{ "Agent Scheduler": "Agent Scheduler", "Queue task and task history": "Queue task and task history", "TemporalKit": "TemporalKit", "An all in one solution for adding Temporal Stability to a Stable Diffusion Render via an automatic1111 extension": "An all in one solution for adding Temporal Stability to a Stable Diffusion Render via an automatic1111 extension", "ua_UA Localization": "烏克蘭語本地化語言包", "Ukrainian localization": "烏克蘭語本地化", "Batch Checkpoints and Prompts": "批量檢查點和關鍵字", "Test a base prompt with different checkpoints and for the checkpoints specific prompt templates ": "使用不同的檢查點和檢查點特定的提示詞模板測試基本提示詞 ", "Kandinsky": "Kandinsky", "Adds a script to run Kandinsky 2.X": "Adds a script to run Kandinsky 2.X", "Txt/Img to 3D Model": "Txt/Img to 3D Model", "An extension integrated OpenAI Shap-E that allow you to generate 3D model from prompt or image": "An extension integrated OpenAI Shap-E that allow you to generate 3D model from prompt or image", "sd-webui-openpose-editor": "sd-webui-openpose-editor", "Integrated openpose editor for ControlNet. Full hand/face support.": "Integrated openpose editor for ControlNet. Full hand/face support.", "sd-webui-segment-anything": "sd-webui-segment-anything", "Segment Anything for Stable Diffusion WebUI. Automatically generate high-quality segmentations/masks for images by clicking or text prompting. Aim for connecting WebUI and ControlNet with Segment Anything and GroundingDINO to enhance Stable Diffusion/ControlNet inpainting (both single image and batch process), enhance ControlNet semantic segmentation, automate image matting and create LoRA/LyCORIS training set.": "Segment Anything for Stable Diffusion WebUI. Automatically generate high-quality segmentations/masks for images by clicking or text prompting. Aim for connecting WebUI and ControlNet with Segment Anything and GroundingDINO to enhance Stable Diffusion/ControlNet inpainting (both single image and batch process), enhance ControlNet semantic segmentation, automate image matting and create LoRA/LyCORIS training set.", "Stable Diffusion AWS Extension": "Stable Diffusion AWS Extension", "Allow user to migrate existing workloads including ckpt merge, model training, model inferencing onto AWS": "Allow user to migrate existing workloads including ckpt merge, model training, model inferencing onto AWS", "Aesthetic Gradients": "美學梯度", "Allows training an embedding from one or few pictures, specifically meant for applying styles. Also, allows use of these specific embeddings to generated images.": "允許從一張或多張圖像中訓練一個嵌入（embedding），專門用於套用風格。同時，也允許使用這些特定的嵌入來產生圖像。", "Dreambooth": "Dreambooth", "Dreambooth training based on Shivam Shiaro's repo, optimized for lower-VRAM GPUs.": "基於 Shivam Shiaro 的代碼移植的 Dreambooth 訓練，為低 VRAM 顯示卡做了優化", "training-picker": "training-picker", "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.": "向 webui 加入一個頁籤，允許用戶自動從影片中提取關鍵幀，並手動裁剪 512x512 大小以用於模型訓練", "Dataset Tag Editor": "數據集標記編輯器", "Feature-rich UI tab that allows image viewing, search-filtering and editing.": "功能豐富的用戶介面標籤，允許查看圖像、搜尋過濾和編輯。", "DreamArtist": "夢想家（DreamArtist）", "Towards Controllable One-Shot Text-to-Image Generation via Contrastive Prompt-Tuning.": "通過對比調整提示詞，實現可控的一次性文字文件到圖像生成", "Hypernetwork-Monkeypatch-Extension": "Hypernetwork-Monkeypatch-擴充套件", "Extension that provides additional training features for hypernetwork training. Also supports using multiple hypernetworks for inference.": "提供超網絡訓練的額外訓練功能的擴充套件。也支援同時使用多個超網絡進行推論。", "Custom Diffusion": "自訂擴散", "Custom Diffusion is, in short, finetuning-lite with TI, instead of tuning the whole model. Similar speed and memory requirements to TI and supposedly gives better results in less steps.": "簡而言之，自訂擴散是用 TI 的微調代替整個模型的微調。速度和記憶體需求類似 TI，並且在較少步驟內獲得更好的結果。", "Smart Process": "智慧預處理", "Smart pre-process including auto subject identification, caption subject swapping, and upscaling/facial restoration.": "智慧預處理，包括自動識別主體、切換描述文字主體和放大／面部恢復", "Embeddings editor": "多個嵌入編輯器", "Allows you to manually edit textual inversion embeddings using sliders.": "讓你可以手動用滑桿編輯風格遷移多個嵌入的參數", "embedding-inspector": "嵌入檢查器", "Inspect any token(a word) or Textual-Inversion embeddings and find out which embeddings are similar. You can mix, modify, or create the embeddings in seconds.": "檢查任何標記（一個單詞）或文本反轉嵌入並找出相似的嵌入。您可以在幾秒鐘內混合，修改或創建嵌入。", "Merge Board": "合併面板", "Multiple lane merge support(up to 10). Save and Load your merging combination as Recipes, which is simple text.": "支援多條道路合併(多達10條)，可以將合併組合儲存為「食譜」，食譜是一個簡單的文字檔案。", "Model Converter": "模型轉換器", "Convert models to fp16/bf16 no-ema/ema-only safetensors. Convert/copy/delete any parts of model: unet, text encoder(clip), vae.": "將模型轉換為 fp16/bf16 no-ema/ema-only safetensors。轉換/複製/刪除模型的任何部分：unet，文字編碼器（剪貼），vae。", "Kohya-ss Additional Networks": "Kohya-ss 附加網路", "Allows the Web UI to use LoRAs (1.X and 2.X) to generate images. Also allows editing .safetensors networks prompt metadata.": "允許使用者介面使用 LoRAs（1.X 和 2.X）產生圖像。同時，還允許編輯 .safetensors 網路提示詞中繼資料。", "Merge Block Weighted": "合併塊加權", "Merge models with separate rate for each 25 U-Net block (input, middle, output).": "合併模型，每 25 個 U-Net 塊（輸入、中間、輸出）有獨立的比率。", "Embedding Merge": "嵌入合併", "Merging Textual Inversion embeddings at runtime from string literals. Phrases and weight values also supported.": "在運行時從字符串文字中合併文本反轉嵌入。也支援短語和權重值。", "SuperMerger": "超級融合器", "Merge and run without saving to drive. Sequential XY merge generations; extract and merge loras, bind loras to ckpt, merge block weights, and more.": "無需儲存到硬碟合併並執行。按順序進行 XY 合併；提取並合併 LoRAs，將 LoRAs 綁定到模型權重存檔點，合併區塊權重以及更多。", "LoRA Block Weight": "LoRA 區塊權重", "Applies LoRA strength; block by block on the fly. Includes presets, weight analysis, randomization, XY plot.": "在執行時逐塊的套用 LoRA 強度。包括預設值、權重分析、隨機化以及 XY 圖。", "Image browser": "圖庫瀏覽器", "Provides an interface to browse created images in the web browser.": "在網頁瀏覽器裡提供一個瀏覽已產生的圖像使用者介面", "Infinite image browsing": "無限圖像瀏覽", "A fast image browser that allows browsing all images without paging, and supports joint search using image parameters, with a layout similar to VS Code.": "A fast image browser that allows browsing all images without paging, and supports joint search using image parameters, with a layout similar to VS Code.", "Inspiration": "靈感", "Randomly display the pictures of the artist's or artistic genres typical style, more pictures of this artist or genre is displayed after selecting. So you don't have to worry about how hard it is to choose the right style of art when you create.": "隨機顯示一位藝術家或某藝術流派的圖像，選擇後會顯示更多該藝術家或藝術流派的圖像。所以你不用擔心在創作時難以選擇出想要的藝術風格", "Artists to study": "藝術家圖庫", "Shows a gallery of generated pictures by artists separated into categories.": "將藝術家按類別劃分，並顯示其產生出來的圖像", "Prompt Gallery": "提示詞畫廊", "Build a yaml file filled with prompts of your character, hit generate, and quickly preview them by their word attributes and modifiers.": "建立一個使用您的角色提示的 yaml 檔，點擊產生，並快速通過其字屬性和修飾符預覽它們。", "Infinity Grid Generator": "無限網格產生器", "Build a yaml file with your chosen parameters, and generate infinite-dimensional grids. Built-in ability to add description text to fields. See readme for usage details.": "建立一個使用選定的參數的 yaml 檔，並產生無限維的網格。內建能力將描述文字添加到字段中。有關用法細節，請參閱 readme。", "Config-Presets": "配置預設值", "Adds a configurable dropdown to allow you to change UI preset settings in the txt2img and img2img tabs.": "在文生圖和圖生圖頁面中添加可設定下拉菜單，以允許您更改 UI 預設設定。", "Preset Utilities": "預設工具", "Preset utility tool for ui. Offers compatibility with custom scripts. (to a limit)": "預設工具，用於 ui。提供與自定義腳本的兼容性。（有限制）", "openOutpaint extension": "openOutpaint 擴展", "A tab with the full openOutpaint UI. Run with the --api flag.": "具有完整 openOutpaint UI 的選項卡。使用 --api 標誌運行。", "quick-css": "快速 CSS", "Extension for quickly selecting and applying custom.css files, for customizing look and placement of elements in ui.": "用於快速選擇和應用 custom.css 文件的擴展，以自定義 ui 中元素的外觀和位置。", "Aspect Ratio selector": "長寬比選擇器", "Adds image aspect ratio selector buttons.": "添加圖像長寬比選擇按鈕。", "Nevysha's Cozy Nest": "Nevysha's Cozy Nest", "Extension for an improved UI/UX. Find your cozy spot on Auto1111's webui!.": "Extension for an improved UI/UX. Find your cozy spot on Auto1111's webui!.", "Catppuccin Theme": "Catppuccin 主題", "Adds various custom themes": "添加多種自定義主題。", "Bilingual Localization": "雙語翻譯對照", "Bilingual translation, no need to worry about how to find the original button. Compatible with language pack extensions, no need to re-import.": "雙語翻譯，無需擔心如何尋找原文按鈕。與語言包擴充功能相容，無需重新導入。", "Dynamic Prompts": "動態提示詞", "Implements an expressive template language for random or combinatorial prompt generation along with features to support deep wildcard directory structures.": "為隨機或組合式提示詞的生成實現了一種表達性模板語言，並支持深層目錄結構中的萬用字元", "Unprompted": "非文本（代碼化）提示詞", "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. It now includes integrations like hard-prompts made easy, ControlNet, txt2img2img and txt2mask.": "允許您在提示詞中包含各種短碼。您可以從文件中提取文本，設定自己的變數，通過條件函數處理文字等 ，就像是在類固醇中的萬用字元。它現在包括了一些整合，如硬提示詞（hard-prompts）、ControlNet、文生圖生圖和文生遮罩。", "StylePile": "樣式積累", "An easy way to mix and match elements to prompts that affect the style of the result.": "方便地組合不同元素，並影響結果的樣式。", "Booru tag autocompletion": "Booru 標記自動補齊", "Displays autocompletion hints for tags from image booru boards such as Danbooru. Uses local tag CSV files and includes a config for customization.": "顯示來自圖像板塊（如 Danbooru）的標記自動補齊。使用本地標記CSV 檔案，並包含可用於自定義配置的檔案", "novelai-2-local-prompt": "novelai-2-local-prompt", "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.": "加入一個按鈕以將 NovelAI 中使用的提示詞轉換為在 WebUI 中使用。此外，加入一個按鈕，讓你可以調用以前使用過的提示詞", "tokenizer": "標記解析器", "Adds a tab that lets you preview how CLIP model would tokenize your text.": "新增一個頁籤讓你能夠預覽 CLIP 模型如何對你的文本進行標記拆分", "Randomize": "隨機化", "Allows for random parameters during txt2img generation. This script will function with others as well. Original author: https://git.mmaker.moe/mmaker/stable-diffusion-webui-randomize": "允許在文生圖產生過程中使用隨機參數。此指令碼也可以與其他指令碼一起執行。原作者：https://git.mmaker.moe/mmaker/stable-diffusion-webui-randomize", "conditioning-highres-fix": "高解析度修復原圖調節", "This is Extension for rewriting Inpainting conditioning mask strength value relative to Denoising strength at runtime. This is useful for Inpainting models such as sd-v1-5-inpainting.ckpt": "這是在運行時重新實現的局部重繪圖像調節遮罩強度（相對於重繪強度）的擴充功能。這對於局部重繪專用的模型（例如 sd-v1-5-inpainting.ckpt）很有用", "model-keyword": "模型關鍵字", "Inserts matching keyword(s) to the prompt automatically. Update this extension to get the latest model+keyword mappings.": "自動將匹配關鍵字插入提示。更新此擴展以獲取最新的「模型+關鍵字」映射。", "Prompt Generator": "提示產生器", "generate a prompt from a small base prompt using distilgpt2. Adds a tab with additional control of the model.": "使用 distilgpt2 從小基礎提示產生提示。添加一個具有模型額外控制的選項卡。", "Promptgen": "提示詞生成器", "Use transformers models to generate prompts.": "使用 transformers 模型產生提示詞。", "text2prompt": "文生提示詞", "Generates anime tags using databases and models for tokenizing.": "使用資料庫和分詞模型產生動漫標籤。", "Prompt Translator": "提示詞翻譯器", "A integrated translator for translating prompts to English using Deepl or Baidu.": "一個使用 Deepl 或 Baidu 翻譯提示至英文的統整翻譯器。", "Deforum": "Deforum", "The official port of Deforum, an extensive script for 2D and 3D animations, supporting keyframable sequences, dynamic math parameters (even inside the prompts), dynamic masking, depth estimation and warping.": "Deforum 的官方移植，一個用於 2D 和 3D 動畫的擴展指令碼，支持關鍵幀序列、動態數學參數（甚至可用於提示詞內）、動態遮罩、深度預測和變形", "Animator": "動畫製作器", "A basic img2img script that will dump frames and build a video file. Suitable for creating interesting zoom-in warping movies. This is intended to be a versatile toolset to help you automate some img2img tasks.": "一個簡單的圖生圖腳本，將輸出幀並建立視訊檔案。適合製作有趣的縮放曲折電影。這是一個多用途的工具組，可幫助您自動化一些圖生圖任務。", "gif2gif": "GIF生GIF", "A script for img2img that extract a gif frame by frame for img2img generation and recombine them back into an animated gif": "圖生圖的腳本，逐幀提取圖生圖以生成 gif，並將它們重新組合成動畫gif", "Video Loopback": "Video Loopback", "A video2video script that tries to improve on the temporal consistency and flexibility of normal vid2vid.": "一個嘗試改善普通 vid2vid 的時間一致性和靈活性的 video2video 指令碼。", "seed travel": "種子變遷", "Small script for AUTOMATIC1111/stable-diffusion-webui to create images that exists between seeds.": "一個用於生成不同隨機種子之間的漸變過程的小指令碼", "shift-attention": "shift-attention", "Generate a sequence of images shifting attention in the prompt. This script enables you to give a range to the weight of tokens in a prompt and then generate a sequence of images stepping from the first one to the second.": "根據提示詞產生一系列關注逐漸轉移的圖像。此指令碼使你能夠在提示詞中為標記的權重指定一個範圍，然後產生從一端到另一端的一系列圖像", "prompt travel": "提示詞變遷", "Extension script for AUTOMATIC1111/stable-diffusion-webui to travel between prompts in latent space.": "一個在潛在變數中對不同提示詞之間進行插值漸變，並生成其漸變過程的擴充功能指令碼", "Steps Animation": "步驟動畫", "Create animation sequence from denoised intermediate steps.": "從降噪過程中的中間步驟建立動畫序列。", "auto-sd-paint-ext": "畫圖工具擴充", "Krita Plugin.": "Krita 套件", "Batch Face Swap": "批次臉部交換", "Automatically detects faces and replaces them.": "自動偵測臉部並進行替換。", "Depth Maps": "深度圖", "Depth Maps, Stereo Image, 3D Mesh and Video generator extension.": "深度圖、立體圖像、3D網格和影片生成器擴展。", "multi-subject-render": "多主題繪製", "It is a depth aware extension that can help to create multiple complex subjects on a single image. It generates a background, then multiple foreground subjects, cuts their backgrounds after a depth analysis, paste them onto the background and finally does an img2img for a clean finish.": "它是一個深度感知延伸，可以幫助在單張圖像上創建多個復雜主題。它先產生背景，再產生多個前景主題，根據深度分析切割它們的背景，將它們粘貼到背景上，最後進行圖生圖，得到一個乾淨的結果。", "depthmap2mask": "深度圖生遮罩", "Create masks for img2img based on a depth estimation made by MiDaS.": "根據 MiDaS 的深度估計為圖生圖創建遮罩。", "ABG_extension": "ABG_擴展", "Automatically remove backgrounds. Uses an onnx model fine-tuned for anime images. Runs on GPU.": "自動刪除背景。使用為動漫圖像微調的 onnx 模型。在 GPU 上運行。", "Pixel": "Pixel", "Quickly and easily perform downscaling, color palette limiting, and other useful pixel art effects through the extras tab.": "Quickly and easily perform downscaling, color palette limiting, and other useful pixel art effects through the extras tab.", "Pixelization": "像素化", "Using pre-trained models, produce pixel art out of images in the extras tab.": "使用預先訓練的模型，在附加標籤中將圖像轉換為像素藝術。", "haku-img": "HAKU 圖像工具", "Image utils extension. Allows blending, layering, hue and color adjustments, blurring and sketch effects, and basic pixelization.": "圖像工具擴充套件。允許混合、分層、色調和顏色調整、模糊和素描效果，以及基本的像素化。", "Asymmetric Tiling": "非對稱平舖", "An always visible script extension to configure seamless image tiling independently for the X and Y axes.": "一個始終可見的腳本擴充套件，用於分別配置 X 和 Y 軸上的無縫圖像鋪貼。", "Latent Mirroring": "鏡像潛在變數", "Applies mirroring and flips to the latent images to produce anything from subtle balanced compositions to perfect reflections": "將圖像的潛在變數狀態進行鏡像和翻轉，以產生從輕度平衡的構圖到完全對稱的任何圖像", "Sonar": "聲納", "Improve the generated image quality, searches for similar (yet even better!) images in the neighborhood of some known image, focuses on single prompt optimization rather than traveling between multiple prompts.": "提高產生的圖像品質，在某個已知圖像的附近搜索類似（甚至更好！）的圖像，專注於單個提示的優化，而不是在多個提示之間旅行。", "Depth Image I/O": "深度影像輸入/輸出", "An extension to allow managing custom depth inputs to Stable Diffusion depth2img models.": "一個擴充套件，允許管理自訂深度輸入到 Stable Diffusion depth2img 模型。", "Ultimate SD Upscale": "終極 SD 放大", "More advanced options for SD Upscale, less artifacts than original using higher denoise ratio (0.3-0.5).": "比 SD 放大的更為進階的選項，使用更高的降噪比率 (0.3-0.5)，比原始的更少的人工假象。", "Prompt Fusion": "Prompt Fusion", "Adds prompt-travel and shift-attention-like interpolations (see exts), but during/within the sampling steps. Always-on + works w/ existing prompt-editing syntax. Various interpolation modes. See their wiki for more info.": "加入提示旅行和類似位移注意力的插值（請參閱 exts），但在採樣步驟中進行。始終啟用 + 可與現有提示編輯語法一起使用。各種插值模式。有關更多信息，請參閱其 wiki。", "Neutral Prompt": "Neutral Prompt", "Adds new keywords for manipulating noise blending and prompt interactions. Allows for organizing prompts in a hierarchical manner instead of a flat list.": "Adds new keywords for manipulating noise blending and prompt interactions. Allows for organizing prompts in a hierarchical manner instead of a flat list.", "Dynamic Thresholding": "動態閾值", "Adds customizable dynamic thresholding to allow high CFG Scale values without the burning / 'pop art' effect.": "加入可自訂的動態閾值，以允許高 CFG Scale 值，而不會有燒焦或「流行藝術」效果。", "anti-burn": "反燒機", "Smoothing generated images by skipping a few very last steps and averaging together some images before them.": "跳過最後幾步並將之前的一些圖像平均在一起，以平滑生成的圖像。", "sd-webui-controlnet": "sd-webui-controlnet", "WebUI extension for ControlNet. Note: (WIP), so don't expect seed reproducibility - as updates may change things.": "ControlNet 的 WebUI 擴充功能。注意：由於仍在開發中，因此不保證種子的再現性，因為更新可能會更改內容。", "Latent Couple": "潛在變數伴侶", "An extension of the built-in Composable Diffusion, allows you to determine the region of the latent space that reflects your subprompts. Note: New maintainer, uninstall prev. ext if needed.": "內置 Composable Diffusion 擴充功能，能使您將子提示詞反映在特定的潛在變數空間區域。注意：如有必要，請解除安裝先前的擴充功能。", "Composable LoRA": "Composable LoRA", "Enables using AND keyword(composable diffusion) to limit LoRAs to subprompts. Useful when paired with Latent Couple extension.": "允許使用 AND 關鍵字（composable diffusion）來限制 LoRA 到子提示詞。當與潛在變數伴侶擴充功能搭配使用時非常有用。", "Auto TLS-HTTPS": "自動使用安全性傳輸協定（https）", "Allows you to easily, or even completely automatically start using HTTPS.": "讓你可以很簡單的自動配置安全性傳輸協定（https）", "booru2prompt": "booru轉提示詞", "This SD extension allows you to turn posts from various image boorus into stable diffusion prompts. It does so by pulling a list of tags down from their API. You can copy-paste in a link to the post you want yourself, or use the built-in search feature to do it all without leaving SD.": "這個 SD 延伸可以將各種圖像 boorus 的文章轉換為穩定擴散提示。它通過從API下載標籤列表來完成此操作。您可以自行複製粘貼您想要的文章的網址，或使用內置的搜索功能在不離開 SD 的情況下完成所有操作。", "Gelbooru Prompt": "Gelbooru 提示", "Extension that gets tags for saved gelbooru images in AUTOMATIC1111's Stable Diffusion webui": "擴充功能，可獲取在 AUTOMATIC1111 的 Stable Diffusion webui 中儲存的 Gelbooru 圖像的標籤", "e621 Prompt": "e621 Prompt", "Request tags of an image from e621 and convert them into a prompt": "Request tags of an image from e621 and convert them into a prompt", "NSFW checker": "NSFW 檢查器", "Replaces NSFW images with black.": "用黑色替換 NSFW 圖像。", "Diffusion Defender": "擴散防御者", "Prompt blacklist, find and replace, for semi-private and public instances.": "提示黑名單，查找並替換半私人和公共實例。", "DH Patch": "DH 更新檔", "Random patches by D8ahazard. Auto-load config YAML files for v2, 2.1 models; patch latent-diffusion to fix attention on 2.1 models (black boxes without no-half), whatever else I come up with.": "D8ahazard 的隨機修補程式。自動加載 v2、2.1 模型的 YAML 配置文件；修補 2.1 模型的潛在變數擴散以修復注意力（沒有 no-half 的黑盒子），以及其他任何我想到的。", "Riffusion": "Riffusion", "Use Riffusion model to produce music in gradio. To replicate original interpolation technique, input the prompt travel extension output frames into the riffusion tab.": "使用 Riffusion 模型在 gradio 中產生音樂。要重現原始插值技巧，請將提示旅行擴展輸出幀輸入到 Riffusion 頁面中。", "Save Intermediate Images": "儲存中間圖像", "Save intermediate images during the sampling process. You can also make videos from the intermediate images.": "在採樣過程中儲存中間圖像。您也可以從中間圖像製作影片。", "Add image number to grid": "將圖像編號添加到網格中", "Add the image's number to its picture in the grid.": "將圖像的編號添加到網格中的圖片中。", "Multiple Hypernetworks": "多個超網絡", "Adds the ability to apply multiple hypernetworks at once. Apply multiple hypernetworks sequentially, with different weights.": "增加同時應用多個超網絡的能力。連續應用多個超網絡，具有不同的權重。", "System Info": "系統資訊", "System Info tab for WebUI which shows realtime information of the server. Also supports sending crowdsourced inference data as an option.": "System Info tab for WebUI which shows realtime information of the server. Also supports sending crowdsourced inference data as an option.", "OpenPose Editor": "OpenPose編輯器", "This can add multiple pose characters, detect pose from image, save to PNG, and send to controlnet extension.": "可添加多個姿勢角色，從圖像中檢測姿勢，儲存為 PNG 並發送到 ControlNet 擴充功能。", "Stable Horde Worker": "Stable Horde 工作端", "Worker Client for Stable Horde. Generate pictures for other users with your PC. Please see readme for additional instructions.": "Stable Horde 工作端。使用您的 PC 為其他使用者產生圖片。請閱讀說明以獲取其他指示。", "Stable Horde Client": "Stable Horde 客戶端", "Stable Horde Client. Generate pictures using other user's PC. Useful if u have no GPU.": "Stable Horde 客戶端。使用其他用戶的 PC 產生圖片。如果自己沒有 GPU 的話，這很有用。", "Discord Rich Presence": "Discord 豐富存在", "Provides connection to Discord RPC, showing a fancy table in the user profile.": "提供與 Discord RPC 的連接，在用戶資料頁面顯示漂亮的表格。", "mine-diffusion": "mine-diffusion", "This extension converts images into blocks and creates schematics for easy importing into Minecraft using the Litematica mod.": "This extension converts images into blocks and creates schematics for easy importing into Minecraft using the Litematica mod.", "Aesthetic Image Scorer": "美學圖像評分器", "Calculates aesthetic score for generated images using CLIP+MLP Aesthetic Score Predictor based on Chad Scorer": "為產生出來的圖像計算其美學分數。基於 Chad Scorer 使用 CLIP+MLP 美學分數預測器", "Aesthetic Scorer": "美學評分器", "Uses existing CLiP model with an additional small pretrained model to calculate perceived aesthetic score of an image.": "使用現有的 CLiP 模型和額外的小型預訓練模型來計算圖像的感知美學分數。", "cafe-aesthetic": "咖啡審美器", "Pre-trained model, determines if aesthetic/non-aesthetic, does 5 different style recognition modes, and Waifu confirmation. Also has a tab with Batch processing.": "預先訓練的模型，用於判斷美學/非美學，進行五種不同樣式的識別模式，以及 Waifu 確認。此外還有批次處理的標籤。", "Clip Interrogator": "Clip Interrogator", "Clip Interrogator by pharmapsychotic ported to an extension. Features a variety of clip models and interrogate settings.": "Clip Interrogator by pharmapsychotic ported to an extension. Features a variety of clip models and interrogate settings.", "Visualize Cross-Attention": "可視化跨注意力", "Generates highlighted sectors of a submitted input image, based on input prompts. Use with tokenizer extension. See the readme for more info.": "根據輸入提示詞產生輸入圖像的突出顯示區域。需與 Tokenizer 擴充功能一起使用。詳細資訊請參閱自述文件。", "DAAM": "擴散注意力歸因圖（DAAM）", "DAAM stands for Diffusion Attentive Attribution Maps. Enter the attention text (must be a string contained in the prompt) and run. An overlapping image with a heatmap for each attention will be generated along with the original image.": "DAAM 代表擴散注意力歸因圖（Diffusion Attentive Attribution Maps）。輸入注意力文（必須是提示詞中包含的字串）並運行。將生成一張與原始圖像重疊的圖像，每個注意力將附帶一個熱度圖。", "Dump U-Net": "Dump U-Net", "View different layers, observe U-Net feature maps. Image generation by giving different prompts for each block of the unet: https://note.com/kohya_ss/n/n93b7c01b0547": "View different layers, observe U-Net feature maps. Image generation by giving different prompts for each block of the unet: https://note.com/kohya_ss/n/n93b7c01b0547", "posex": "posex", "Estimated Image Generator for Pose2Image. This extension allows moving the openpose figure in 3d space.": "Estimated Image Generator for Pose2Image. This extension allows moving the openpose figure in 3d space.", "LLuL": "潛空間區域放大", "Local Latent Upscaler. Target an area to selectively enhance details.": "潛在變數區域放大。指定一個範圍以選擇性增強細節。", "CFG-Schedule-for-Automatic1111-SD": "CFG-Schedule-for-Automatic1111-SD", "These scripts allow for dynamic CFG control during generation steps. With the right settings, this could help get the details of high CFG without damaging the generated image even with low denoising in img2img.": "These scripts allow for dynamic CFG control during generation steps. With the right settings, this could help get the details of high CFG without damaging the generated image even with low denoising in img2img.", "ebsynth_utility": "ebsynth_utility", "Extension for creating videos using img2img and ebsynth. Output edited videos using ebsynth. Works with ControlNet extension.": "Extension for creating videos using img2img and ebsynth. Output edited videos using ebsynth. Works with ControlNet extension.", "VRAM Estimator": "VRAM 估量器", "Runs txt2img, img2img, highres-fix at increasing dimensions and batch sizes until OOM, and outputs data to graph.": "執行遞增的圖像尺寸與批次數量文生圖、圖生圖以及高解析修復直到將記憶體耗盡，並輸出資料圖表。", "TiledDiffusion with Tiled VAE": "TiledDiffusion with Tiled VAE", "Seamless large image regional generation and upscaling, along with vram-efficient tiled vae script.": "Seamless large image regional generation and upscaling, along with vram-efficient tiled vae script.", "3D Model&Pose Loader": "3D 模型與姿勢載入器", "Load your 3D model/animation inside webui, or edit model pose as well, then send screenshot to txt2img or img2img to ControlNet.": "載入你的 3D 模型 / 動畫到網頁使用者介面，或編輯模型姿勢，然後傳送截圖至文生圖或圖生圖的 ControlNet。", "Corridor Crawler Outpainting": "Corridor Crawler Outpainting", "Generate hallways with the depth-to-image model at 512 resolution. It can be tweaked to work with other models/resolutions.": "使用解析度為 512 的深度圖像模型產生畫廊。它可以調整以適應其他模型 / 解析度。", "Panorama Viewer": "全景圖像查看器", "Provides a tab to display equirectangular images in interactive 3d-view.": "提供一個分頁以顯示互動式 3D 視圖中的等矩形圖像。", "db-storage1111": "資料庫儲存", "Enables the storage of pictures and their metadata in a MongoDB database.": "Enables the storage of pictures and their metadata in a MongoDB database.", "stable-diffusion-webui-rembg": "stable-diffusion-webui-rembg", "Removes backgrounds from pictures.": "從圖片移除背景。", "sd-webui-tunnels": "sd-webui-tunnels", "Add alternatives to the default tunneling methods. (including cloudflared)": "加入使用預設 tunneling 方法以外的替代方法（包括 cloudflared）", "3D Openpose Editor": "3D Openpose Editor", "Edit the pose of 3D models in the WebUI, and generate Openpose/Depth/Normal/Canny maps for ControlNet.": "在網頁使用者介面上編輯 3D 模型的姿勢，並為 ControlNet 產生 Openpose/Depth/Normal/Canny 圖。", "sd-webui-enable-checker": "sd-webui-enable-checker", "Switch background color by clicking the Enable buttons in SD Web UI": "透過在網頁使用者介面中點擊啟用按鈕來切換背景顏色。", "stable-diffusion-webui-state": "stable-diffusion-webui-state", "Preserves the UI state after reload/restart.": "Preserves the UI state after reload/restart.", "text2video": "text2video", "Brings a range of true text2video models, such as ModelScope and Videocrafter, into the WebUI.": "Brings a range of true text2video models, such as ModelScope and Videocrafter, into the WebUI.", "Aspect Ratio Helper": "長寬比小幫手", "Easily scale dimensions while retaining the same aspect ratio.": "Easily scale dimensions while retaining the same aspect ratio.", "Canvas Zoom": "Canvas Zoom", "Added the ability to scale Inpaint, Sketch, and Inpaint Sketch. Adds useful hotkeys": "Added the ability to scale Inpaint, Sketch, and Inpaint Sketch. Adds useful hotkeys", "Regional Prompter": "Regional Prompter", "Specify different prompts for different regions; an alternative method and potential improvement to latent couple.": "Specify different prompts for different regions; an alternative method and potential improvement to latent couple.", "Auto Translate": "自動翻譯", "Language extension allows users to write prompts in their native language and automatically translate UI, without the need to manually download configuration files. New plugins can also be translated.": "Language extension allows users to write prompts in their native language and automatically translate UI, without the need to manually download configuration files. New plugins can also be translated.", "Allows users to generate images based on prompts written in 50 different languages. It translates the prompts to english from a selected source language before generating the image.": "允許使用者根據用50種不同語言寫成的提示詞來產生圖像。在產生圖像之前，它會將來自所選源語言的提示翻譯成英語。", "Abysz LAB": "Abysz LAB", "Temporal Coherence Tools": "Temporal Coherence Tools", "Negative Prompt Weight": "反向提示詞權重", "Allows users to set a global weight for the negative prompt.": "允許使用者設定反向提示詞的全域權重", "Discord - Dynamic Rich Presence": "Discord 動態狀態訊息", "Will show your current sd model selected. Also showing if you are idle, or generating something - in that case, total image/s being generated.": "在 Discord 動態狀態顯示目前選用的模型名稱。另外也會顯示閒置中或正在產生圖像等訊息。", "PBRemTools": "PBRemTools", "PBRemTools(Precise background remover tools) is a collection of tools to crop backgrounds from a single picture with high accuracy.": "PBRemTools(Precise background remover tools) is a collection of tools to crop backgrounds from a single picture with high accuracy.", "a1111-sd-webui-lycoris": "a1111-sd-webui-lycoris", "No longer needed for webui >= 1.5.0, Load lycoris: non-conventional rank adapters; in separate networks gallery tab.": "No longer needed for webui >= 1.5.0, Load lycoris: non-conventional rank adapters; in separate networks gallery tab.", "sd-canvas-editor": "sd-canvas-editor", "A full capability canvas editor which you can use layer, text, image, elements and so on.": "A full capability canvas editor which you can use layer, text, image, elements and so on.", "Infinite Zoom": "無限縮放", "allows users to create infinite zoom effect videos using stable diffusion outpainting method.": "使用 stable diffusion 向外繪製建立無限縮放效果影片。", "Eye Mask": "Eye Mask", "Puts an end to poorly drawn eyes by automatically identifying and redrawing them.": "Puts an end to poorly drawn eyes by automatically identifying and redrawing them.", "zh_CN Localization": "簡體中文本地化語言包", "Simplified Chinese localization, recommend using with Bilingual Localization.": "簡體中文本地化，推薦搭配雙語翻譯對照擴充功能使用。", "zh_TW Localization": "正體中文在地化語言包", "Traditional Chinese localization": "正體中文本地化", "ko_KR Localization": "韓文在地化語言包", "Korean localization": "韓語本地化", "th_TH Localization": "泰語本地化語言包", "Thai localization": "泰語本地化", "es_ES Localization": "西班牙語本地化語言包", "Spanish localization": "西班牙語本地化", "it_IT Localization": "義大利語本地化語言包", "Italian localization": "義大利語本地化", "de_DE Localization": "德語本地化語言包", "German localization": "德語本地化", "ja_JP Localization": "日文本地化語言包", "Japanese localization": "日語本地化", "pt_BR Localization": "巴西葡萄牙語本地化語言包", "Brazillian portuguese localization": "巴西葡萄牙語本地化", "tr_TR Localization": "土耳其語本地化語言包", "Turkish localization": "土耳其語本地化", "no_NO Localization": "挪威語本地化語言包", "Norwegian localization": "挪威語本地化", "ru_RU Localization": "俄語本地化語言包", "Russian localization": "俄語本地化", "fi_FI Localization": "芬蘭語本地化語言包", "Finnish localization": "芬蘭語本地化", "zh_Hans Localization": "簡體中文本地化語言包", "Simplified Chinese localization.": "簡體中文本地化。", "old localizations": "過時的本地化語言包", "Old unmaintained localizations that used to be a part of main repository": "曾經在主分支上但現在不再維護的舊語言包", "Model Organizer": "Model Organizer", "Allows to store and manage own model collections, add information, notes, previews, download links of model. Easily download from any external direct link or shared file link from Google Drive. Share own models collection with json file or use remote Firestore database to make it available and synced on several devices.": "Allows to store and manage own model collections, add information, notes, previews, download links of model. Easily download from any external direct link or shared file link from Google Drive. Share own models collection with json file or use remote Firestore database to make it available and synced on several devices.", "Model Preset Manager": "Model Preset Manager", "Lets you create and apply presets per model for all generation data (e.g. prompt, negative prompt, cfg_scale, resolution, sampler, clip skip, steps, etc). Also automatically fetches model trigger words and thumbnails from Civitai.": "Lets you create and apply presets per model for all generation data (e.g. prompt, negative prompt, cfg_scale, resolution, sampler, clip skip, steps, etc). Also automatically fetches model trigger words and thumbnails from Civitai.", "SD-CN-Animation": "SD-CN-Animation", "Allows users to create video2video and text2video animations using any SD models as a backbone. Please, make sure that 'sd-webui-controlnet' extension is also installed.": "Allows users to create video2video and text2video animations using any SD models as a backbone. Please, make sure that 'sd-webui-controlnet' extension is also installed.", "Model toolkit": "Model toolkit", "A Multipurpose toolkit for pruning, editing and fixing models.": "A Multipurpose toolkit for pruning, editing and fixing models.", "sd-webui-prompt-all-in-one": "sd-webui-prompt-all-in-one", "Improve the user experience of the prompt/negative prompt input box. It has a more intuitive and powerful input interface that offers features such as automatic translation, history records, and favorites.": "Improve the user experience of the prompt/negative prompt input box. It has a more intuitive and powerful input interface that offers features such as automatic translation, history records, and favorites.", "sd-model-preview-xd": "sd-model-preview-xd", "Adds model, LoRA and embedding previews to the UI including preview images, descriptions and LoRA prompt lists.": "Adds model, LoRA and embedding previews to the UI including preview images, descriptions and LoRA prompt lists.", "!After Detailer": "!After Detailer", "Automatic detection, masking and inpainting tool for details": "Automatic detection, masking and inpainting tool for details", "Weight Gradient": "Weight Gradient", "Allows you to dynamically change the weights of tokens during generation. Useful in morphing.": "Allows you to dynamically change the weights of tokens during generation. Useful in morphing.", "One Button Prompt": "One Button Prompt", "One Button Prompt is a script for beginners and advanced users that generates an entire prompt from scratch. It is random, but controlled. You simply load up the script and press generate, and let it inspire you.": "One Button Prompt is a script for beginners and advanced users that generates an entire prompt from scratch. It is random, but controlled. You simply load up the script and press generate, and let it inspire you.", "Miaoshouai Assistant": "Miaoshouai Assistant", "Miaoshouai Assistant allows you to enhance your automatic1111 webui user experience, including updating boot settings, freeup vram, managing and downloading your models from civitai.com and liandange.com, generate prompts from chatgpt all through a single tab.": "Miaoshouai Assistant allows you to enhance your automatic1111 webui user experience, including updating boot settings, freeup vram, managing and downloading your models from civitai.com and liandange.com, generate prompts from chatgpt all through a single tab.", "miniPaint": "miniPaint", "The miniPaint extension allows for better image editing capabilites. Edit images simply direct inside the webui!": "The miniPaint extension allows for better image editing capabilites. Edit images simply direct inside the webui!", "StableSR": "StableSR", "WebUI extension for StableSR - a powerful upscaler for both realistic and anime images": "WebUI extension for StableSR - a powerful upscaler for both realistic and anime images", "Web UI client queue": "Web UI client queue", "Adds a queue function to the web ui that processes a set of settings one or more times, it can then load a different set of settings and so on.": "Adds a queue function to the web ui that processes a set of settings one or more times, it can then load a different set of settings and so on.", "Distributed": "Distributed", "Generate batches more quickly by chaining together separate webui instances": "Generate batches more quickly by chaining together separate webui instances", "StableStudio Adapter": "StableStudio Adapter", "A custom extension for webui to extend rest APIs to do some local operations, using in StableStudio.": "A custom extension for webui to extend rest APIs to do some local operations, using in StableStudio.", "Quick Tab Switch": "Quick Tab Switch", "Simple tab switcher for Stable Diffusion WebUI. From now on, no matter how many tabs you add, no more finding for them by yourself!": "Simple tab switcher for Stable Diffusion WebUI. From now on, no matter how many tabs you add, no more finding for them by yourself!", "Lua": "Lua", "Generate images with Lua scripts in Stable Diffusion webui.": "Generate images with Lua scripts in Stable Diffusion webui.", "Model Downloader": "Model Downloader", "Alternative tool for Downloading Models, Recommended for Cloud users.": "Alternative tool for Downloading Models, Recommended for Cloud users.", "Styles Editor": "Styles Editor", "Adds a spreadsheet-style editor for saved styles, with support for filtering, search and replace, and subdividing styles into multiple files": "Adds a spreadsheet-style editor for saved styles, with support for filtering, search and replace, and subdividing styles into multiple files", "Clip I/O": "Clip I/O", "The extension allows you to investigate embeddings/conditioning and feed conditioning to Stable Diffusion.": "The extension allows you to investigate embeddings/conditioning and feed conditioning to Stable Diffusion.", "Inpaint Anything": "Inpaint Anything", "The Inpaint Anything extension performs SD inpainting, cleaner, ControlNet inpaint, and sending a mask to img2img, using a mask selected from the segmentation output of Segment Anything.": "The Inpaint Anything extension performs SD inpainting, cleaner, ControlNet inpaint, and sending a mask to img2img, using a mask selected from the segmentation output of Segment Anything.", "QR Code Generator": "QR Code Generator", "Create QR Codes for ControlNet.": "Create QR Codes for ControlNet.", "sd-webui-roop": "sd-webui-roop", "Enable face swapping with reference image.": "Enable face swapping with reference image.", "sd-webui-color-enhance": "sd-webui-color-enhance", "Enhance image colors using GIMP/GEGL \"Color Enhance\" algorithm.": "Enhance image colors using GIMP/GEGL \"Color Enhance\" algorithm.", "sd-webui-bluescape": "sd-webui-bluescape", "Upload generated images to a Bluescape workspace for review and collaboration.": "Upload generated images to a Bluescape workspace for review and collaboration.", "sd-webui-prompt_history": "sd-webui-prompt_history", "Automatic store your generation info with image and apply back anytime.": "Automatic store your generation info with image and apply back anytime.", "Danbooru Prompt": "Danbooru Prompt", "Fetch tags from Danbooru images link": "Fetch tags from Danbooru images link", "Pixel art": "Pixel art", "Extension that provides basic functionality for pixel art: downscaling, palette limiting, grayscale, black&white, ability to change image colors with custom color palette": "Extension that provides basic functionality for pixel art: downscaling, palette limiting, grayscale, black&white, ability to change image colors with custom color palette", "Lobe Theme": "Lobe Theme", "The modern theme for stable diffusion webui, legacy verison a.k.a kitchen theme.": "The modern theme for stable diffusion webui, legacy verison a.k.a kitchen theme.", "Kitchen Theme": "Kitchen 主題", "Custom Theme.": "自定義主題。", "IF_prompt_MKR": "IF_prompt_MKR", "Creates prompts using a local LlMs via Oobabooga text webUI API": "Creates prompts using a local LlMs via Oobabooga text webUI API", "3D Editor": "3D Editor", "3D modeling features (add/edit basic elements, load your custom model, modify scene and so on), then send screenshot to txt2img or img2img as your ControlNet's reference image, basing on ThreeJS editor.": "3D modeling features (add/edit basic elements, load your custom model, modify scene and so on), then send screenshot to txt2img or img2img as your ControlNet's reference image, basing on ThreeJS editor.", "Aspect Ratio selector plus": "Aspect Ratio selector plus", "Fork of Aspect Ratio selector with new features and logic for aspect ratio": "Fork of Aspect Ratio selector with new features and logic for aspect ratio", "SD Delete Button": "SD Delete Button", "Add a delete button for txt2img and img2img using Send2Trash": "Add a delete button for txt2img and img2img using Send2Trash", "sd-webui-qrcode-toolkit": "sd-webui-qrcode-toolkit", "Integration with Anthony's QR Toolkit for easy QR Code generation and verification.": "Integration with Anthony's QR Toolkit for easy QR Code generation and verification.", "SadTalker": "SadTalker", "Generating talking head videos with facial image and speech audio": "Generating talking head videos with facial image and speech audio", "Auto-Photoshop-StableDiffusion-Plugin": "Auto-Photoshop-StableDiffusion-Plugin", "Adds API routes for Auto-Photoshop-StableDiffusion-Plugin": "Adds API routes for Auto-Photoshop-StableDiffusion-Plugin", "Civitai Shortcut": "Civitai Shortcut", "This extension allows you to register the models available on civitai as favorites (shortcuts) in sdui, and then you can download the models using the registered shortcuts when needed.": "This extension allows you to register the models available on civitai as favorites (shortcuts) in sdui, and then you can download the models using the registered shortcuts when needed.", "WD 1.4 Tagger": "WD 1.4 標記器", "Interrogates single or multiple image files using various alternative models, similar to deepdanbooru interrogate.": "使用各種替代模型檢查單一或多個圖像檔，類似於 deepdanbooru 的檢查。", "Loopback Scaler": "Loopback Scaler", "Iteratively improves image quality and detail via user-controlled, gradual resolution increments.": "Iteratively improves image quality and detail via user-controlled, gradual resolution increments.", "Mask2Background": "Mask2Background", "Take a png image, generate a background and mask, then send it to img2img to generate a new backgrou": "Take a png image, generate a background and mask, then send it to img2img to generate a new backgrou", "ComfyUI": "ComfyUI", "Embed ComfyUI workflows in different sections of the Webui": "Embed ComfyUI workflows in different sections of the Webui", "GPU temperature protection": "GPU temperature protection", "Pause image generation when GPU is to hot, suppots NVIDIA & AMD GPUs": "Pause image generation when GPU is to hot, suppots NVIDIA & AMD GPUs", "zoom-image": "zoom-image", "Pan and Zoom for fullscreen image viewer with mouse and gesture.": "Pan and Zoom for fullscreen image viewer with mouse and gesture.", "Shutdown button": "Shutdown button", "Adds a button in quick settings for killing webui": "Adds a button in quick settings for killing webui", "Latent Upscale": "Latent Upscale", "Provides more options for latent upscale in img2img, surpassing those offered by Hires Fix for the txt2img process.": "Provides more options for latent upscale in img2img, surpassing those offered by Hires Fix for the txt2img process.", "sd-history-slider": "sd-history-slider", "A slider change the prompt based on the history of what was used.": "A slider change the prompt based on the history of what was used.", "prompts filter": "prompts filter", "Filter out banned words in prompts and negative_prompts, and also filter out duplicate prompts and empty prompts.": "Filter out banned words in prompts and negative_prompts, and also filter out duplicate prompts and empty prompts.", "sd-webui-animatediff": "sd-webui-animatediff", "This extension integrates AnimateDiff into WebUI and generates GIF just like generating images": "This extension integrates AnimateDiff into WebUI and generates GIF just like generating images", "Dynamic Javascript": "Dynamic Javascript", "Embed Javascript code blocks in positive and negative prompts.": "Embed Javascript code blocks in positive and negative prompts.", "Detection Detailer": "檢測細緻化", "Dotgeo(hijack) Detection Detailer. Fork of ddetailer. Object detection and auto-mask extension for Stable Diffusion web UI.": "Dotgeo(hijack) Detection Detailer. Fork of ddetailer. Object detection and auto-mask extension for Stable Diffusion web UI.", "seamless-tile-inpainting": "seamless-tile-inpainting", "A script for making tiles seamless using inpainting. Designed for SD1.5 inpainting model at 512x512, but should work fine with other inpainting models.": "A script for making tiles seamless using inpainting. Designed for SD1.5 inpainting model at 512x512, but should work fine with other inpainting models.", "FaceSwapLab": "FaceSwapLab", "Extended faceswap with multiple faceswaps, inpainting, checkpoints.": "Extended faceswap with multiple faceswaps, inpainting, checkpoints.", "Style Selector for SDXL 1.0": "Style Selector for SDXL 1.0", "a Automatic1111 Extension allows users to select and apply different styles to their inputs using SDXL 1.0.": "a Automatic1111 Extension allows users to select and apply different styles to their inputs using SDXL 1.0.", "sd-webui-oldsix-prompt": "sd-webui-oldsix-prompt", "Prompt library - comes with built-in Chinese libeary": "Prompt library - comes with built-in Chinese libeary", "Custom Hires Fix": "Custom Hires Fix", "Adds custom hires fix with advanced features to improve details.": "Adds custom hires fix with advanced features to improve details.", "Refiner": "Refiner", "Adds support for SD XL refiner models, it's extending the pipeline to process the last steps with the refiner models Unet.": "Adds support for SD XL refiner models, it's extending the pipeline to process the last steps with the refiner models Unet.", "sd-webui-deoldify": "sd-webui-deoldify", "DeOldify for Stable Diffusion WebUI:Colorize of old photos and old video, based on deoldify": "DeOldify for Stable Diffusion WebUI:Colorize of old photos and old video, based on deoldify", "sd-wav2lip-uhq": "sd-wav2lip-uhq", "All-in-one solution for creating high-quality lip-sync videos based on video or image": "All-in-one solution for creating high-quality lip-sync videos based on video or image", "Controlnet Fastload": "Controlnet Fastload", "Save and load controlnet parameters": "Save and load controlnet parameters", "LoRA Control": "LoRA Control", "Dynamically control the weights of LoRAs during image generation": "Dynamically control the weights of LoRAs during image generation", "Wildcards": "萬用字元", "Allows you to use __name__ syntax in your prompt to get a random line from a file named name.txt in the wildcards directory.": "Allows you to use __name__ syntax in your prompt to get a random line from a file named name.txt in the wildcards directory.", "SD Ratio Lock": "SD Ratio Lock", "Locks image aspect ratio": "Locks image aspect ratio", "sd-webui-chatgpt": "sd-webui-chatgpt", "Using ChatGPT in Stable Diffusion web UI. When you say something like 'generate an image', ChatGPT will automatically generate a prompt and generate an image.": "Using ChatGPT in Stable Diffusion web UI. When you say something like 'generate an image', ChatGPT will automatically generate a prompt and generate an image.", "sd-webui-auto-tweet.json": "sd-webui-auto-tweet.json", "The generated images are automatically posted to your Twitter feed. There is also a button to post the generated image to Twitter.": "The generated images are automatically posted to your Twitter feed. There is also a button to post the generated image to Twitter.", "zh_Hant Localization": "zh_Hant Localization", "Traditional Chinese localization (mixin zh_TW and zh_Hans)": "Traditional Chinese localization (mixin zh_TW and zh_Hans)", "SD Webui Vectorscope CC": "SD Webui Vectorscope CC", "Adjust the output images brightness contrast saturation through latent noise manipulation during generation": "Adjust the output images brightness contrast saturation through latent noise manipulation during generation", "Prompt Formatter - by uwidev": "Prompt Formatter - by uwidev", "Remove excess spaces and convert nested brackets": "Remove excess spaces and convert nested brackets", "Prompt Format - by Haoming02": "Prompt Format - by Haoming02", "Remove duplicated spaces and commas.": "Remove duplicated spaces and commas.", "FABRIC": "FABRIC", "Personalizing Diffusion Models with Iterative Feedback, a training-free approach that conditions the diffusion process on a set of feedback images": "Personalizing Diffusion Models with Iterative Feedback, a training-free approach that conditions the diffusion process on a set of feedback images", "Webpage close confirmation dialogue": "Webpage close confirmation dialogue", "Adds a confirmation dialogue when you try to \"close\" leave\" or \"reload\" the webpage": "Adds a confirmation dialogue when you try to \"close\" leave\" or \"reload\" the webpage", "sd-webui-discord-ex": "sd-webui-discord-ex", "Supports distributed deployment of SD node's Stable Diffusion WebUi Discord bot": "Supports distributed deployment of SD node's Stable Diffusion WebUi Discord bot", "CivitAI Browser+": "CivitAI Browser+", "Extension to access CivitAI via WebUI: download, delete, scan for updates, list installed models, assign tags, and boost downloads with multi-threading.": "Extension to access CivitAI via WebUI: download, delete, scan for updates, list installed models, assign tags, and boost downloads with multi-threading.", "Img2img batch interrogator": "Img2img batch interrogator", "The extension runs the interrogator before processing each image": "The extension runs the interrogator before processing each image", "SD Masonry Gallery": "SD Masonry Gallery", "An images tab to display local images in a compact masonry gallery.": "An images tab to display local images in a compact masonry gallery.", "sd-webui-depth-lib": "sd-webui-depth-lib", "Depth map library for use with the ControlNet extension": "Depth map library for use with the ControlNet extension", "Stable Diffusion Webui Civitai Helper": "Stable Diffusion Webui Civitai Helper", "Download or populate models with metadata and preview image from civitai.com": "Download or populate models with metadata and preview image from civitai.com", "Scenario loader": "Scenario loader", "A series of tool to make it easier to create images.": "A series of tool to make it easier to create images.", "PromptsBrowser": "PromptsBrowser", "An extension to quickly work with, explore, and catalog prompts.": "An extension to quickly work with, explore, and catalog prompts.", "Model Mixer": "Model Mixer", "Checkpoint Model Mixer/Merger extension - merges models without saving a merged model, and is used for image generation. Support Merge Block Weights, XYZ plots, etc.": "Checkpoint Model Mixer/Merger extension - merges models without saving a merged model, and is used for image generation. Support Merge Block Weights, XYZ plots, etc.", "Fast PNG Info": "Fast PNG Info", "Allows you to view PNG Info of an image without upload to webui's backend server, significantly faster when webui is hosted remotely like on Colab.": "Allows you to view PNG Info of an image without upload to webui's backend server, significantly faster when webui is hosted remotely like on Colab.", "sd-webui-mov2mov": "sd-webui-mov2mov", "Process videos frame by frame and automatically merge and export": "Process videos frame by frame and automatically merge and export", "EasyPhoto": "EasyPhoto", "Support easy photo generation with an online-trained LoRA model that guarantees high-quality output images closely relevant to the input.": "Support easy photo generation with an online-trained LoRA model that guarantees high-quality output images closely relevant to the input.", "sd-webui-rich-text": "sd-webui-rich-text", "An extension allows using a rich-text editor for text-to-image generation (https://github.com/songweige/rich-text-to-image).": "An extension allows using a rich-text editor for text-to-image generation (https://github.com/songweige/rich-text-to-image).", "sd-webui-bg-mask": "sd-webui-bg-mask", "Generate a mask for the image background": "Generate a mask for the image background", "Ranbooru": "Ranbooru", "Get random prompts from different boorus with a lot of creative features to influence the prompts. Works with txt2img and img2img": "Get random prompts from different boorus with a lot of creative features to influence the prompts. Works with txt2img and img2img", "CivBrowser": "CivBrowser", "Extension to search and download Civitai models in multiple tabs. Save model information. Send sample infotext to txt2img.": "Extension to search and download Civitai models in multiple tabs. Save model information. Send sample infotext to txt2img.", "NSFW Blurrer-NSFWJS": "NSFW Blurrer-NSFWJS", "Blurs NSFW images using NSFWJS, based on onnxmodel ": "Blurs NSFW images using NSFWJS, based on onnxmodel ", "NegPiP": "NegPiP", "Enable negative strength in the prompt. This will have a stronger effect than a negative prompt.": "Enable negative strength in the prompt. This will have a stronger effect than a negative prompt.", "CD(Color/Detail) Tuner": "CD(Color/Detail) Tuner", "Adjust color tone, brightness, and level of detailing using a different mechanism of LoRA or ADtailer": "Adjust color tone, brightness, and level of detailing using a different mechanism of LoRA or ADtailer", "DevDark theme": "DevDark theme", "Custom css based on Catppuccin, enable / disabled via extensions tab.": "Custom css based on Catppuccin, enable / disabled via extensions tab.", "auxiliary API": "auxiliary API", "Adds API routes for uploading, removing, syncing models and etc": "Adds API routes for uploading, removing, syncing models and etc", "ReActor": "ReActor", "Fast and Simple FaceSwap Extension with a lot of improvements. Read README.md, additional installation steps required": "Fast and Simple FaceSwap Extension with a lot of improvements. Read README.md, additional installation steps required", "TensorRT": "TensorRT", "TensorRT acceleration for Stable Diffusion on NVIDIA RTX GPUs.": "TensorRT acceleration for Stable Diffusion on NVIDIA RTX GPUs.", "encrypt-image": "encrypt-image", "Encrypt and save the image to the disk to reduce the risk of account suspension when storing images in public clouds. When installing and starting, you need to add the parameter --encrypt-pass=your password.": "Encrypt and save the image to the disk to reduce the risk of account suspension when storing images in public clouds. When installing and starting, you need to add the parameter --encrypt-pass=your password.", "NudeNet NSFW Censor": "NudeNet NSFW Censor", "Customizable detection and censoring of NSFW portions within an image using NudeNet.": "Customizable detection and censoring of NSFW portions within an image using NudeNet.", "Latent Consistency Models": "Latent Consistency Models", "Generate high quality images in just 4 steps. Run Latent Consistency Models with Automatic1111.": "Generate high quality images in just 4 steps. Run Latent Consistency Models with Automatic1111.", "Stable Diffusion checkpoint": "Stable Diffusion 模型權重存檔點", "txt2img": "文生圖", "img2img": "圖生圖", "Extras": "附加功能", "PNG Info": "圖片資訊", "Checkpoint Merger": "模型權重存檔點合併", "Train": "訓練", "Settings": "設定", "Extensions": "擴充功能", "Prompt": "提示詞", "Negative prompt": "反向提示詞", "Interrupt": "中止", "Skip": "跳過", "Generate": "產生", "Run": "執行", "Styles": "樣式", "Label": "標記", "File": "檔案", "Drop File Here": "拖曳檔案到此", "or": "or", "Click to Upload": "點選以上傳", "Textual Inversion": "文本反轉（Textual Inversion）", "Hypernetworks": "超網路（Hypernetwork）", "Checkpoints": "模型權重存檔點", "Lora": "LoRA", "Refresh": "重新整理", "Nothing here. Add some content to the following directories:": "這裡什麼都沒有。加入一些內容至以下目錄：", "replace preview": "取代預覽", "Textbox": "文字方塊", "Save preview": "儲存預覽", "Sampling method": "取樣方法", "Sampling steps": "取樣步驟", "Restore faces": "面部修復", "Tiling": "可平鋪", "Hires. fix": "高解析度修正（Hires. fix）", "resize: from": "resize: from", "512x512": "512x512", "to": "to", "1024x1024": "1024x1024", "Upscaler": "放大演算法", "Hires steps": "高解析步驟", "Denoising strength": "重繪幅度", "Upscale by": "放大至", "Resize width to": "將寬度調整至", "Resize height to": "將高度調整至", "Hires sampling method": "Hires sampling method", "Hires prompt": "Hires prompt", "Hires negative prompt": "Hires negative prompt", "Width": "寬度", "Height": "高度", "Batch count": "產生批次", "Batch size": "每批數量", "CFG Scale": "提示詞相關性（CFG）", "Seed": "隨機種子", "Extra": "▼", "Variation seed": "差異隨機種子", "Variation strength": "差異強度", "Resize seed from width": "寬度（縮放種子）", "Resize seed from height": "高度（縮放種子）", "Override settings": "覆寫設定", "Script": "指令碼", "Put variable parts at start of prompt": "把可變部分放在提示詞的開頭", "Use different seed for each picture": "對每張圖片使用不同的種子", "Select prompt": "選擇提示詞", "positive": "正向", "negative": "反向", "Select joining char": "選擇接合字母", "comma": "逗號", "space": "空間", "Grid margins (px)": "網格邊距（px）", "Iterate seed every line": "每行輸入都換一個隨機種子", "Use same random seed for all lines": "每行輸入都使用同一個隨機種子", "List of prompt inputs": "提示詞輸入列表", "Upload prompt inputs": "上傳提示詞輸入檔案", "X type": "X 軸類型", "X values": "X 軸值", "Y type": "Y 軸類型", "Y values": "Y 軸值", "Z type": "Z 軸類型", "Z values": "Z 軸值", "Draw legend": "在圖表中包括軸類型和值", "Keep -1 for seeds": "保持隨機種子為 -1", "Include Sub Images": "包括子圖像", "Include Sub Grids": "包括子網格", "Swap X/Y axes": "交換 X/Y 軸", "Swap Y/Z axes": "交換 Y/Z 軸", "Swap X/Z axes": "交換 X/Z 軸", "Save": "儲存", "Zip": "Zip", "Send to img2img": ">> 圖生圖", "Send to inpaint": ">> 局部重繪", "Send to extras": ">> 附加功能", "Interrogate\nCLIP": "CLIP\n反推提示詞", "Interrogate\nDeepBooru": "DeepBooru\n反推提示詞", "Sketch": "素描", "Inpaint": "局部重繪", "Inpaint sketch": "修復素描", "Inpaint upload": "修復上傳", "Batch": "批次", "Image for img2img": "圖生圖的圖像", "Drop Image Here": "拖曳圖像到此", "Copy image to:": "複製圖片到：", "sketch": "素描", "inpaint": "修復", "inpaint sketch": "修復草圖", "Image for inpainting with mask": "用於局部重繪並手動畫遮罩的圖像", "Color sketch inpainting": "彩繪修復", "Mask": "遮罩", "Process images in a directory on the same machine where the server is running.": "處理伺服器主機上的某一個目錄中的圖像。", "Use an empty output directory to save pictures normally instead of writing to the output directory.": "輸出圖像到一個空目錄，而非設定裡指定的輸出目錄。", "Add inpaint batch mask directory to enable inpaint batch processing.": "新增修補批次遮罩目錄以啟用批次處理修補功能。", "Input directory": "輸入目錄", "Output directory": "輸出目錄", "Inpaint batch mask directory (required for inpaint batch processing only)": "修補批次遮罩目錄（僅適用於批次處理修補功能）", "Resize mode": "縮放模式", "Just resize": "拉伸", "Crop and resize": "裁剪", "Resize and fill": "填充", "Just resize (latent upscale)": "僅重新調整大小（潛在變數放大）", "Mask blur": "遮罩模糊", "Mask transparency": "遮罩透明度", "Mask mode": "遮罩模式", "Inpaint masked": "重繪遮罩內容", "Inpaint not masked": "重繪非遮罩內容", "Masked content": "遮罩內容", "fill": "填充", "original": "原圖", "latent noise": "潛在變數噪點", "latent nothing": "潛在變數數值零", "Inpaint area": "修復區域", "Whole picture": "全圖", "Only masked": "僅被遮罩", "Only masked padding, pixels": "僅填充遮罩部分（像素）", "Resize to": "Resize to", "Resize by": "Resize by", "Scale": "放大倍率", "no image selected": "no image selected", "Unused": "Unused", "Image CFG Scale": "圖像提示詞相關性", "should be 2 or lower.": "必須小於等於 2", "Override `Sampling method` to Euler?(this method is built for it)": "覆寫「採樣方法」為 Euler？（這個方法就是為它設計的）", "Override `prompt` to the same value as `original prompt`?(and `negative prompt`)": "覆寫「提示詞」為「初始提示詞」？（「反向提示詞」同理）", "Original prompt": "初始提示詞", "Original negative prompt": "初始反向提示詞", "Override `Sampling Steps` to the same value as `Decode steps`?": "覆寫「取樣疊代步數」為「解碼疊代步數」？", "Decode steps": "解碼疊代步數", "Override `Denoising strength` to 1?": "覆寫「重繪幅度」為 1？", "Decode CFG scale": "解碼提示詞相關性", "Randomness": "隨機度", "Sigma adjustment for finding noise for image": "為尋找圖中噪點的希格瑪（Sigma）調整", "Loops": "疊代次數", "Final denoising strength": "最終重繪幅度", "Denoising strength curve": "降噪強度曲線", "Append interrogated prompt at each iteration": "在每次疊代中附加詢問提示。", "Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8": "推薦設定：取樣疊代步數：80-100，取樣器：Euler a，重繪幅度：0.8", "Pixels to expand": "拓展的畫素數", "Outpainting direction": "向外繪製的方向", "left": "左", "right": "右", "up": "上", "down": "下", "Fall-off exponent (lower=higher detail)": "衰減指數（越小細節越好）", "Color variation": "色彩變化", "Will upscale the image by the selected scale factor; use width and height sliders to set tile size": "將會通過所選擇的縮放因子將圖像放大；使用寬度和高度滑塊設定磚大小", "Tile overlap": "圖塊重疊的畫素", "Scale Factor": "比例因子", "None": "無", "Lanczos": "Lanczos", "Nearest": "最鄰近整數縮放（Nearest）", "ESRGAN_4x": "ESRGAN_4x", "LDSR": "LDSR", "R-ESRGAN 4x+": "R-ESRGAN 4x+", "R-ESRGAN 4x+ Anime6B": "R-ESRGAN 4x+ Anime6B", "ScuNET GAN": "ScuNET GAN", "ScuNET PSNR": "ScuNET PSNR", "SwinIR 4x": "SwinIR 4x", "Single Image": "單張圖像", "Batch Process": "批次處理", "Batch from Directory": "從目錄進行批量處理", "Source": "來源", "Show result images": "顯示輸出圖像", "Scale by": "等比縮放", "Scale to": "指定解析度縮放", "Resize": "縮放比例", "Crop to fit": "裁剪以適應寬高比", "Upscaler 2 visibility": "放大演算法 2 可見度", "GFPGAN visibility": "GFPGAN 可見度", "CodeFormer visibility": "CodeFormer 可見度", "CodeFormer weight (0 = maximum effect, 1 = minimum effect)": "CodeFormer 權重 （為 0 時效果最大，為 1 時效果最小）", "Send to txt2img": ">> 文生圖", "A weighted sum will be used for interpolation. Requires two models; A and B. The result is calculated as A * (1 - M) + B * M": "插值將使用加權和。需要兩個模型；A和B。結果為A *（1-M）+ B * M計算。", "Primary model (A)": "主要模型（A）", "Secondary model (B)": "次要模型（B）", "Tertiary model (C)": "第三模型（C）", "Custom Name (Optional)": "自訂名稱 （可選）", "Multiplier (M) - set to 0 to get model A": "倍率（M）- 設為 0 等價於模型 A", "Interpolation Method": "插值方法", "No interpolation": "無插值", "Weighted sum": "加權和", "Add difference": "加入差分", "Checkpoint format": "模型權重檢查點格式", "ckpt": "ckpt", "safetensors": "safetensors", "Save as float16": "以 float16 儲存", "Save metadata (.safetensors only)": "Save metadata (.safetensors only)", "Copy config from": "複製配置自", "A, B or C": "A, B or C", "B": "B", "C": "C", "Don't": "不要", "Bake in VAE": "嵌入VAE", "Discard weights with matching name": "丟棄名稱相符的權重", "Merge": "合併", "See": "檢視", "wiki": "wiki 文件", "for detailed explanation.": "以了解詳細說明", "Create embedding": "建立嵌入", "Create hypernetwork": "建立超網路（Hypernetwork）", "Preprocess images": "圖像預處理", "Name": "名稱", "Initialization text": "初始化文字", "Number of vectors per token": "每個標記的向量數", "Overwrite Old Embedding": "覆寫舊的嵌入", "Modules": "模組", "Enter hypernetwork layer structure": "輸入超網路（Hypernetwork）層結構", "Select activation function of hypernetwork. Recommended : Swish / Linear(none)": "選擇超網路（Hypernetwork）的激活函數。建議：Swish／Linear（線性，等於不用）", "Select Layer weights initialization. Recommended: Kaiming for relu-like, Xavier for sigmoid-like, Normal otherwise": "選擇層權重初始化方式。建議：relu-like 選 Kaiming，sigmoid-like 選 Xavier，其它選 Normal。", "Add layer normalization": "加入層歸一化", "Use dropout": "採用 dropout 防止過擬合", "Enter hypernetwork Dropout structure (or empty). Recommended : 0~0.35 incrementing sequence: 0, 0.05, 0.15": "輸入 Hypernetwork Dropout 結構（或空）。推薦：0~0.35 的遞增序列：0、0.05、0.15", "Overwrite Old Hypernetwork": "覆寫舊的超網路（Hypernetwork）", "Source directory": "來源目錄", "Destination directory": "目標目錄", "Existing Caption txt Action": "對現有的文字文件進行描述文字的動作", "Keep original size": "Keep original size", "Create flipped copies": "建立鏡像副本", "Split oversized images": "分割過大的圖像", "Auto focal point crop": "自動焦點裁切", "Auto-sized crop": "自動選擇大小的剪裁", "Use BLIP for caption": "使用 BLIP 產生描述（自然語言描述）", "Use deepbooru for caption": "使用 deepbooru 產生描述（標記）", "Split image threshold": "圖像分割閾值", "Split image overlap ratio": "分割圖像重疊的比率", "Focal point face weight": "焦點面部權重", "Focal point entropy weight": "焦點熵權重", "Focal point edges weight": "焦點線條權重", "Create debug image": "建立除錯圖像", "Each image is center-cropped with an automatically chosen width and height.": "每個圖像以自動選擇的寬度和高度為中心進行裁剪。", "Dimension lower bound": "維度下限", "Dimension upper bound": "維度上限", "Area lower bound": "面積下限", "Area upper bound": "面積上限", "Resizing objective": "調整大小目標", "Maximize area": "最大化面積", "Minimize error": "最小化誤差", "Error threshold": "誤差閾值", "Preprocess": "預處理", "Train an embedding or Hypernetwork; you must specify a directory with a set of 1:1 ratio images": "訓練嵌入或者超網路；必須指定一個具有一組 1:1 比例圖像的目錄", "[wiki]": "[wiki]", "Embedding": "嵌入", "Hypernetwork": "超網路", "Embedding Learning rate": "嵌入學習率", "Hypernetwork Learning rate": "超網路學習率", "Gradient Clipping": "梯度修剪", "Gradient accumulation steps": "梯度累加步數", "Dataset directory": "資料集目錄", "Log directory": "日誌目錄", "Prompt template": "提示模板", "Do not resize images": "不要調整影像大小", "Max steps": "最大疊代步數", "Save an image to log directory every N steps, 0 to disable": "每 N 步儲存一張圖像到記錄目錄，0 表示停用", "Save a copy of embedding to log directory every N steps, 0 to disable": "每 N 步將嵌入的副本儲存到記錄目錄，0 表示停用", "Use PNG alpha channel as loss weight": "使用 PNG 透明通道作為損失權重", "Save images with embedding in PNG chunks": "儲存圖像，並在 PNG 圖片檔案中嵌入檔案", "Read parameters (prompt, etc...) from txt2img tab when making previews": "進行預覽時，從文生圖頁籤中讀取參數（提示詞等）", "Shuffle tags by ',' when creating prompts.": "在建立提示時用 ',' 洗牌標籤", "Drop out tags when creating prompts.": "在建立提示時刪除標籤", "Choose latent sampling method": "選擇潛在變數取樣方法", "once": "一次", "deterministic": "確定", "random": "隨機", "Train Embedding": "訓練嵌入", "Train Hypernetwork": "訓練超網路", "Apply settings": "套用設定", "Reload UI": "重新載入 UI", "Saving images/grids": "儲存圖像 / 宮格圖", "Paths for saving": "儲存路徑", "Saving to a directory": "儲存到目錄", "Upscaling": "放大", "Face restoration": "面部修復", "System": "系統", "Training": "訓練", "Stable Diffusion": "Stable Diffusion", "Optimizations": "Optimizations", "Compatibility": "相容性", "Interrogate Options": "反推提示詞選項", "Extra Networks": "額外網路", "User interface": "使用者介面", "Infotext": "Infotext", "Live previews": "即時預覽", "Sampler parameters": "取樣器參數", "Postprocessing": "後處理", "Defaults": "Defaults", "Actions": "動作", "Licenses": "授權", "Show all pages": "顯示所有頁面", "Always save all generated images": "始終儲存所有產生的圖像", "File format for images": "圖像的檔案格式", "Images filename pattern": "圖像檔案名格式", "Add number to filename when saving": "儲存的時候在檔案名里加入數字", "Always save all generated image grids": "始終儲存所有產生的宮格圖", "File format for grids": "宮格圖的檔案格式", "Add extended info (seed, prompt) to filename when saving grid": "儲存宮格圖時，將擴展資訊（隨機種子，提示詞）加入到檔案名", "Do not save grids consisting of one picture": "只有一張圖片時不要儲存宮格圖", "Prevent empty spots in grid (when set to autodetect)": "（啟用自動偵測時）防止宮格圖中出現空位", "Grid row count; use -1 for autodetect and 0 for it to be same as batch size": "宮格圖行數； 使用 -1 進行自動檢測，使用 0 使其與每批數量相同", "Save text information about generation parameters as chunks to png files": "將有關生成參數的文本資訊，作為塊儲存到 PNG 圖片檔案中", "Create a text file next to every image with generation parameters.": "儲存圖像時，在每個圖像旁邊建立一個文本檔案儲存生成參數", "Save a copy of image before doing face restoration.": "在進行面部修復之前儲存圖像副本", "Save a copy of image before applying highres fix.": "在做高解析度修復之前儲存初始圖像副本", "Save a copy of image before applying color correction to img2img results": "在對圖生圖結果套用顏色校正之前儲存圖像副本", "For inpainting, save a copy of the greyscale mask": "對於局部重繪，保存一份灰度遮罩的副本。", "For inpainting, save a masked composite": "對於修補，保存一個遮罩合成圖像。", "Quality for saved jpeg images": "儲存的 JPEG 圖像的品質", "Use lossless compression for webp images": "對 webp 圖像使用無損壓縮", "Save copy of large images as JPG": "Save copy of large images as JPG", "(if the file size is above the limit, or either width or height are above the limit)": "(if the file size is above the limit, or either width or height are above the limit)", "File size limit for the above option, MB": "檔案容量上限（MB）", "Width/height limit for the above option, in pixels": "解析度寬高上限（px）", "Maximum image size": "Maximum image size", "(in megapixels)": "(in megapixels)", "Use original name for output filename during batch process in extras tab": "在更多頁籤中的批量處理過程中，使用原始名稱作為輸出檔案名", "Use upscaler name as filename suffix in the extras tab": "使用上色器名稱作為附加檔的檔名後綴", "When using 'Save' button, only save a single selected image": "使用「儲存」按鈕時，只儲存一個選定的圖像", "Save init images when using img2img": "Save init images when using img2img", "Directory for temporary images; leave empty for default": "暫存影像的目錄；留空以使用預設值", "Cleanup non-default temporary directory when starting webui": "在啟動網頁介面時清除非預設的暫存目錄", "Output directory for images; if empty, defaults to three directories below": "圖像的輸出目錄； 如果為空，則預設為以下三個目錄", "Output directory for txt2img images": "文生圖的輸出目錄", "Output directory for img2img images": "圖生圖的輸出目錄", "Output directory for images from extras tab": "更多頁籤的輸出目錄", "Output directory for grids; if empty, defaults to two directories below": "宮格圖的輸出目錄； 如果為空，則預設為以下兩個目錄", "Output directory for txt2img grids": "文生圖宮格的輸出目錄", "Output directory for img2img grids": "圖生圖宮格的輸出目錄", "Directory for saving images using the Save button": "使用「儲存」按鈕儲存圖像的目錄", "Directory for saving init images when using img2img": "Directory for saving init images when using img2img", "Save images to a subdirectory": "將圖像儲存到子目錄", "Save grids to a subdirectory": "將宮格圖儲存到子目錄", "When using \"Save\" button, save images to a subdirectory": "使用「儲存」按鈕時，將圖像儲存到子目錄", "Directory name pattern": "目錄名稱格式", "Max prompt words for [prompt_words] pattern": "[prompt_words] 格式的最大提示詞數量", "Tile size for ESRGAN upscalers.": "Tile size for ESRGAN upscalers.", "(0 = no tiling)": "(0 = no tiling)", "Tile overlap for ESRGAN upscalers.": "Tile overlap for ESRGAN upscalers.", "(Low values = visible seam)": "(Low values = visible seam)", "Upscaler for img2img": "圖生圖的放大演算法", "LDSR processing steps. Lower = faster": "LDSR 處理疊代步數。越少越快", "Cache LDSR model in memory": "將 LDSR 模型快取在記憶體中", "Tile size for SCUNET upscalers.": "Tile size for SCUNET upscalers.", "Tile overlap for SCUNET upscalers.": "Tile overlap for SCUNET upscalers.", "Tile size for all SwinIR.": "適用所有 SwinIR 系演算法的圖塊尺寸", "Tile overlap, in pixels for SwinIR. Low values = visible seam.": "SwinIR 的圖塊重疊畫素。較小時可見接縫", "CodeFormer weight": "CodeFormer weight", "(0 = maximum effect; 1 = minimum effect)": "(0 = maximum effect; 1 = minimum effect)", "Move face restoration model from VRAM into RAM after processing": "面部修復處理完成後，將此模型從 VRAM 移至 RAM", "Show warnings in console.": "在控制台顯示警告訊息。", "VRAM usage polls per second during generation.": "VRAM usage polls per second during generation.", "(0 = disable)": "(0 = disable)", "Always print all generation info to standard output": "始終將所有產生資訊輸出到 standard output （一般為控制台）", "Add a second progress bar to the console that shows progress for an entire job.": "向控制台加入第二個進度列，顯示整個作業的進度", "Print extra hypernetwork information to console.": "將額外的超網路資訊印到控制台。", "Load models/files in hidden directories": "Load models/files in hidden directories", "(directory is hidden if its name starts with \".\")": "(directory is hidden if its name starts with \".\")", "Move VAE and CLIP to RAM when training if possible. Saves VRAM.": "訓練時將 VAE 和 CLIP 從 VRAM 移放到 RAM 如果可行的話，節省 VRAM", "Turn on pin_memory for DataLoader. Makes training slightly faster but can increase memory usage.": "對 DataLoader 開啟 pin_memory。使訓練略快，但可能會增加記憶體使用量。", "Saves Optimizer state as separate *.optim file. Training of embedding or HN can be resumed with the matching optim file.": "將優化器狀態儲存為獨立的 *.optim 檔。嵌入或超網路的訓練可以使用相匹配的優化檔恢復。", "Save textual inversion and hypernet settings to a text file whenever training starts.": "每次訓練開始時，將文本反轉和超網路設定儲存到一個文字檔案中。", "Filename word regex": "檔案名用詞的正則表達式", "Filename join string": "檔案名連接用字串", "Number of repeats for a single input image per epoch; used only for displaying epoch number": "每期（epoch）中單個輸入圖像的重複次數； 僅用於顯示期（epoch）數", "Save an csv containing the loss to log directory every N steps, 0 to disable": "每 N 步儲存一個包含 loss 的 CSV 檔案到記錄目錄，0 表示停用", "Use cross attention optimizations while training": "訓練時開啟 cross attention 最佳化", "Enable tensorboard logging.": "啟用 TensorBoard 日誌記錄。", "Save generated images within tensorboard.": "在 TensorBoard 中儲存產生的圖像。", "How often, in seconds, to flush the pending tensorboard events and summaries to disk.": "多少秒刷新一次待辦 TensorBoard 事件和摘要到磁盤上", "Checkpoints to cache in RAM": "暫存在內存（RAM）中的模型權重存檔點數", "VAE Checkpoints to cache in RAM": "在快取記憶體中快取 VAE 模型權重存檔點", "SD VAE": "模型的 VAE", "(choose VAE model: Automatic = use one with same filename as checkpoint; None = use VAE from checkpoint)": "(choose VAE model: Automatic = use one with same filename as checkpoint; None = use VAE from checkpoint)", "Ignore selected VAE for stable diffusion checkpoints that have their own .vae.pt next to them": ".vae.pt 模型權重存檔點在名稱相同時，忽略掉選中的 VAE", "Inpainting conditioning mask strength": "局部重繪時圖像調節的遮罩屏蔽強度", "Noise multiplier for img2img": "圖生圖的噪聲乘數", "Apply color correction to img2img results to match original colors.": "對圖生圖結果套用顏色校正以匹配原始顏色", "With img2img, do exactly the amount of steps the slider specifies.": "With img2img, do exactly the amount of steps the slider specifies.", "(normally you'd do less with less denoising)": "(normally you'd do less with less denoising)", "With img2img, fill image's transparent parts with this color.": "在 img2img 中，以此顏色填滿圖片的透明部分。", "Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply.": "在 K 取樣器中啟用量化以獲得更清晰，乾淨的結果。這可能會改變現有的隨機種子。需要儲存設定並重新啟動才能套用", "Enable emphasis": "Enable emphasis", "(use (text) to make model pay more attention to text and [text] to make it pay less attention)": "(use (text) to make model pay more attention to text and [text] to make it pay less attention)", "Make K-diffusion samplers produce same images in a batch as when making a single image": "使 K-diffusion 取樣器批量生成與生成單個圖像時，產出相同的圖像", "Prompt word wrap length limit": "Prompt word wrap length limit", "(in tokens - for texts shorter than specified, if they don't fit into 75 token limit, move them to the next 75 token chunk)": "(in tokens - for texts shorter than specified, if they don't fit into 75 token limit, move them to the next 75 token chunk)", "Clip skip": "Clip 跳過層", "(ignore last layers of CLIP nrtwork; 1 ignores none, 2 ignores one layer)": "(ignore last layers of CLIP nrtwork; 1 ignores none, 2 ignores one layer)", "Upcast cross attention layer to float32": "將交叉注意層升級為 float32", "Random number generator source.": "Random number generator source.", "(changes seeds drastically; use CPU to produce the same picture across different vidocard vendors)": "(changes seeds drastically; use CPU to produce the same picture across different vidocard vendors)", "GPU": "GPU", "CPU": "CPU", "Cross attention optimization": "Cross attention optimization", "PR": "PR", "Negative Guidance minimum sigma": "Negative Guidance minimum sigma", "(skip negative prompt for some steps when the image is almost ready; 0=disable, higher=faster)": "(skip negative prompt for some steps when the image is almost ready; 0=disable, higher=faster)", "Token merging ratio": "Token merging ratio", "(0=disable, higher=faster)": "(0=disable, higher=faster)", "Token merging ratio for img2img": "Token merging ratio for img2img", "(only applies if non-zero and overrides above)": "(only applies if non-zero and overrides above)", "Token merging ratio for high-res pass": "Token merging ratio for high-res pass", "Use old emphasis implementation. Can be useful to reproduce old seeds.": "使用舊的強調符實作。可用於復現舊隨機種子", "Use old karras scheduler sigmas (0.1 to 10).": "使用舊的 karras 調度器 sigma（0.1 至 10）", "Do not make DPM++ SDE deterministic across different batch sizes.": "不要使 DPM++ SDE 在不同的批次大小之間具有確定性。", "For hires fix, use width/height sliders to set final resolution rather than first pass (disables Upscale by, Resize width/height to).": "為了 hires fix，使用寬度/高度滑桿設定最終解析度，而不是第一遍（停用放大比例、調整寬度/高度）", "Do not fix prompt schedule for second order samplers.": "Do not fix prompt schedule for second order samplers.", "Lora: use old method that takes longer when you have multiple Loras active and produces same results as kohya-ss/sd-webui-additional-networks extension": "Lora: use old method that takes longer when you have multiple Loras active and produces same results as kohya-ss/sd-webui-additional-networks extension", "Keep models in VRAM": "Keep models in VRAM", "Include ranks of model tags matches in results.": "Include ranks of model tags matches in results.", "(booru only)": "(booru only)", "BLIP: num_beams": "BLIP: num_beams", "BLIP: minimum description length": "BLIP: minimum description length", "BLIP: maximum description length": "BLIP: maximum description length", "CLIP: maximum number of lines in text file": "CLIP: maximum number of lines in text file", "(0 = No limit)": "(0 = No limit)", "CLIP: skip inquire categories": "CLIP：跳過詢問類別", "deepbooru: score threshold": "deepbooru: score threshold", "deepbooru: sort tags alphabetically": "deepbooru: sort tags alphabetically", "(if not: sort by score)": "(if not: sort by score)", "deepbooru: use spaces in tags": "deepbooru: use spaces in tags", "(if not: use underscores)": "(if not: use underscores)", "deepbooru: escape (\\) brackets": "deepbooru: escape (\\) brackets", "(so they are used as literal brackets and not for emphasis)": "(so they are used as literal brackets and not for emphasis)", "deepbooru: filter out those tags": "deepbooru: filter out those tags", "(separate by comma)": "(separate by comma)", "Show hidden directories": "Show hidden directories", "(directory is hidden if its name starts with \".\".)": "(directory is hidden if its name starts with \".\".)", "Show cards for models in hidden directories": "Show cards for models in hidden directories", "(\"When searched\" option will only show the item when the search string has 4 characters or more)": "(\"When searched\" option will only show the item when the search string has 4 characters or more)", "Always": "Always", "When searched": "When searched", "Never": "Never", "Default view for Extra Networks": "額外網絡的默認視圖", "Multiplier for extra networks": "額外網絡的乘數", "Card width for Extra Networks": "Card width for Extra Networks", "(in pixels)": "(in pixels)", "Card height for Extra Networks": "額外網絡的卡片高度", "Extra networks separator": "Extra networks separator", "(extra text to add before <...> when adding extra network to prompt)": "(extra text to add before <...> when adding extra network to prompt)", "Extra networks tab order": "額外網絡標籤順序", "(requires restart)": "(requires restart)", "Add hypernetwork to prompt": "將超網路加入至提示詞", "Add Lora to prompt": "將 LoRA 添加到提示詞", "When adding to prompt, refer to Lora by": "When adding to prompt, refer to Lora by", "Alias from file": "Alias from file", "Filename": "Filename", "Add Lora hashes to infotext": "Add Lora hashes to infotext", "Localization": "本地化", "Gradio theme": "Gradio 主題", "img2img: height of image editor": "img2img: height of image editor", "Show grid in results for web": "在網頁的結果中顯示宮格圖", "For inpainting, include the greyscale mask in results for web": "對於局部重繪，將灰度遮罩包含在網頁結果中", "For inpainting, include masked composite in results for web": "對於局部重繪，將遮罩合成包含在網頁結果中。", "Do not show any images in results for web": "不在網頁的結果中顯示任何圖像", "Send seed when sending prompt or image to other interface": "將提示詞或者圖像發送到 >> 其他界面時，把隨機種子也傳送過去", "Send size when sending prompt or image to another interface": "發送提示或圖片到其他介面時，發送大小", "Font for image grids that have text": "有文字的宮格圖使用的字體", "Enable full page image viewer": "啟用整頁圖像檢視器", "Show images zoomed in by default in full page image viewer": "在整頁圖像檢視器中，預設放大顯示圖像", "Navigate image viewer with gamepad": "Navigate image viewer with gamepad", "Gamepad repeat period, in milliseconds": "Gamepad repeat period, in milliseconds", "Show generation progress in window title.": "在視窗標題中顯示生成進度", "Use dropdown for sampler selection instead of radio group": "使用下拉式選單代替單選群組選擇取樣器", "Show Width/Height and Batch sliders in same row": "在同一列中顯示寬度 / 高度和批量滑塊", "Ctrl+up/down precision when editing (attention:1.1)": "編輯時使用 Ctrl + up/down 調整精度 (注意：1.1)", "Ctrl+up/down precision when editing ": "編輯時使用 Ctrl + up/down 調整精度 <額外網路：0.9>", "Ctrl+up/down word delimiters": "Ctrl+up/down word delimiters", "info": "info", "Quicksettings list": "快捷設定列表", "(setting entries that appear at the top of page rather than in settings tab)": "(setting entries that appear at the top of page rather than in settings tab)", "sd_model_checkpoint": "sd_model_checkpoint", "UI tab order": "UI tab order", "Hidden UI tabs": "Hidden UI tabs", "txt2img/img2img UI item order": "文生圖 / 圖生圖 UI 項目順序", "Hires fix: show hires sampler selection": "Hires fix: show hires sampler selection", "Hires fix: show hires prompt and negative prompt": "Hires fix: show hires prompt and negative prompt", "Add model hash to generation information": "將模型的雜湊值加入到生成資訊", "Add model name to generation information": "將模型名稱加入到生成資訊", "Add program version to generation information": "Add program version to generation information", "When reading generation parameters from text into UI (from PNG info or pasted text), do not change the selected model/checkpoint.": "從文本讀取生成參數到使用者介面（從 PNG 圖片資訊或粘貼文本）時，不要更改選定的模型權重存檔點", "Show progressbar": "顯示進度列", "Show live previews of the created image": "顯示所創建的圖像的實時預覽", "Live preview file format": "Live preview file format", "jpeg": "jpeg", "png": "png", "webp": "webp", "Show previews of all images generated in a batch as a grid": "以宮格圖的形式，預覽批量產生的所有圖像", "Live preview display period": "Live preview display period", "(in sampling steps - show new live preview image every N sampling steps; -1 = only show after completion of batch)": "(in sampling steps - show new live preview image every N sampling steps; -1 = only show after completion of batch)", "Live preview method": "Live preview method", "(Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise)": "(Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise)", "Full": "完整", "Approx NN": "Approx NN", "Approx cheap": "Approx cheap", "TAESD": "TAESD", "Live preview subject": "實時預覽主題", "Combined": "結合", "Progressbar and preview update period": "Progressbar and preview update period", "(in milliseconds)": "(in milliseconds)", "Hide samplers in user interface": "Hide samplers in user interface", "Euler a": "Euler a", "Euler": "Euler", "LMS": "LMS", "Heun": "Heun", "DPM2": "DPM2", "DPM2 a": "DPM2 a", "DPM++ 2S a": "DPM++ 2S a", "DPM++ 2M": "DPM++ 2M", "DPM++ SDE": "DPM++ SDE", "DPM++ 2M SDE": "DPM++ 2M SDE", "DPM fast": "DPM fast", "DPM adaptive": "DPM adaptive", "LMS Karras": "LMS Karras", "DPM2 Karras": "DPM2 Karras", "DPM2 a Karras": "DPM2 a Karras", "DPM++ 2S a Karras": "DPM++ 2S a Karras", "DPM++ 2M Karras": "DPM++ 2M Karras", "DPM++ SDE Karras": "DPM++ SDE Karras", "DPM++ 2M SDE Karras": "DPM++ 2M SDE Karras", "DDIM": "DDIM", "PLMS": "PLMS", "UniPC": "UniPC", "Eta for DDIM": "Eta for DDIM", "(noise multiplier; higher = more unperdictable results)": "(noise multiplier; higher = more unperdictable results)", "Eta for ancestral samplers": "Eta for ancestral samplers", "(noise multiplier; applies to Euler a and other samplers that have a in them)": "(noise multiplier; applies to Euler a and other samplers that have a in them)", "img2img DDIM discretize": "圖生圖 DDIM 離散化", "uniform": "均勻", "quad": "二階", "sigma churn": "希格瑪流失量（sigma churn）", "sigma tmin": "希格瑪最小值（sigma tmin）", "sigma noise": "希格瑪噪點量（sigma noise）", "Eta noise seed delta": "Eta 噪點種子偏移（ENSD）", "(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)": "(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)", "Always discard next-to-last sigma": "始終丟棄倒數第二個 sigma", "UniPC variant": "UniPC 變體", "bh1": "bh1", "bh2": "bh2", "vary_coeff": "vary_coeff", "UniPC skip type": "UniPC 跳過類型", "time_uniform": "time_uniform", "time_quadratic": "time_quadratic", "logSNR": "logSNR", "UniPC order": "UniPC order", "(must be < sampling steps)": "(must be < sampling steps)", "UniPC lower order final": "UniPC 最終步採用低階取樣。", "Enable postprocessing operations in txt2img and img2img tabs": "啟用文生圖和圖生圖選項卡中的後處理操作", "Postprocessing operation order": "後處理操作順序", "Maximum number of images in upscaling cache": "放大快取中圖像的最大數量", "This page allows you to change default values in UI elements on other tabs.": "This page allows you to change default values in UI elements on other tabs.", "Make your changes, press 'View changes' to review the changed default values,": "Make your changes, press 'View changes' to review the changed default values,", "then press 'Apply' to write them to D:\\sd.webui\\webui\\ui-config.json.": "then press 'Apply' to write them to D:\\sd.webui\\webui\\ui-config.json.", "New defaults will apply after you restart the UI.": "New defaults will apply after you restart the UI.", "View changes": "View changes", "Apply": "套用", "Request browser notifications": "請求瀏覽器通知", "Download localization template": "下載本地化模板", "Reload custom script bodies (No ui updates, No restart)": "重新載入自訂指令碼主體（使用者介面不刷新，不重新啟動）", "Unload SD checkpoint to free VRAM": "卸載模型權重存檔點以釋放 VRAM", "Reload the last SD checkpoint back into VRAM": "重新載入上一個模型權重存檔點至 VRAM", "Installed": "已安裝", "Available": "可用", "Install from URL": "從網址安裝", "Backup/Restore": "Backup/Restore", "Apply and restart UI": "更新並重新啟動使用者介面", "Check for updates": "檢查更新", "Disable all extensions": "停用所有擴充功能", "none": "無", "extra": "額外的", "all": "全部", "Time taken:": "用時：", "Extension": "擴充功能", "Use checkbox to enable the extension; it will be enabled or disabled when you click apply button": "勾選要啟用的擴充功能並按下套用以啟用，取消勾選則停用", "URL": "網址", "Branch": "Branch", "Version": "版本", "Extension version": "擴充功能版本", "Date": "Date", "Update": "更新", "Use checkbox to mark the extension for update; it will be updated when you click apply button": "勾選要更新的擴充功能並按下套用以更新", "built-in": "內建的", "latest": "最新", "behind": "有可用更新", "Error": "錯誤", "unknown": "未知", "ScuNET": "ScuNET", "prompt-bracket-checker": "提示括號檢查器", "Load from:": "載入自", "Extension index URL": "擴充列表網址", "Hide extensions with tags": "隱藏含有以下標記的擴充工具", "script": "指令碼", "ads": "含廣告", "localization": "本地化", "installed": "已安裝", "Description": "描述", "Action": "動作", "dropdown": "下拉式清單", "UI related": "使用者介面相關", "tab": "頁籤", "animation": "動畫", "online": "線上", "extras": "附加功能", "science": "科學", "models": "模型", "query": "查詢", "training": "訓練", "Fusion": "融合", "editing": "編輯", "Waiting...": "等待中...", "prompting": "提示詞", "manipulations": "操作", "Order": "排序", "newest first": "最新的在最前面", "oldest first": "最舊的在最前面", "a-z": "字母順序：從a到z", "z-a": "字母順序：從z到a", "internal order": "內部順序", "Search": "搜尋", "URL for extension's git repository": "擴充功能的 git 倉庫網址", "Specific branch name": "Specific branch name", "Local directory name": "本地目錄名稱", "Install": "安裝", "Saved Configs": "Saved Configs", "State to restore": "State to restore", "extensions": "extensions", "webui": "webui", "both": "both", "Restore Selected Config": "Restore Selected Config", "Save Current Config": "Save Current Config", "Config Backup: Config": "Config Backup: Config", "Filepath:": "Filepath:", "Created at:": "Created at:", "WebUI State": "WebUI State", "Commit": "Commit", "Extension State": "Extension State", "N/A": "N/A", "Change checkpoint": "切換模型權重存檔點", "Clear": "Clear", "Use via API": "使用API", "Built with Gradio": "使用 Gradio 構建", "Prompt (press Ctrl+Enter or Alt+Enter to generate)": "提示詞（按 Ctrl+Enter 或 Alt+Enter 產生）", "Negative prompt (press Ctrl+Enter or Alt+Enter to generate)": "反向提示詞（按 Ctrl+Enter 或 Alt+Enter 產生）", "Stop processing images and return any results accumulated so far.": "停止處理圖像，並返回迄今為止累積的任何結果", "Stop processing current image and continue processing.": "停止處理當前圖像，並繼續處理下一個", "Read generation parameters from prompt or last generation if prompt is empty into user interface.": "從提示詞中讀取生成參數，如果提示詞為空，則讀取上一次的生成參數到使用者介面", "Clear prompt": "清除提示詞", "Show/hide extra networks": "顯示 / 隱藏額外的網路", "Apply selected styles to current prompt": "將所選樣式套用於當前提示", "Save style": "儲存樣式", "Restore progress": "Restore progress", "Search...": "搜尋...", "Which algorithm to use to produce the image": "使用哪種演算法生成圖像", "How many times to improve the generated image iteratively; higher values take longer; very low values can produce bad results": "疊代改進產生的圖像多少次；更高的值需要更長的時間；非常低的值會產生不好的結果", "Produce an image that can be tiled.": "生成可用於平舖的圖像", "Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition": "使用兩步處理的時候，以較小的解析度生成初步圖像，接著放大圖像，然後在不更改構圖的情況下改進其中的細節", "Number of sampling steps for upscaled picture. If 0, uses same as for original.": "放大圖片的取樣步數。如果為0，則使用與原始圖片相同的值。", "Determines how little respect the algorithm should have for image's content. At 0, nothing will change, and at 1 you'll get an unrelated image. With values below 1.0, processing will take less steps than the Sampling Steps slider specifies.": "決定演算法對圖像內容的影響程度。設定 0 時，什麼都不會改變，而在 1 時，你將獲得不相關的圖像。\n值低於 1.0 時，處理的疊代步數將少於「取樣疊代步數」滑桿指定的步數", "Adjusts the size of the image by multiplying the original width and height by the selected value. Ignored if either Resize width to or Resize height to are non-zero.": "通過乘以選定值來調整圖像的大小。如果「將寬度調整至」或「將高度調整至」不為零，則會忽略。", "Resizes image to this width. If 0, width is inferred from either of two nearby sliders.": "將圖像調整到此寬度。如果為0，則寬度會從兩個附近的滑塊之一推斷。", "Resizes image to this height. If 0, height is inferred from either of two nearby sliders.": "將圖像調整到此高度。如果為0，則高度會從兩個附近的滑塊之一推斷。", "How many batches of images to create (has no impact on generation performance or VRAM usage)": "要產生多少批圖像（對產生效能或 VRAM 使用沒有影響）。", "How many image to create in a single batch (increases generation performance at cost of higher VRAM usage)": "在一個批次中產生的圖像數量，增加這個數量可以加快圖像產生速度，但會增加 VRAM 的使用量。", "Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results": "無分類器指導訊息影響尺度（Classifier Free Guidance Scale）- 圖像應在多大程度上服從提示詞 - 較低的值會產生更有創意的結果", "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": "一個固定隨機數生成器輸出的值 — 以相同參數和隨機種子生成的圖像會得到相同的結果\n🎲 將隨機種子設定為負數（預設-1），則每次都會使用一個非負數的隨機整數\n♻️ 重用上一次使用的隨機種子，如果想要固定輸出結果的話這很有用", "Set seed to -1, which will cause a new random number to be used every time": "將隨機種子設定為 -1，則每次都會使用一個新的隨機數", "Reuse seed from last generation, mostly useful if it was randomed": "重用上一次使用的隨機種子，如果想要固定結果就會很有用", "Seed of a different picture to be mixed into the generation.": "將要參與生成的另一張圖的隨機種子", "How strong of a variation to produce. At 0, there will be no effect. At 1, you will get the complete picture with variation seed (except for ancestral samplers, where you will just get something).": "想要產生多強烈的變化。設為 0 時，將沒有效果。設為 1 時，你將獲得完全產自差異隨機種子的圖像（此功能對帶有 a 後綴的取樣器無效）", "Make an attempt to produce a picture similar to what would have been produced with same seed at specified resolution": "在相同隨機種子但不同解析度的情況下，嘗試生成與指定解析度的生成結果相似的圖片", "Separate values for X axis using commas.": "使用逗號分隔 X 軸的值", "Paste available values into the field": "將可用的值貼上到字段中", "Separate values for Y axis using commas.": "使用逗號分隔 Y 軸的值", "Open images output directory": "打開圖像輸出目錄", "Write image to a directory (default - log/images) and generation parameters into csv file.": "將圖像寫入目錄（預設 — log/images）並將生成參數寫入CSV表格檔案", "Resize image to target resolution. Unless height and width match, you will get incorrect aspect ratio.": "將圖像大小調整為目標解析度。除非高度和寬度匹配，否則你將獲得不正確的縱橫比", "Resize the image so that entirety of target resolution is filled with the image. Crop parts that stick out.": "調整圖像大小，使整個目標解析度都被圖像填充。裁剪多出來的部分", "Resize the image so that entirety of image is inside target resolution. Fill empty space with image's colors.": "調整圖像大小，使整個圖像在目標解析度內。用圖像的顏色填充空白區域", "How much to blur the mask before processing, in pixels.": "處理前要對遮罩進行多強的模糊，以畫素為單位", "What to put inside the masked area before processing it with Stable Diffusion.": "在使用 Stable Diffusion 處理遮罩區域之前要在遮罩區域內放置什麼", "fill it with colors of the image": "用圖像的顏色（高強度模糊）填充它", "keep whatever was there originally": "保留原來的圖像，不進行預處理", "fill it with latent space noise": "以潛在變數空間噪點填充", "fill it with latent space zeroes": "以潛在變數填零填充", "How many times to process an image. Each output is used as the input of the next loop. If set to 1, behavior will be as if this script were not used.": "設定圖像處理的迴圈次數，每次迴圈的輸出會作為下一個迴圈的輸入。若設定為1，則行為會像沒有使用此腳本一樣。", "The denoising strength for the final loop of each image in the batch.": "每個批次中每張圖像的最後迴圈的重繪幅度。", "The denoising curve controls the rate of denoising strength change each loop. Aggressive: Most of the change will happen towards the start of the loops. Linear: Change will be constant through all loops. Lazy: Most of the change will happen towards the end of the loops.": "降噪曲線控制每個迴圈中降噪強度的變化率。Aggressive（激進）：大部分的變化會發生在迴圈的開始。Linear（線性）：變化會在所有迴圈中保持恆定。Lazy（懶惰）：大部分的變化會發生在迴圈的結尾。", "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.": "使用 SD 放大時，圖塊之間應該有多少畫素重疊。圖塊之間需要重疊才可以讓它們在合併回一張圖像時，沒有清晰可見的接縫", "Do not do anything special": "什麼都不做", "A directory on the same machine where the server is running.": "伺服器主機上某一目錄", "Leave blank to save images to the default path.": "留空以將圖像儲存到預設路徑", "Result = A": "結果 = A", "Result = A * (1 - M) + B * M": "結果 = A * (1 - M) + B * M", "Result = A + (B - C) * M": "結果 = A + (B - C) * M", "Regular expression; if weights's name matches it, the weights is not written to the resulting checkpoint. Use ^model_ema to discard EMA weights.": "正則表達式；如果 weights 的名稱與其匹配，則不將 weights 寫入得到的檢查點。使用 ^model_ema 丟棄 EMA weights。", "If the number of tokens is more than the number of vectors, some may be skipped.\nLeave the textbox empty to start with zeroed out vectors": "如果標記數量大於向量數量，則可能會被跳過。\n留下文字方塊空白以開始填零的向量", "1st and last digit must be 1. ex:'1, 2, 1'": "第一個和最後一個數字必須是 1。例：'1, 2, 1'", "1st and last digit must be 0 and values should be between 0 and 1. ex:'0, 0.01, 0'": "第1和最後一個數字必須是 0，並且值應該在 0 和 1 之間。 ex：'0, 0.01, 0", "Gradient clip value": "梯度剪裁值", "Path to directory with input images": "帶有輸入圖像的目錄路徑", "Path to directory where to write outputs": "進行輸出的目錄路徑", "Use following tags to define how filenames for images are chosen: [steps], [cfg], [clip_skip], [batch_number], [generation_number], [prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime], [datetime