز تهشير (Hash) ملف الأوزان لعوامل الإنتاج",
   "Add model name to generation information": "أضف اسم ملف الأوزان لعوامل الإنتاج",
   "When reading generation parameters from text into UI (from PNG info or pasted text), do not change the selected model/checkpoint.": "لا تغير الأوزان المختارة عند قراءة عوامل الإنتاج من صورة أو من ملف",
+  "Send seed when sending prompt or image to other interface": "عند إرسال صورة أو طلب ألحق البذرة أيضا",
   "Font for image grids that have text": "نوع الخط في جداول الصور التي تحتوي على نصوص",
   "Enable full page image viewer": "اسمح بعرض الصور في وضع ملئ الشاشة",
   "Show images zoomed in by default in full page image viewer": "اعرض الصور مقربة عند استخدام وضع ملئ الشاشة",
@@ -400,6 +457,18 @@
   "Quicksettings list": "قائمة الإعدادات السريعة",
   "List of setting names, separated by commas, for settings that should go to the quick access bar at the top, rather than the usual setting tab. See modules/shared.py for setting names. Requires restarting to apply.": "قائمة مقسمة بفواصل لأسماء الإعدادات التي يجب أن تظهر في الأعلى لتسهيل الوصول إليها، انظر إلى modules/shared.py لمعرفة الأسماء، يتطلب إعادة تشغيل",
   "Localization (requires restart)": "اللغة (تتطلب إعادة تشغيل)",
+  "pt_BR": "البرتغالية",
+  "zh_CN": "الصينية",
+  "ko_KR": "الكورية",
+  "fr_FR": "الفرنسية",
+  "ru_RU": "الروسية",
+  "ar_AR": "العربية",
+  "tr_TR": "التركية",
+  "it_IT": "الإيطالية",
+  "ja_JP": "اليابانية",
+  "de_DE": "الألمانية",
+  "zh_TW": "الصينية (تايوان)",
+  "es_ES": "الإسبانية",
   "Sampler parameters": "عوامل أساليب الخطو",
   "Hide samplers in user interface (requires restart)": "اخف أساليب الخطو التالية (يتطلب إعادة تشغيل)",
   "eta (noise multiplier) for DDIM": "العامل Eta η لأسلوب الخطو DDIM",
@@ -420,5 +489,30 @@
   "Request browser notifications": "اطلب تنبيهات المتصفح",
   "Download localization template": "حمل ملف اللغة",
   "Reload custom script bodies (No ui updates, No restart)": "أعد تحميل الأدوات الخاصة (بدون واجهة المستخدم ولا يحتاج إعادة تشغيل)",
-  "Restart Gradio and Refresh components (Custom Scripts, ui.py, js and css only)": "أعد تشغيل gradio وتحميل الأدوات الخاصة وواجهة المستخدم"
-}
\ No newline at end of file
+  "Restart Gradio and Refresh components (Custom Scripts, ui.py, js and css only)": "أعد تشغيل gradio وتحميل الأدوات الخاصة وواجهة المستخدم",
+  "⤡": "⤡",
+  "⊞": "⊞",
+  "×": "×",
+  "❮": "❮",
+  "❯": "❯",
+  "•": "•",
+  "Label": "Label",
+  "File": "File",
+  "Image": "Image",
+  "Check progress": "Check progress",
+  "Check progress (first)": "Check progress (first)",
+  "Textbox": "Textbox",
+  "Image for img2img": "Image for img2img",
+  "Image for inpainting with mask": "Image for inpainting with mask",
+  "Mask": "Mask",
+  "Mask mode": "Mask mode",
+  "Masking mode": "Masking mode",
+  "Resize mode": "Resize mode",
+  "Prev batch": "Prev batch",
+  "Next batch": "Next batch",
+  "Refresh page": "Refresh page",
+  "Date to": "Date to",
+  "Number": "Number",
+  "set_index": "set_index",
+  "Checkbox": "Checkbox"
+}

localizations/ko_KR.json

@@ -33,10 +33,12 @@
   "Always save all generated images": "생성된 이미지 항상 저장하기",
   "api": "",
   "append": "뒤에 삽입",
+  "Append commas": "쉼표 삽입",
   "Apply color correction to img2img results to match original colors.": "이미지→이미지 결과물이 기존 색상과 일치하도록 색상 보정 적용하기",
   "Apply selected styles to current prompt": "현재 프롬프트에 선택된 스타일 적용",
   "Apply settings": "설정 적용하기",
   "Auto focal point crop": "초점 기준 크롭(자동 감지)",
+  "Autocomplete options": "자동완성 설정",
   "Batch count": "배치 수",
   "Batch from Directory": "저장 경로로부터 여러장 처리",
   "Batch img2img": "이미지→이미지 배치",
@@ -45,6 +47,7 @@
   "BSRGAN 4x": "BSRGAN 4x",
   "built with gradio": "gradio로 제작되었습니다",
   "Cancel generate forever": "반복 생성 취소",
+  "cfg cnt": "CFG 변화 횟수",
   "cfg count": "CFG 변화 횟수",
   "CFG Scale": "CFG 스케일",
   "cfg1 min/max": "CFG1 최소/최대",
@@ -64,6 +67,9 @@
   "CodeFormer weight parameter; 0 = maximum effect; 1 = minimum effect": "CodeFormer 가중치 설정값 (0 = 최대 효과, 1 = 최소 효과)",
   "Collect": "즐겨찾기",
   "Color variation": "색깔 다양성",
+  "Combinations": "조합",
+  "Combinatorial batches": "조합 배치 수",
+  "Combinatorial generation": "조합 생성",
   "copy": "복사",
   "Create a grid where images will have different parameters. Use inputs below to specify which parameters will be shared by columns and rows": "서로 다른 설정값으로 생성된 이미지의 그리드를 만듭니다. 아래의 설정으로 가로/세로에 어떤 설정값을 적용할지 선택하세요.",
   "Create a text file next to every image with generation parameters.": "생성된 이미지마다 생성 설정값을 담은 텍스트 파일 생성하기",
@@ -78,10 +84,12 @@
   "custom fold": "커스텀 경로",
   "Custom Name (Optional)": "병합 모델 이름 (선택사항)",
   "Dataset directory": "데이터셋 경로",
+  "date": "생성 일자",
   "DDIM": "DDIM",
   "Decode CFG scale": "디코딩 CFG 스케일",
   "Decode steps": "디코딩 스텝 수",
   "Delete": "삭제",
+  "delete next": "선택한 이미지부터 시작해서 삭제할 이미지 갯수",
   "Denoising": "디노이징",
   "Denoising Diffusion Implicit Models - best at inpainting": "Denoising Diffusion Implicit Models - 인페이팅에 뛰어남",
   "Denoising strength": "디노이즈 강도",
@@ -108,6 +116,7 @@
   "Draw mask": "마스크 직접 그리기",
   "Drop File Here": "파일을 끌어 놓으세요",
   "Drop Image Here": "이미지를 끌어 놓으세요",
+  "Dropdown": "드롭다운",
   "Embedding": "임베딩",
   "Embedding Learning rate": "임베딩 학습률",
   "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention": "강조 : (텍스트)를 이용해 모델의 텍스트에 대한 가중치를 더 강하게 주고 [텍스트]를 이용해 더 약하게 줍니다.",
@@ -134,7 +143,7 @@
   "Face restoration": "얼굴 보정",
   "Face restoration model": "얼굴 보정 모델",
   "Fall-off exponent (lower=higher detail)": "감쇠 지수 (낮을수록 디테일이 올라감)",
-  "favorites": "즐겨찾기",
+  "Favorites": "즐겨찾기",
   "File": "파일",
   "File format for grids": "그리드 이미지 파일 형식",
   "File format for images": "이미지 파일 형식",
@@ -150,6 +159,7 @@
   "First Page": "처음 페이지",
   "Firstpass height": "초기 세로길이",
   "Firstpass width": "초기 가로길이",
+  "Fixed seed": "시드 고정",
   "Focal point edges weight": "경계면 가중치",
   "Focal point entropy weight": "엔트로피 가중치",
   "Focal point face weight": "얼굴 가중치",
@@ -186,6 +196,7 @@
   "Image Browser": "이미지 브라우저",
   "Image for img2img": "Image for img2img",
   "Image for inpainting with mask": "마스크로 인페인팅할 이미지",
+  "Image not found (may have been already moved)": "이미지를 찾을 수 없습니다 (이미 옮겨졌을 수 있음)",
   "Images Browser": "이미지 브라우저",
   "Images directory": "이미지 경로",
   "Images filename pattern": "이미지 파일명 패턴",
@@ -202,6 +213,7 @@
   "Inpaint at full resolution padding, pixels": "전체 해상도로 인페인트시 패딩값(픽셀 단위)",
   "Inpaint masked": "마스크만 처리",
   "Inpaint not masked": "마스크 이외만 처리",
+  "Inpainting conditioning mask strength": "인페인팅 조절 마스크 강도",
   "Input directory": "인풋 이미지 경로",
   "Input images directory": "이미지 경로 입력",
   "Interpolation Method": "보간 방법",
@@ -218,9 +230,11 @@
   "Interrogate: use artists from artists.csv": "분석 : artists.csv의 작가들 사용하기",
   "Interrupt": "중단",
   "Is negative text": "네거티브 텍스트일시 체크",
+  "Iterate seed every line": "줄마다 시드 반복하기",
   "Just resize": "리사이징",
   "Keep -1 for seeds": "시드값 -1로 유지",
   "keep whatever was there originally": "이미지 원본 유지",
+  "keyword": "프롬프트",
   "Label": "라벨",
   "Lanczos": "Lanczos",
   "Last prompt:": "마지막 프롬프트 : ",
@@ -234,6 +248,7 @@
   "Leave blank to save images to the default path.": "기존 저장 경로에 이미지들을 저장하려면 비워두세요.",
   "left": "왼쪽",
   "linear": "linear",
+  "List of prompt inputs": "프롬프트 입력 리스트",
   "List of setting names, separated by commas, for settings that should go to the quick access bar at the top, rather than the usual setting tab. See modules/shared.py for setting names. Requires restarting to apply.": "설정 탭이 아니라 상단의 빠른 설정 바에 위치시킬 설정 이름을 쉼표로 분리해서 입력하십시오. 설정 이름은 modules/shared.py에서 찾을 수 있습니다. 재시작이 필요합니다.",
   "LMS": "LMS",
   "LMS Karras": "LMS Karras",
@@ -244,6 +259,7 @@
   "Loopback": "루프백",
   "Loops": "루프 수",
   "Loss:": "손실(Loss) : ",
+  "Magic prompt": "매직 프롬프트",
   "Make an attempt to produce a picture similar to what would have been produced with same seed at specified resolution": "동일한 시드 값으로 생성되었을 이미지를 주어진 해상도로 최대한 유사하게 재현합니다.",
   "Make K-diffusion samplers produce same images in a batch as when making a single image": "K-diffusion 샘플러들이 단일 이미지를 생성하는 것처럼 배치에서도 동일한 이미지를 생성하게 하기",
   "Make Zip when Save?": "저장 시 Zip 생성하기",
@@ -257,11 +273,13 @@
   "Minimum number of pages per load": "한번 불러올 때마다 불러올 최소 페이지 수",
   "Modules": "모듈",
   "Move face restoration model from VRAM into RAM after processing": "처리가 완료되면 얼굴 보정 모델을 VRAM에서 RAM으로 옮기기",
+  "Move to favorites": "즐겨찾기로 옮기기",
   "Move VAE and CLIP to RAM when training hypernetwork. Saves VRAM.": "하이퍼네트워크 훈련 진행 시 VAE와 CLIP을 RAM으로 옮기기. VRAM이 절약됩니다.",
+  "Moved to favorites": "즐겨찾기로 옮겨짐",
   "Multiplier (M) - set to 0 to get model A": "배율 (M) - 0으로 적용하면 모델 A를 얻게 됩니다",
   "Name": "이름",
   "Negative prompt": "네거티브 프롬프트",
-  "Negative prompt (press Ctrl+Enter or Alt+Enter to generate)": "네거티브 프롬프트 입력(Ctrl+Enter나 Alt+Enter로 생성 시작)",
+  "Negative prompt (press Ctrl+Enter or Alt+Enter to generate)": "네거티브 프롬프트(Prompt) 입력(Ctrl+Enter나 Alt+Enter로 생성 시작)",
   "Next batch": "다음 묶음",
   "Next Page": "다음 페이지",
   "None": "없음",
@@ -274,6 +292,7 @@
   "Number of repeats for a single input image per epoch; used only for displaying epoch number": "세대(Epoch)당 단일 인풋 이미지의 반복 횟수 - 세대(Epoch) 숫자를 표시하는 데에만 사용됩니다. ",
   "Number of rows on the page": "각 페이지마다 표시할 세로줄 수",
   "Number of vectors per token": "토큰별 벡터 수",
+  "Only applies to inpainting models. Determines how strongly to mask off the original image for inpainting and img2img. 1.0 means fully masked, which is the default behaviour. 0.0 means a fully unmasked conditioning. Lower values will help preserve the overall composition of the image, but will struggle with large changes.": "인페인팅 모델에만 적용됩니다. 인페인팅과 이미지→이미지에서 원본 이미지를 얼마나 마스킹 처리할지 결정하는 값입니다. 1.0은 완전히 마스킹함(기본 설정)을 의미하고, 0.0은 완전히 언마스킹된 이미지를 의미합니다. 낮은 값일수록 이미지의 전체적인 구성을 유지하는 데에 도움되겠지만, 변화량이 많을수록 불안정해집니다.",
   "Open for Clip Aesthetic!": "클립 스타일 기능을 활성화하려면 클릭!",
   "Open images output directory": "이미지 저장 경로 열기",
   "Open output directory": "저장 경로 열기",
@@ -281,6 +300,7 @@
   "original": "원본 유지",
   "Original negative prompt": "기존 네거티브 프롬프트",
   "Original prompt": "기존 프롬프트",
+  "Others": "기타",
   "Outpainting direction": "아웃페인팅 방향",
   "Outpainting mk2": "아웃페인팅 마크 2",
   "Output directory": "이미지 저장 경로",
@@ -299,6 +319,7 @@
   "Overwrite Old Hypernetwork": "기존 하이퍼네트워크 덮어쓰기",
   "Page Index": "페이지 인덱스",
   "parameters": "설정값",
+  "path name": "경로 이름",
   "Path to directory where to write outputs": "결과물을 출력할 경로",
   "Path to directory with input images": "인풋 이미지가 있는 경로",
   "Paths for saving": "저장 경로",
@@ -319,7 +340,7 @@
   "Process images in a directory on the same machine where the server is running.": "WebUI 서버가 돌아가고 있는 디바이스에 존재하는 디렉토리의 이미지들을 처리합니다.",
   "Produce an image that can be tiled.": "타일링 가능한 이미지를 생성합니다.",
   "Prompt": "프롬프트",
-  "Prompt (press Ctrl+Enter or Alt+Enter to generate)": "프롬프트 입력(Ctrl+Enter나 Alt+Enter로 생성 시작)",
+  "Prompt (press Ctrl+Enter or Alt+Enter to generate)": "프롬프트(Prompt) 입력(Ctrl+Enter나 Alt+Enter로 생성 시작)",
   "Prompt matrix": "프롬프트 매트릭스",
   "Prompt order": "프롬프트 순서",
   "Prompt S/R": "프롬프트 스타일 변경",
@@ -388,6 +409,7 @@
   "Select activation function of hypernetwork": "하이퍼네트워크 활성화 함수 선택",
   "Select Layer weights initialization. relu-like - Kaiming, sigmoid-like - Xavier is recommended": "레이어 가중치 초기화 방식 선택 - relu류 : Kaiming 추천, sigmoid류 : Xavier 추천",
   "Select which Real-ESRGAN models to show in the web UI. (Requires restart)": "WebUI에 표시할 Real-ESRGAN 모델을 선택하십시오. (재시작 필요)",
+  "Send seed when sending prompt or image to other interface": "다른 화면으로 프롬프트나 이미지를 보낼 때 시드도 함께 보내기",
   "Send to extras": "부가기능으로 전송",
   "Send to img2img": "이미지→이미지로 전송",
   "Send to inpaint": "인페인트로 전송",
@@ -419,6 +441,7 @@
   "Skip": "건너뛰기",
   "Slerp angle": "구면 선형 보간 각도",
   "Slerp interpolation": "구면 선형 보간",
+  "sort by": "정렬 기준",
   "Source": "원본",
   "Source directory": "원본 경로",
   "Split image overlap ratio": "이미지 분할 겹침 비율",
@@ -426,6 +449,7 @@
   "Split oversized images": "사이즈가 큰 이미지 분할하기",
   "Stable Diffusion": "Stable Diffusion",
   "Stable Diffusion checkpoint": "Stable Diffusion 체크포인트",
+  "step cnt": "스텝 변화 횟수",
   "step count": "스텝 변화 횟수",
   "step1 min/max": "스텝1 최소/최대",
   "step2 min/max": "스텝2 최소/최대",
@@ -464,6 +488,8 @@
   "uniform": "uniform",
   "up": "위쪽",
   "Upload mask": "마스크 업로드하기",
+  "Upload prompt inputs": "입력할 프롬프트를 업로드하십시오",
+  "Upscale Before Restoring Faces": "얼굴 보정을 진행하기 전에 업스케일링 먼저 진행하기",
   "Upscale latent space image when doing hires. fix": "고해상도 보정 사용시 잠재 공간 이미지 업스케일하기",
   "Upscale masked region to target resolution, do inpainting, downscale back and paste into original image": "마스크된 부분을 설정된 해상도로 업스케일하고, 인페인팅을 진행한 뒤, 다시 다운스케일 후 원본 이미지에 붙여넣습니다.",
   "Upscaler": "업스케일러",

modules/api/api.py

+import time
 import uvicorn
 from gradio.processing_utils import encode_pil_to_base64, decode_base64_to_file, decode_base64_to_image
-from fastapi import APIRouter, HTTPException
+from fastapi import APIRouter, Depends, 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
 
+
 def upscaler_to_index(name: str):
     try:
         return [x.name.lower() for x in shared.sd_upscalers].index(name.lower())
     except:
         raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be on of these: {' , '.join([x.name for x in sd_upscalers])}")
 
+
 sampler_to_index = lambda name: next(filter(lambda row: name.lower() == row[1].name.lower(), enumerate(all_samplers)), None)
 
+
 def setUpscalers(req: dict):
     reqDict = vars(req)
     reqDict['extras_upscaler_1'] = upscaler_to_index(req.upscaler_1)
@@ -23,6 +28,7 @@ def setUpscalers(req: dict):
     reqDict.pop('upscaler_2')
     return reqDict
 
+
 class Api:
     def __init__(self, app, queue_lock):
         self.router = APIRouter()
@@ -33,15 +39,16 @@ class Api:
         self.app.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=ExtrasSingleImageResponse)
         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)
 
     def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI):
         sampler_index = sampler_to_index(txt2imgreq.sampler_index)
-        
+
         if sampler_index is None:
-            raise HTTPException(status_code=404, detail="Sampler not found") 
-        
+            raise HTTPException(status_code=404, detail="Sampler not found")
+
         populate = txt2imgreq.copy(update={ # Override __init__ params
-            "sd_model": shared.sd_model, 
+            "sd_model": shared.sd_model,
             "sampler_index": sampler_index[0],
             "do_not_save_samples": True,
             "do_not_save_grid": True
@@ -49,34 +56,39 @@ class Api:
         )
         p = StableDiffusionProcessingTxt2Img(**vars(populate))
         # Override object param
+
+        shared.state.begin()
+
         with self.queue_lock:
             processed = process_images(p)
-        
+
+        shared.state.end()
+
         b64images = list(map(encode_pil_to_base64, processed.images))
-        
+
         return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js())
 
     def img2imgapi(self, img2imgreq: StableDiffusionImg2ImgProcessingAPI):
         sampler_index = sampler_to_index(img2imgreq.sampler_index)
-        
+
         if sampler_index is None:
-            raise HTTPException(status_code=404, detail="Sampler not found") 
+            raise HTTPException(status_code=404, detail="Sampler not found")
 
 
         init_images = img2imgreq.init_images
         if init_images is None:
-            raise HTTPException(status_code=404, detail="Init image not found") 
+            raise HTTPException(status_code=404, detail="Init image not found")
 
         mask = img2imgreq.mask
         if mask:
             mask = decode_base64_to_image(mask)
 
-        
+
         populate = img2imgreq.copy(update={ # Override __init__ params
-            "sd_model": shared.sd_model, 
+            "sd_model": shared.sd_model,
             "sampler_index": sampler_index[0],
             "do_not_save_samples": True,
-            "do_not_save_grid": True, 
+            "do_not_save_grid": True,
             "mask": mask
             }
         )
@@ -88,16 +100,20 @@ class Api:
             imgs = [img] * p.batch_size
 
         p.init_images = imgs
-        # Override object param
+
+        shared.state.begin()
+
         with self.queue_lock:
             processed = process_images(p)
-        
+
+        shared.state.end()
+
         b64images = list(map(encode_pil_to_base64, processed.images))
 
         if (not img2imgreq.include_init_images):
             img2imgreq.init_images = None
             img2imgreq.mask = None
-       
+
         return ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js())
 
     def extras_single_image_api(self, req: ExtrasSingleImageRequest):
@@ -125,7 +141,7 @@ class Api:
             result = run_extras(extras_mode=1, image="", input_dir="", output_dir="", **reqDict)
 
         return ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1])
-    
+
     def pnginfoapi(self, req: PNGInfoRequest):
         if(not req.image.strip()):
             return PNGInfoResponse(info="")
@@ -134,6 +150,32 @@ class Api:
 
         return PNGInfoResponse(info=result[1])
 
+    def progressapi(self, req: ProgressRequest = Depends()):
+        # copy from check_progress_call of ui.py
+
+        if shared.state.job_count == 0:
+            return ProgressResponse(progress=0, eta_relative=0, state=shared.state.dict())
+
+        # avoid dividing zero
+        progress = 0.01
+
+        if shared.state.job_count > 0:
+            progress += shared.state.job_no / shared.state.job_count
+        if shared.state.sampling_steps > 0:
+            progress += 1 / shared.state.job_count * shared.state.sampling_step / shared.state.sampling_steps
+
+        time_since_start = time.time() - shared.state.time_start
+        eta = (time_since_start/progress)
+        eta_relative = eta-time_since_start
+
+        progress = min(progress, 1)
+
+        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 launch(self, server_name, port):
         self.app.include_router(self.router)
         uvicorn.run(self.app, host=server_name, port=port)

modules/api/models.py

@@ -52,17 +52,17 @@ class PydanticModelGenerator:
             # field_type = str if not overrides.get(k) else overrides[k]["type"]
             # print(k, v.annotation, v.default)
             field_type = v.annotation
-            
+
             return Optional[field_type]
-        
+
         def merge_class_params(class_):
             all_classes = list(filter(lambda x: x is not object, inspect.getmro(class_)))
             parameters = {}
             for classes in all_classes:
                 parameters = {**parameters, **inspect.signature(classes.__init__).parameters}
             return parameters
-            
-                
+
+
         self._model_name = model_name
         self._class_data = merge_class_params(class_instance)
         self._model_def = [
@@ -74,11 +74,11 @@ class PydanticModelGenerator:
             )
             for (k,v) in self._class_data.items() if k not in API_NOT_ALLOWED
         ]
-        
+
         for fields in additional_fields:
             self._model_def.append(ModelDef(
-                field=underscore(fields["key"]), 
-                field_alias=fields["key"], 
+                field=underscore(fields["key"]),
+                field_alias=fields["key"],
                 field_type=fields["type"],
                 field_value=fields["default"],
                 field_exclude=fields["exclude"] if "exclude" in fields else False))
@@ -95,15 +95,15 @@ class PydanticModelGenerator:
         DynamicModel.__config__.allow_population_by_field_name = True
         DynamicModel.__config__.allow_mutation = True
         return DynamicModel
-    
+
 StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
-    "StableDiffusionProcessingTxt2Img", 
+    "StableDiffusionProcessingTxt2Img",
     StableDiffusionProcessingTxt2Img,
     [{"key": "sampler_index", "type": str, "default": "Euler"}]
 ).generate_model()
 
 StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
-    "StableDiffusionProcessingImg2Img", 
+    "StableDiffusionProcessingImg2Img",
     StableDiffusionProcessingImg2Img,
     [{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "init_images", "type": list, "default": None}, {"key": "denoising_strength", "type": float, "default": 0.75}, {"key": "mask", "type": str, "default": None}, {"key": "include_init_images", "type": bool, "default": False, "exclude" : True}]
 ).generate_model()
@@ -155,4 +155,13 @@ class PNGInfoRequest(BaseModel):
     image: str = Field(title="Image", description="The base64 encoded PNG image")
 
 class PNGInfoResponse(BaseModel):
-    info: str = Field(title="Image info", description="A string with all the info the image had")
\ No newline at end of file
+    info: str = Field(title="Image info", description="A string with all the info the image had")
+
+class ProgressRequest(BaseModel):
+    skip_current_image: bool = Field(default=False, title="Skip current image", description="Skip current image serialization")
+
+class ProgressResponse(BaseModel):
+    progress: float = Field(title="Progress", description="The progress with a range of 0 to 1")
+    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.")

modules/generation_parameters_copypaste.py

@@ -66,6 +66,7 @@ def integrate_settings_paste_fields(component_dict):
 
     settings_map = {
         'sd_hypernetwork': 'Hypernet',
+        'sd_hypernetwork_strength': 'Hypernet strength',
         'CLIP_stop_at_last_layers': 'Clip skip',
         'sd_model_checkpoint': 'Model hash',
     }

modules/hypernetworks/hypernetwork.py

@@ -209,13 +209,16 @@ def list_hypernetworks(path):
     res = {}
     for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True):
         name = os.path.splitext(os.path.basename(filename))[0]
-        res[name] = filename
+        # Prevent a hypothetical "None.pt" from being listed.
+        if name != "None":
+            res[name] = filename
     return res
 
 
 def load_hypernetwork(filename):
     path = shared.hypernetworks.get(filename, None)
-    if path is not None:
+    # Prevent any file named "None.pt" from being loaded.
+    if path is not None and filename != "None":
         print(f"Loading hypernetwork {filename}")
         try:
             shared.loaded_hypernetwork = Hypernetwork()
@@ -332,7 +335,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
     # images allows training previews to have infotext. Importing it at the top causes a circular import problem.
     from modules import images
 
-    assert hypernetwork_name, 'hypernetwork not selected'
+    save_hypernetwork_every = save_hypernetwork_every or 0
+    create_image_every = create_image_every or 0
+    textual_inversion.validate_train_inputs(hypernetwork_name, learn_rate, batch_size, data_root, template_file, steps, save_hypernetwork_every, create_image_every, log_directory, name="hypernetwork")
 
     path = shared.hypernetworks.get(hypernetwork_name, None)
     shared.loaded_hypernetwork = Hypernetwork()
@@ -358,39 +363,44 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
     else:
         images_dir = None
 
+    hypernetwork = shared.loaded_hypernetwork
+    checkpoint = sd_models.select_checkpoint()
+
+    ititial_step = hypernetwork.step or 0
+    if ititial_step >= steps:
+        shared.state.textinfo = f"Model has already been trained beyond specified max steps"
+        return hypernetwork, filename
+
+    scheduler = LearnRateScheduler(learn_rate, steps, ititial_step)
+    
+    # dataset loading may take a while, so input validations and early returns should be done before this
     shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
     with torch.autocast("cuda"):
         ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file, include_cond=True, batch_size=batch_size)
+
     if unload:
         shared.sd_model.cond_stage_model.to(devices.cpu)
         shared.sd_model.first_stage_model.to(devices.cpu)
 
-    hypernetwork = shared.loaded_hypernetwork
-    weights = hypernetwork.weights()
-    for weight in weights:
-        weight.requires_grad = True
-
     size = len(ds.indexes)
     loss_dict = defaultdict(lambda : deque(maxlen = 1024))
     losses = torch.zeros((size,))
     previous_mean_losses = [0]
     previous_mean_loss = 0
     print("Mean loss of {} elements".format(size))
-
-    last_saved_file = "<none>"
-    last_saved_image = "<none>"
-    forced_filename = "<none>"
-
-    ititial_step = hypernetwork.step or 0
-    if ititial_step > steps:
-        return hypernetwork, filename
-
-    scheduler = LearnRateScheduler(learn_rate, steps, ititial_step)
+    
+    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)
 
     steps_without_grad = 0
 
+    last_saved_file = "<none>"
+    last_saved_image = "<none>"
+    forced_filename = "<none>"
+
     pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step)
     for i, entries in pbar:
         hypernetwork.step = i + ititial_step
@@ -443,9 +453,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
 
         if hypernetwork_dir is not None and steps_done % save_hypernetwork_every == 0:
             # Before saving, change name to match current checkpoint.
-            hypernetwork.name = f'{hypernetwork_name}-{steps_done}'
-            last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork.name}.pt')
-            hypernetwork.save(last_saved_file)
+            hypernetwork_name_every = f'{hypernetwork_name}-{steps_done}'
+            last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork_name_every}.pt')
+            save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, last_saved_file)
 
         textual_inversion.write_loss(log_directory, "hypernetwork_loss.csv", hypernetwork.step, len(ds), {
             "loss": f"{previous_mean_loss:.7f}",
@@ -506,13 +516,23 @@ Last saved image: {html.escape(last_saved_image)}<br/>
 """
         
     report_statistics(loss_dict)
-    checkpoint = sd_models.select_checkpoint()
 
-    hypernetwork.sd_checkpoint = checkpoint.hash
-    hypernetwork.sd_checkpoint_name = checkpoint.model_name
-    # Before saving for the last time, change name back to the base name (as opposed to the save_hypernetwork_every step-suffixed naming convention).
-    hypernetwork.name = hypernetwork_name
-    filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork.name}.pt')
-    hypernetwork.save(filename)
+    filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork_name}.pt')
+    save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, filename)
 
     return hypernetwork, filename
+
+def save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, filename):
+    old_hypernetwork_name = hypernetwork.name
+    old_sd_checkpoint = hypernetwork.sd_checkpoint if hasattr(hypernetwork, "sd_checkpoint") else None
+    old_sd_checkpoint_name = hypernetwork.sd_checkpoint_name if hasattr(hypernetwork, "sd_checkpoint_name") else None
+    try:
+        hypernetwork.sd_checkpoint = checkpoint.hash
+        hypernetwork.sd_checkpoint_name = checkpoint.model_name
+        hypernetwork.name = hypernetwork_name
+        hypernetwork.save(filename)
+    except:
+        hypernetwork.sd_checkpoint = old_sd_checkpoint
+        hypernetwork.sd_checkpoint_name = old_sd_checkpoint_name
+        hypernetwork.name = old_hypernetwork_name
+        raise

modules/processing.py

@@ -396,6 +396,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration
         "Model hash": getattr(p, 'sd_model_hash', None if not opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash),
         "Model": (None if not opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', '')),
         "Hypernet": (None if shared.loaded_hypernetwork is None else shared.loaded_hypernetwork.name),
+        "Hypernet strength": (None if shared.loaded_hypernetwork is None or shared.opts.sd_hypernetwork_strength >= 1 else shared.opts.sd_hypernetwork_strength),
         "Batch size": (None if p.batch_size < 2 else p.batch_size),
         "Batch pos": (None if p.batch_size < 2 else position_in_batch),
         "Variation seed": (None if p.subseed_strength == 0 else all_subseeds[index]),
@@ -686,15 +687,12 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         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()
 
-        image_conditioning = self.img2img_image_conditioning(
-            decoded_samples, 
-            samples, 
-            decoded_samples.new_ones(decoded_samples.shape[0], 1, decoded_samples.shape[2], decoded_samples.shape[3])
-        )
         samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps, image_conditioning=image_conditioning)
 
         return samples

modules/shared.py

@@ -144,9 +144,38 @@ class State:
         self.sampling_step = 0
         self.current_image_sampling_step = 0
 
-    def get_job_timestamp(self):
-        return datetime.datetime.now().strftime("%Y%m%d%H%M%S")  # shouldn't this return job_timestamp?
+    def dict(self):
+        obj = {
+            "skipped": self.skipped,
+            "interrupted": self.skipped,
+            "job": self.job,
+            "job_count": self.job_count,
+            "job_no": self.job_no,
+            "sampling_step": self.sampling_step,
+            "sampling_steps": self.sampling_steps,
+        }
+
+        return obj
+
+    def begin(self):
+        self.sampling_step = 0
+        self.job_count = -1
+        self.job_no = 0
+        self.job_timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
+        self.current_latent = None
+        self.current_image = None
+        self.current_image_sampling_step = 0
+        self.skipped = False
+        self.interrupted = False
+        self.textinfo = None
+
+        devices.torch_gc()
+
+    def end(self):
+        self.job = ""
+        self.job_count = 0
 
+        devices.torch_gc()
 
 state = State()
 

modules/textual_inversion/dataset.py

@@ -42,6 +42,8 @@ class PersonalizedBase(Dataset):
         self.lines = lines
 
         assert data_root, 'dataset directory not specified'
+        assert os.path.isdir(data_root), "Dataset directory doesn't exist"
+        assert os.listdir(data_root), "Dataset directory is empty"
 
         cond_model = shared.sd_model.cond_stage_model
 

modules/textual_inversion/learn_schedule.py

@@ -4,30 +4,37 @@ import tqdm
 class LearnScheduleIterator:
     def __init__(self, learn_rate, max_steps, cur_step=0):
         """
-        specify learn_rate as "0.001:100, 0.00001:1000, 1e-5:10000" to have lr of 0.001 until step 100, 0.00001 until 1000, 1e-5:10000 until 10000
+        specify learn_rate as "0.001:100, 0.00001:1000, 1e-5:10000" to have lr of 0.001 until step 100, 0.00001 until 1000, and 1e-5 until 10000
         """
 
         pairs = learn_rate.split(',')
         self.rates = []
         self.it = 0
         self.maxit = 0
-        for i, pair in enumerate(pairs):
-            tmp = pair.split(':')
-            if len(tmp) == 2:
-                step = int(tmp[1])
-                if step > cur_step:
-                    self.rates.append((float(tmp[0]), min(step, max_steps)))
-                    self.maxit += 1
-                    if step > max_steps:
+        try:
+            for i, pair in enumerate(pairs):
+                if not pair.strip():
+                    continue
+                tmp = pair.split(':')
+                if len(tmp) == 2:
+                    step = int(tmp[1])
+                    if step > cur_step:
+                        self.rates.append((float(tmp[0]), min(step, max_steps)))
+                        self.maxit += 1
+                        if step > max_steps:
+                            return
+                    elif step == -1:
+                        self.rates.append((float(tmp[0]), max_steps))
+                        self.maxit += 1
                         return
-                elif step == -1:
+                else:
                     self.rates.append((float(tmp[0]), max_steps))
                     self.maxit += 1
                     return
-            else:
-                self.rates.append((float(tmp[0]), max_steps))
-                self.maxit += 1
-                return
+            assert self.rates
+        except (ValueError, AssertionError):
+            raise Exception('Invalid learning rate schedule. It should be a number or, for example, like "0.001:100, 0.00001:1000, 1e-5:10000" to have lr of 0.001 until step 100, 0.00001 until 1000, and 1e-5 until 10000.')
+
 
     def __iter__(self):
         return self

modules/textual_inversion/textual_inversion.py

@@ -119,7 +119,7 @@ class EmbeddingDatabase:
             vec = emb.detach().to(devices.device, dtype=torch.float32)
             embedding = Embedding(vec, name)
             embedding.step = data.get('step', None)
-            embedding.sd_checkpoint = data.get('hash', None)
+            embedding.sd_checkpoint = data.get('sd_checkpoint', None)
             embedding.sd_checkpoint_name = data.get('sd_checkpoint_name', None)
             self.register_embedding(embedding, shared.sd_model)
 
@@ -204,9 +204,30 @@ def write_loss(log_directory, filename, step, epoch_len, values):
             **values,
         })
 
+def validate_train_inputs(model_name, learn_rate, batch_size, data_root, template_file, steps, save_model_every, create_image_every, log_directory, name="embedding"):
+    assert model_name, f"{name} not selected"
+    assert learn_rate, "Learning rate is empty or 0"
+    assert isinstance(batch_size, int), "Batch size must be integer"
+    assert batch_size > 0, "Batch size must be positive"
+    assert data_root, "Dataset directory is empty"
+    assert os.path.isdir(data_root), "Dataset directory doesn't exist"
+    assert os.listdir(data_root), "Dataset directory is empty"
+    assert template_file, "Prompt template file is empty"
+    assert os.path.isfile(template_file), "Prompt template file doesn't exist"
+    assert steps, "Max steps is empty or 0"
+    assert isinstance(steps, int), "Max steps must be integer"
+    assert steps > 0 , "Max steps must be positive"
+    assert isinstance(save_model_every, int), "Save {name} must be integer"
+    assert save_model_every >= 0 , "Save {name} must be positive or 0"
+    assert isinstance(create_image_every, int), "Create image must be integer"
+    assert create_image_every >= 0 , "Create image must be positive or 0"
+    if save_model_every or create_image_every:
+        assert log_directory, "Log directory is empty"
 
 def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_directory, training_width, training_height, steps, create_image_every, save_embedding_every, template_file, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
-    assert embedding_name, 'embedding not selected'
+    save_embedding_every = save_embedding_every or 0
+    create_image_every = create_image_every or 0
+    validate_train_inputs(embedding_name, learn_rate, batch_size, data_root, template_file, steps, save_embedding_every, create_image_every, log_directory, name="embedding")
 
     shared.state.textinfo = "Initializing textual inversion training..."
     shared.state.job_count = steps
@@ -233,19 +254,30 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
         os.makedirs(images_embeds_dir, exist_ok=True)
     else:
         images_embeds_dir = None
-        
+
     cond_model = shared.sd_model.cond_stage_model
 
+    hijack = sd_hijack.model_hijack
+
+    embedding = hijack.embedding_db.word_embeddings[embedding_name]
+    checkpoint = sd_models.select_checkpoint()
+
+    ititial_step = embedding.step or 0
+    if ititial_step >= steps:
+        shared.state.textinfo = f"Model has already been trained beyond specified max steps"
+        return embedding, filename
+
+    scheduler = LearnRateScheduler(learn_rate, steps, ititial_step)
+
+    # dataset loading may take a while, so input validations and early returns should be done before this
     shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
     with torch.autocast("cuda"):
         ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, device=devices.device, template_file=template_file, batch_size=batch_size)
     if unload:
         shared.sd_model.first_stage_model.to(devices.cpu)
 
-    hijack = sd_hijack.model_hijack
-
-    embedding = hijack.embedding_db.word_embeddings[embedding_name]
     embedding.vec.requires_grad = True
+    optimizer = torch.optim.AdamW([embedding.vec], lr=scheduler.learn_rate)
 
     losses = torch.zeros((32,))
 
@@ -254,13 +286,6 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
     forced_filename = "<none>"
     embedding_yet_to_be_embedded = False
 
-    ititial_step = embedding.step or 0
-    if ititial_step > steps:
-        return embedding, filename
-
-    scheduler = LearnRateScheduler(learn_rate, steps, ititial_step)
-    optimizer = torch.optim.AdamW([embedding.vec], lr=scheduler.learn_rate)
-
     pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step)
     for i, entries in pbar:
         embedding.step = i + ititial_step
@@ -293,9 +318,9 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
 
         if embedding_dir is not None and steps_done % save_embedding_every == 0:
             # Before saving, change name to match current checkpoint.
-            embedding.name = f'{embedding_name}-{steps_done}'
-            last_saved_file = os.path.join(embedding_dir, f'{embedding.name}.pt')
-            embedding.save(last_saved_file)
+            embedding_name_every = f'{embedding_name}-{steps_done}'
+            last_saved_file = os.path.join(embedding_dir, f'{embedding_name_every}.pt')
+            save_embedding(embedding, checkpoint, embedding_name_every, last_saved_file, remove_cached_checksum=True)
             embedding_yet_to_be_embedded = True
 
         write_loss(log_directory, "textual_inversion_loss.csv", embedding.step, len(ds), {
@@ -382,14 +407,26 @@ Last saved image: {html.escape(last_saved_image)}<br/>
 </p>
 """
 
-    checkpoint = sd_models.select_checkpoint()
-
-    embedding.sd_checkpoint = checkpoint.hash
-    embedding.sd_checkpoint_name = checkpoint.model_name
-    embedding.cached_checksum = None
-    # Before saving for the last time, change name back to base name (as opposed to the save_embedding_every step-suffixed naming convention).
-    embedding.name = embedding_name
-    filename = os.path.join(shared.cmd_opts.embeddings_dir, f'{embedding.name}.pt')
-    embedding.save(filename)
+    filename = os.path.join(shared.cmd_opts.embeddings_dir, f'{embedding_name}.pt')
+    save_embedding(embedding, checkpoint, embedding_name, filename, remove_cached_checksum=True)
 
     return embedding, filename
+
+def save_embedding(embedding, checkpoint, embedding_name, filename, remove_cached_checksum=True):
+    old_embedding_name = embedding.name
+    old_sd_checkpoint = embedding.sd_checkpoint if hasattr(embedding, "sd_checkpoint") else None
+    old_sd_checkpoint_name = embedding.sd_checkpoint_name if hasattr(embedding, "sd_checkpoint_name") else None
+    old_cached_checksum = embedding.cached_checksum if hasattr(embedding, "cached_checksum") else None
+    try:
+        embedding.sd_checkpoint = checkpoint.hash
+        embedding.sd_checkpoint_name = checkpoint.model_name
+        if remove_cached_checksum:
+            embedding.cached_checksum = None
+        embedding.name = embedding_name
+        embedding.save(filename)
+    except:
+        embedding.sd_checkpoint = old_sd_checkpoint
+        embedding.sd_checkpoint_name = old_sd_checkpoint_name
+        embedding.name = old_embedding_name
+        embedding.cached_checksum = old_cached_checksum
+        raise

test/extras_test.py

+import unittest
+
+
+class TestExtrasWorking(unittest.TestCase):
+    def setUp(self):
+        self.url_img2img = "http://localhost:7860/sdapi/v1/extra-single-image"
+        self.simple_extras = {
+            "resize_mode": 0,
+            "show_extras_results": True,
+            "gfpgan_visibility": 0,
+            "codeformer_visibility": 0,
+            "codeformer_weight": 0,
+            "upscaling_resize": 2,
+            "upscaling_resize_w": 512,
+            "upscaling_resize_h": 512,
+            "upscaling_crop": True,
+            "upscaler_1": "None",
+            "upscaler_2": "None",
+            "extras_upscaler_2_visibility": 0,
+            "image": ""
+            }
+
+
+class TestExtrasCorrectness(unittest.TestCase):
+    pass
+
+
+if __name__ == "__main__":
+    unittest.main()

test/img2img_test.py

+import unittest
+import requests
+from gradio.processing_utils import encode_pil_to_base64
+from PIL import Image
+
+
+class TestImg2ImgWorking(unittest.TestCase):
+    def setUp(self):
+        self.url_img2img = "http://localhost:7860/sdapi/v1/img2img"
+        self.simple_img2img = {
+            "init_images": [encode_pil_to_base64(Image.open(r"test/test_files/img2img_basic.png"))],
+            "resize_mode": 0,
+            "denoising_strength": 0.75,
+            "mask": None,
+            "mask_blur": 4,
+            "inpainting_fill": 0,
+            "inpaint_full_res": False,
+            "inpaint_full_res_padding": 0,
+            "inpainting_mask_invert": 0,
+            "prompt": "example prompt",
+            "styles": [],
+            "seed": -1,
+            "subseed": -1,
+            "subseed_strength": 0,
+            "seed_resize_from_h": -1,
+            "seed_resize_from_w": -1,
+            "batch_size": 1,
+            "n_iter": 1,
+            "steps": 3,
+            "cfg_scale": 7,
+            "width": 64,
+            "height": 64,
+            "restore_faces": False,
+            "tiling": False,
+            "negative_prompt": "",
+            "eta": 0,
+            "s_churn": 0,
+            "s_tmax": 0,
+            "s_tmin": 0,
+            "s_noise": 1,
+            "override_settings": {},
+            "sampler_index": "Euler a",
+            "include_init_images": False
+            }
+
+    def test_img2img_simple_performed(self):
+        self.assertEqual(requests.post(self.url_img2img, json=self.simple_img2img).status_code, 200)
+
+    def test_inpainting_masked_performed(self):
+        self.simple_img2img["mask"] = encode_pil_to_base64(Image.open(r"test/test_files/mask_basic.png"))
+        self.assertEqual(requests.post(self.url_img2img, json=self.simple_img2img).status_code, 200)
+
+
+class TestImg2ImgCorrectness(unittest.TestCase):
+    pass
+
+
+if __name__ == "__main__":
+    unittest.main()

test/server_poll.py

+import unittest
+import requests
+import time
+
+
+def run_tests():
+    timeout_threshold = 240
+    start_time = time.time()
+    while time.time()-start_time < timeout_threshold:
+        try:
+            requests.head("http://localhost:7860/")
+            break
+        except requests.exceptions.ConnectionError:
+            pass
+    if time.time()-start_time < timeout_threshold:
+        suite = unittest.TestLoader().discover('', pattern='*_test.py')
+        result = unittest.TextTestRunner(verbosity=2).run(suite)
+    else:
+        print("Launch unsuccessful")

test/txt2img_test.py

+import unittest
+import requests
+
+
+class TestTxt2ImgWorking(unittest.TestCase):
+    def setUp(self):
+        self.url_txt2img = "http://localhost:7860/sdapi/v1/txt2img"
+        self.simple_txt2img = {
+            "enable_hr": False,
+            "denoising_strength": 0,
+            "firstphase_width": 0,
+            "firstphase_height": 0,
+            "prompt": "example prompt",
+            "styles": [],
+            "seed": -1,
+            "subseed": -1,
+            "subseed_strength": 0,
+            "seed_resize_from_h": -1,
+            "seed_resize_from_w": -1,
+            "batch_size": 1,
+            "n_iter": 1,
+            "steps": 3,
+            "cfg_scale": 7,
+            "width": 64,
+            "height": 64,
+            "restore_faces": False,
+            "tiling": False,
+            "negative_prompt": "",
+            "eta": 0,
+            "s_churn": 0,
+            "s_tmax": 0,
+            "s_tmin": 0,
+            "s_noise": 1,
+            "sampler_index": "Euler a"
+        }
+
+    def test_txt2img_simple_performed(self):
+        self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
+
+    def test_txt2img_with_negative_prompt_performed(self):
+        self.simple_txt2img["negative_prompt"] = "example negative prompt"
+        self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
+
+    def test_txt2img_not_square_image_performed(self):
+        self.simple_txt2img["height"] = 128
+        self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
+
+    def test_txt2img_with_hrfix_performed(self):
+        self.simple_txt2img["enable_hr"] = True
+        self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
+
+    def test_txt2img_with_restore_faces_performed(self):
+        self.simple_txt2img["restore_faces"] = True
+        self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
+
+    def test_txt2img_with_tiling_faces_performed(self):
+        self.simple_txt2img["tiling"] = True
+        self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
+
+    def test_txt2img_with_vanilla_sampler_performed(self):
+        self.simple_txt2img["sampler_index"] = "PLMS"
+        self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
+
+    def test_txt2img_multiple_batches_performed(self):
+        self.simple_txt2img["n_iter"] = 2
+        self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
+
+
+class TestTxt2ImgCorrectness(unittest.TestCase):
+    pass
+
+
+if __name__ == "__main__":
+    unittest.main()

webui.py

@@ -46,26 +46,13 @@ def wrap_queued_call(func):
 
 def wrap_gradio_gpu_call(func, extra_outputs=None):
     def f(*args, **kwargs):
-        devices.torch_gc()
-
-        shared.state.sampling_step = 0
-        shared.state.job_count = -1
-        shared.state.job_no = 0
-        shared.state.job_timestamp = shared.state.get_job_timestamp()
-        shared.state.current_latent = None
-        shared.state.current_image = None
-        shared.state.current_image_sampling_step = 0
-        shared.state.skipped = False
-        shared.state.interrupted = False
-        shared.state.textinfo = None
+
+        shared.state.begin()
 
         with queue_lock:
             res = func(*args, **kwargs)
 
-        shared.state.job = ""
-        shared.state.job_count = 0
-
-        devices.torch_gc()
+        shared.state.end()
 
         return res