{ "# of threads to use for hash calculation (increase if using an SSD)": "用于哈希计算的线程数（如果使用SSD可适当增加）", "(A1) Primary": "(A1) 主要", "(A10) Primary": "(A10) 主要", "(A2) Primary": "(A2) 主要", "(A3) Primary": "(A3) 主要", "(A4) Primary": "(A4) 主要", "(A5) Primary": "(A5) 主要", "(A6) Primary": "(A6) 主要", "(A7) Primary": "(A7) 主要", "(A8) Primary": "(A8) 主要", "(A9) Primary": "(A9) 主要", "(B1) Secondary": "(B1) 第二", "(B10) Secondary": "(B10) 第二", "(B2) Secondary": "(B2) 第二", "(B3) Secondary": "(B3) 第二", "(B4) Secondary": "(B4) 第二", "(B5) Secondary": "(B5) 第二", "(B6) Secondary": "(B6) 第二", "(B7) Secondary": "(B7) 第二", "(B8) Secondary": "(B8) 第二", "(B9) Secondary": "(B9) 第二", "(C1) Thertiary": "(C1) 第三", "(C10) Thertiary": "(C10) 第三", "(C2) Thertiary": "(C2) 第三", "(C3) Thertiary": "(C3) 第三", "(C4) Thertiary": "(C4) 第三", "(C5) Thertiary": "(C5) 第三", "(C6) Thertiary": "(C6) 第三", "(C7) Thertiary": "(C7) 第三", "(C8) Thertiary": "(C8) 第三", "(C9) Thertiary": "(C9) 第三", "(M1) Multiplier": "(M1) 倍率", "(M10) Multiplier": "(M10) 倍率", "(M2) Multiplier": "(M2) 倍率", "(M3) Multiplier": "(M3) 倍率", "(M4) Multiplier": "(M4) 倍率", "(M5) Multiplier": "(M5) 倍率", "(M6) Multiplier": "(M6) 倍率", "(M7) Multiplier": "(M7) 倍率", "(M8) Multiplier": "(M8) 倍率", "(M9) Multiplier": "(M9) 倍率", "(O)Output Model Name": "输出模型文件名", "(O1) Output ckpt Name": "(O1) ckpt 输出名", "(O10) Output ckpt Name": "(O10) ckpt 输出名", "(O2) Output ckpt Name": "(O2) ckpt 输出名", "(O3) Output ckpt Name": "(O3) ckpt 输出名", "(O4) Output ckpt Name": "(O4) ckpt 输出名", "(O5) Output ckpt Name": "(O5) ckpt 输出名", "(O6) Output ckpt Name": "(O6) ckpt 输出名", "(O7) Output ckpt Name": "(O7) ckpt 输出名", "(O8) Output ckpt Name": "(O8) ckpt 输出名", "(O9) Output ckpt Name": "(O9) ckpt 输出名", "(Optional) Path to directory with classification/regularization images": "（可选）带有分类/规范化图像的目录路径", "(S1) Inter-Method": "(S1) 插值方法", "(S10) Inter-Method": "(S10) 插值方法", "(S2) Inter-Method": "(S2) 插值方法", "(S3) Inter-Method": "(S3) 插值方法", "(S4) Inter-Method": "(S4) 插值方法", "(S5) Inter-Method": "(S5) 插值方法", "(S6) Inter-Method": "(S6) 插值方法", "(S7) Inter-Method": "(S7) 插值方法", "(S8) Inter-Method": "(S8) 插值方法", "(S9) Inter-Method": "(S9) 插值方法", "180 Degree Rotation": "180度旋转", "1st and last digit must be 1. ex:'1, 2, 1'": "第一个和最后一个数字必须是 1。例：'1, 2, 1'", "90 Degree Rotation": "90度旋转", ": Original extension": "：原始文件的后缀（不含 . ）", ": Original extension\nAvailable algorithms:": "：原始文件哈希，应替换成以下算法之一：", ": Original filename without extension": "：原始文件名（不含后缀）", ": Output extension (has no dot)": "：输出文件的后缀（不含 . ）", "A directory on the same machine where the server is running.": "服务器主机上某一目录", "A range can be provided:": "项数可以有范围", "A weighted sum will be used for interpolation. Requires two models; A and B. The result is calculated as A * (1 - M) + B * M": "将两个模型权重的加权和作为新模型的权重，仅需要填入模型A和B，公式：A*(1-M) + B*M，倍率(M)为模型B所占比例", "A, B or C": "A, B或C", "API Key": "API 密钥", "API info may not be necessary for some boorus, but certain information or posts may fail to load without it. For example, Danbooru doesn't show certain posts in search results unless you auth as a Gold tier member.": "API 信息对于某些 boorus 可能不是必需的，但如果没有它，某些信息或图帖可能无法加载。 例如，除非你的 API 验证属于黄金会员，否则 Danbooru 不会在搜索结果中显示某些图帖", "Accent": "Catppuccin 主题风格（按钮颜色，根据主题样式不同会发生变化，不一定完全与描述相同）", "Accumulation steps": "累加步数", "Action": "操作", "Actions": "其他操作", "Activate Selected Script": "激活所选的脚本", "Activation keywords, comma-separated": "该模型的触发词，逗号分隔", "Active in img2img (Requires restart)": "在图生图页面启用（需要保存设置并重启）", "Active in negative prompts (Requires restart)": "在负面提示词中启用（需要保存设置并重启）", "Active in third party textboxes [Dataset Tag Editor] (Requires restart)": "在第三方文本框[Dataset Tag Editor]中启用（需要保存设置并重启）", "Active in txt2img (Requires restart)": "在文生图页面启用（需要保存设置并重启）", "Add": "添加", "Add Background image": "添加背景图片", "Add Lora to prompt": "将 LoRA 模型添加到提示词", "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.": "添加一个按钮以将 NovelAI 中使用的提示词转换为在 WebUI 中使用。此外，添加一个按钮，让你可以调用以前使用过的提示词", "Add a second progress bar to the console that shows progress for an entire job.": "向控制台添加第二个进度条，显示整个作业的进度", "Add difference": "加上差值", "Add emphasis to a randomly selected keyword in the prompt.": "在提示词中随机选择一个关键字加上强调符", "Add extended info (seed, prompt) to filename when saving grid": "保存宫格图时，将扩展信息（随机种子、提示词）添加到文件名", "Add hypernetwork to prompt": "将超网络(Hypernetwork)添加到提示词", "Add layer normalization": "添加层归一化", "Add model hash to generation information": "将模型的哈希值添加到生成信息（建议开启）", "Add model name to generation information": "将模型名称添加到生成信息（建议开启）", "Add number to filename when saving": "储存的时候在文件名里添加数字", "Add/Remove...": "编辑预设", "AddNet Model 1": "[可选附加网络] 模型 1", "AddNet Model 2": "[可选附加网络] 模型 2", "AddNet Model 3": "[可选附加网络] 模型 3", "AddNet Model 4": "[可选附加网络] 模型 4", "AddNet Model 5": "[可选附加网络] 模型 5", "AddNet TEnc Weight 1": "[可选附加网络] Text Encoder 权重 1", "AddNet TEnc Weight 2": "[可选附加网络] Text Encoder 权重 2", "AddNet TEnc Weight 3": "[可选附加网络] Text Encoder 权重 3", "AddNet TEnc Weight 4": "[可选附加网络] Text Encoder 权重 4", "AddNet TEnc Weight 5": "[可选附加网络] Text Encoder 权重 5", "AddNet UNet Weight 1": "[可选附加网络] UNet 权重 1", "AddNet UNet Weight 2": "[可选附加网络] UNet 权重 2", "AddNet UNet Weight 3": "[可选附加网络] UNet 权重 3", "AddNet UNet Weight 4": "[可选附加网络] UNet 权重 4", "AddNet UNet Weight 5": "[可选附加网络] UNet 权重 5", "AddNet Weight 1": "[可选附加网络] 权重 1", "AddNet Weight 2": "[可选附加网络] 权重 2", "AddNet Weight 3": "[可选附加网络] 权重 3", "AddNet Weight 4": "[可选附加网络] 权重 4", "AddNet Weight 5": "[可选附加网络] 权重 5", "Additional Networks": "可选附加网络(LoRA插件)", "Additional tags (split by comma)": "附加标签(逗号分隔)", "Adds a tab that lets you preview how CLIP model would tokenize your text.": "新增一个选项卡让你能够预览 CLIP 模型如何对你的文本进行词元拆分(tokenize)", "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 添加一个选项卡，允许用户自动从视频中提取关键帧，并手动裁剪 512x512 大小以用于模型训练", "Advanced": "高阶", "Advanced options": "高级选项", "Aesthetic Gradients": "美术风格梯度", "Aesthetic Image Scorer": "美术风格评分", "Aesthetic imgs embedding": "美术风格图集 Embedding", "Aesthetic learning rate": "美术风格学习率", "Aesthetic scorer": "美学评分器", "Aesthetic steps": "美术风格迭代步数", "Aesthetic text for imgs": "该图集的美术风格描述", "Aesthetic weight": "美术风格权重", "All": "全部", "All models in this directory will receive the selected model's metadata": "此目录下所有模型都将被粘贴与选中模型完全相同的元数据", "Allow NSFW": "允许成人内容", "Allow detectmap auto saving": "允许自动保存探测模式图(detected maps)", "Allow other script to control this extension": "允许其他脚本对此扩展插件进行控制", "Allow overwrite output-model": "允许输出模型覆盖同名文件", "Allow the default Euler a Sampling method. (Does not produce good results)": "允许使用默认的 Eular a 采样方法. (通常不会出漂亮的结果)", "Allows you to easily, or even completely automatically start using HTTPS.": "让你可以很简单地自动配置HTTPS", "Allows you to manually edit textual inversion embeddings using sliders.": "让你可以手动用滑条编辑风格迁移 Embeddings 的参数", "Also, please set the booru selection here before using select or search.": "另外，在选择或搜索之前，请在这里设置你要用哪个 booru", "Alternate Steps": "交替迭代", "Always discard next-to-last sigma": "始终舍弃倒数第二个sigma", "Always print all generation info to standard output": "始终将所有生成信息输出到 standard output (一般为控制台)", "Always save all generated image grids": "始终保存所有生成的宫格图", "Always save all generated images": "始终保存所有生成的图像", "An extension of the built-in Composable Diffusion, allows you to determine the region of the latent space that reflects your subprompts.": "内置 Composable Diffusion 的扩展，能让你划分潜空间并在对应区域反映出你指定的提示词段落。", "An object detection and auto-mask extension for Stable Diffusion web UI.": "一个物件检测与自适应蒙版扩展", "Annotator resolution": "预处理器分辨率（Annotator resolution）", "Append comma on tag autocompletion": "自动添加逗号", "Applies mirroring and flips to the latent images to produce anything from subtle balanced compositions to perfect reflections": "将潜变量状态的图像进行镜像和翻转，以生成从轻度平衡的构图到完全对称的任何图像", "Apply": "应用", "Apply (Reload UI)": "应用（重启 WebUI）", "Apply Favicon (edit webui.py to see)": "应用网页图标（编辑 webui.py 后可见）", "Apply Horizontal Flip": "应用水平翻转", "Apply Logo": "应用 Logo", "Apply Lora to outputs rather than inputs when possible (experimental)": "尽可能将 LoRA 模型应用于输出而非输入(实验性选项)", "Apply Style": "应用风格", "Apply and restart UI": "应用并重启用户界面", "Apply block weight from text": "将手动输入的权重应用于滑动条", "Apply changes (Reload UI)": "应用设置（重启 WebUI）", "Apply color correction to img2img results to match original colors.": "对图生图结果应用颜色校正以匹配原始颜色", "Apply settings": "保存设置", "Apply to": "应用于", "Apply transfer control when loading models": "加载模型时应用传输控制", "Artist Tags": "画师标签(Tags)", "Artists to study": "艺术家图库", "Attention grabber": "随机关键词吸引注意力", "Author": "作者", "Author of this model": "此模型的作者", "Auto TLS-HTTPS": "自动 TLS-HTTPS", "Auto focal point crop": "自动焦点裁切", "Automatic": "自动（仅加载与模型同名的 VAE，未找到时不加载）", "Automatically update your prompt with interesting modifiers. (Runs slowly the first time)": "使用有趣的修饰符自动更新你的提示词。（第一次运行会比较慢）", "Available": "可用", "Average image color": "平均图像颜色", "Background": "背景图片", "Bake in VAE": "整合入模型的 VAE", "Batch": "批量处理", "Batch Process": "批量处理", "Batch Size": "每批数量(Batch Size)", "Batch count": "生成批次", "Batch from Directory": "从目录进行批量处理", "Batch from directory": "批量操作", "Batch size": "每批数量", "Before your text is sent to the neural network, it gets turned into numbers in a process called tokenization. These tokens are how the neural network reads and interprets text. Thanks to our great friends at Shousetsu愛 for inspiration for this feature.": "在你的文本被发送到神经网络之前，它在一个称为词元化(tokenization)的过程中被转化为数字。这些词元(tokens)是神经网络阅读和解释文本的方式。感谢我们伟大的朋友 Shousetsu愛 为这个功能带来的灵感", "Bilingual Localization": "双语对照翻译", "Bilingual translation, no need to worry about how to find the original button. Compatible with language pack extensions, no need to re-import.": "全新实现的双语对照翻译功能，不必再担心切换翻译后找不到原始功能。兼容原生语言包扩展，无需重新导入多语言语料。", "Bitwise operation": "按位(Bitwise)运算", "Black outfill": "填黑", "Blacklist": "黑名单（禁用tag自动填充）", "Blend Average": "平均混合", "Blur amount:": "模糊量：", "Blurred & stretched overlay": "模糊拉伸的叠加层", "Booru tag autocompletion": "Booru 标签(tag)自动补全", "Both": "全部", "Built with Gradio": "基于 Gradio 构建", "CFG Scale": "提示词相关性(CFG Scale)", "CLIP: maximum number of lines in text file (0 = No limit)": "CLIP：文本文件中的最大行数（0 为无限制）", "CLIP: skip inquire categories": "CLIP：跳过查询类别", "CLiP model": "CLiP模型", "Cache LDSR model in memory": "把LDSR模型缓存在内存中", "Calculates aesthetic score for generated images using CLIP+MLP Aesthetic Score Predictor based on Chad Scorer": "为生成出来的图像计算其美学分数。基于 Chad Scorer 使用 CLIP+MLP 美学分数预测器", "Cancel": "取消", "Canvas Height": "画布高度（使用上传图片时请忽略此项）", "Canvas Width": "画布宽度（使用上传图片时请忽略此项）", "Captions": "描述文本", "Cardssize": "卡片尺寸（附加网络面板）", "Catppuccin Flavor": "Catppuccin 主题样式（背景颜色）", "Catppuccin Theme": "Catppuccin 个性主题", "Change CTRL keybindings to SHIFT": "将 CTRL 绑定更改为 SHIFT", "Change your brush width to make it thinner if you want to draw something.": "绘制内容请先调整笔刷粗细", "Character Tags": "角色标签(Tags)", "Check for updates": "检查更新", "Checkbox": "勾选框", "Checkpoint Format": "模型格式", "Checkpoint Merger": "模型合并", "Checkpoint format": "模型(ckpt)格式", "Checkpoint name": "模型(ckpt)名", "Checkpoints": "模型(ckpt)", "Checkpoints to cache in RAM": "缓存在内存(RAM)中的模型(ckpt)数", "Choose a number of terms from a list, in this case we choose two artists:": "从列表中选几项，这里选了两个艺术家", "Choose latent sampling method": "选择潜变量的采样方法", "Class Batch Size": "类每批数量(Class Batch Size)", "Class Prompt": "类(Class)提示词", "Classification CFG Scale": "分类提示词相关性(Classification CFG scale)", "Classification Dataset Directory": "分类(Classification)数据集目录", "Classification Image Negative Prompt": "分类(classification)图像反向提示词", "Classification Steps": "分类(Classification)迭代步数", "Classifier path": "分类器(Classifier)的路径", "Cleanup non-default temporary directory when starting webui": "启动 WebUI 时清理非默认临时目录", "Clear": "清除", "Clear inputs": "清除输入", "Clear values": "清空数值", "Click here after the generation to show the video": "生成后点这里显示视频", "Click to Upload": "点击上传", "Clip skip": "Clip 跳过层", "Close": "关闭", "Close the video": "关掉视频", "CodeFormer visibility": "CodeFormer 可见度", "CodeFormer weight (0 = maximum effect, 1 = minimum effect)": "CodeFormer 权重(为 0 时效果最大，为 1 时效果最小)", "CodeFormer weight parameter; 0 = maximum effect; 1 = minimum effect": "CodeFormer 权重参数；为 0 时效果最大；为 1 时效果最小", "Color variation": "色彩变化", "Combinations": "组合", "Combinatorial batches": "组合批次", "Combinatorial generation": "组合生成", "Combined": "兼有", "Comma-separated list of tags (\"artist, style, character, 2d, 3d...\")": "此模型的标签，逗号分隔（如、\"艺术家、风格、角色、2D、3D等\"）", "Compare paths (Separate travels from 1st seed to each destination)": "对比变迁轨迹 (从第一个种子分别变迁到每一个目标种子)", "Compatibility": "兼容性", "Composable LoRA": "可自组 LoRA", "Composable Lora": "可自组 LoRA", "Concepts List": "概念列表", "Cond. Image Mask Weight": "图像调节屏蔽度", "Cond.fix: Disabled (none)": "修复时调节：禁用 (无)", "Cond.fix: Empty": "修复时调节：空掉", "Cond.fix: Full": "修复时调节：完全", "Cond.fix: High (recommended)": "修复时调节：高 (推荐)", "Cond.fix: Highest": "修复时调节：最高", "Cond.fix: Low": "修复时调节：小", "Cond.fix: Lowest": "修复时调节：最小", "Cond.fix: Medium": "修复时调节：中", "Conditionals": "条件", "Conditioning Highres.fix strength (for sd-v1-5-inpainting)": "高清修复原图调节强度 (专为 sd-v1-5-inpainting 设计)", "Config Presets": "预设配置", "Config file for Adapter models": "自适应模型(Adapter models)的配置文件", "Config file for Control Net models": "ControlNet 模型的配置文件", "Config-Presets": "预设配置", "Containing directory": "目标模型目录", "ControlNet-M2M": "ControlNet-视频转绘", "Converted checkpoints will be saved in your": "转化换后的模型(checkpoint)将会保存在", "Copy Metadata": "开始复制元数据", "Copy config from": "从...复制配置文件", "Copy image to:": "将图片复制到:", "Copy metadata to other models in directory": "将元数据复制到其他目录中的模型", "Copyright Tags": "版权标签(Tags)", "Cover image": "封面图像", "Create": "创建", "Create Model": "创建模型", "Create a text file next to every image with generation parameters.": "保存图像时，在每个图像旁边创建一个文本文件储存生成参数（开启前一个选项后不建议开启）", "Create aesthetic embedding": "创建美术风格", "Create an aesthetic embedding out of any number of images": "从任意数量的图像中创建美术风格 Embedding", "Create blank canvas": "创建空白画布（使用手绘草稿而非上传的图片）", "Create debug image": "创建调试(debug)图像", "Create embedding": "创建 Embedding", "Create flipped copies": "创建镜像副本", "Create hypernetwork": "创建超网络(Hypernetwork)", "Create images embedding": "创建图集 Embedding", "Crop Images": "剪裁图像", "Crop and resize": "裁剪", "Crop to fit": "裁剪以适应宽高比", "Cropping": "剪裁", "Cross-attention": "Xattn优化方案", "Ctrl+up/down precision when editing (attention:1.1)": "使用 Ctrl + ↑/↓ 设置 \"(tag:1.1)\" 时的精度", "Ctrl+up/down precision when editing ": "使用 Ctrl + ↑/↓ 设置 \"\" 时的精度", "Current Booru": "当前的 Booru", "Custom Name (Optional)": "输出模型文件名（留空则与模型A相同，同目录下会覆盖模型A）", "Custom Theme.": "自定义主题", "Custom settings file": "自定义设置文件", "Dataset Directory": "数据集目录", "Dataset Tag Editor": "数据集标签编辑器", "Dataset directory": "数据集目录", "Deactivate Selected Script": "停用所选脚本", "Decode CFG scale": "解码提示词相关性(CFG scale)", "Decode steps": "解码迭代步数", "Decoder Tile Size": "解码器图块尺寸(Decoder Tile Size)", "Default cropped image output directory": "裁切后的成品的默认输出目录", "Default view for Extra Networks": "附加网络默认视图", "Delete": "删除", "Denoising": "重绘幅度", "Denoising strength": "重绘幅度(Denoising)", "Denoising strength (Inpaint)": "重绘幅度 (局部重绘)", "Denoising strength change factor": "重绘幅度的调整系数", "Depth Maps": "深度图", "Description": "描述", "Destination directory": "目标目录", "Destination seed(s) (Comma separated)": "目标种子 (逗号分割)", "Detect from image": "从图片识别", "Detection Detailer": "检测细致化", "Detection confidence threshold % (A)": "检测置信阈值 % (A)", "Detection confidence threshold % (B)": "检测置信阈值 % (B)", "Dilation factor (A)": "扩张(Dilation)因子 (A)", "Dilation factor (B)": "扩张因子 (B)", "Directories": "目录", "Directory for detected maps auto saving": "探测模式图(detected maps)保存路径", "Directory for saving images using the Save button": "使用“保存”按钮保存图像的目录", "Directory for temporary images; leave empty for default": "临时图像目录，默认为空", "Directory name pattern": "目录名称格式", "Directory path": "目标路径", "Discard weights with matching name": "放弃与下列名称匹配的权重，可以通过写入\"^model_ema\"以舍弃模型中的EMA信息", "Display name for this model": "此模型显示的名称", "Displays autocompletion hints for tags from image booru boards such as Danbooru. Uses local tag CSV files and includes a config for customization.": "显示来自图像板块（image booru，如 Danbooru）的标签(tags)自动补完。使用本地标签(tag) CSV 文件，并包含可用于自定义配置的文件", "Divisions": "分割", "Do not add watermark to images": "不要给图像加水印（建议开启）", "Do not append detectmap to output": "不输出探测模式图(detected maps)（如深度估算图、动作检测图等）", "Do not make DPM++ SDE deterministic across different batch sizes.": "保留 DPM++SDE采样器 在不同的批量之间的结果差异(可以保持旧种子的复现性但改变批量时结果会发生变化)", "Do not save grids consisting of one picture": "只有一张图像时不要保存宫格图（建议开启）", "Do not show any images in results for web": "不在网页的结果中显示任何图像", "Dominant image color": "图像主色", "Don't": "不复制配置文件（推荐）", "Don't generate images": "不生成图像", "Don't outfill": "不进行填充", "Download localization template": "下载本地化模板", "Downscaling": "缩小", "Draw legend": "显示轴类型和值", "DreamArtist": "梦作家", "DreamArtist Create embedding": "梦作家 创建 Embedding", "DreamArtist Train": "梦作家 训练", "DreamArtist-sd-webui-extension": "梦作家", "Dreambooth training based on Shivam Shiaro's repo, optimized for lower-VRAM GPUs.": "基于 Shivam Shiaro 的代码移植的 Dreambooth 训练，为低显存(lower-VRAM)显卡做了优化", "Drop File Here": "拖拽文件到此", "Drop Image Here": "拖拽图像到此处", "Drop Video Here": "拖拽视频到此处", "Drop out tags when creating prompts.": "创建提示词时丢弃标签(tags)", "Dropdown": "下拉列表", "Dry Run": "试运行", "Duration": "持续时间", "Dynamic Prompts": "动态提示词", "Dynamic Prompts enabled": "启用动态提示词", "EMA (nagetive)": "EMA (负)", "EMA (positive)": "EMA (正)", "EMA replace steps (nagative)": "EMA 替换步数 (负)", "EMA replace steps (positive)": "EMA 替换步数 (正)", "Editing Enabled": "开启元数据编辑", "Effects (on until refresh)": "效果（重启后开启）", "Embedding Editor": "Embedding 编辑器", "Embedding Learning rate": "Embedding 学习率", "Embeddings editor": "Embeddings 编辑器", "Embeddings: loaded": "嵌入式(Embeddings):已加载", "Embeddings: skipped": "嵌入式(Embeddings):已跳过", "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention": "强调符：使用 (文字) 使模型更关注该文本，使用 [文字] 使其关注被减少", "Enable": "启用", "Enable AA for Downscaling.": "缩小时启用抗锯齿(AA)", "Enable AA for Upscaling.": "放大时启用抗锯齿(AA)", "Enable Bilingual Localization": "启用双语对照翻译", "Enable CFG-Based guidance": "启用基于CFG的引导(CFG-Based guidance)（配合无提示词(prompt)模式使用时请删除所有提示词，推荐设置\"采样次数：50，CFG：3~5\"，ControlNet将会自动识别输入的模式图）", "Enable Dynamic Thresholding (CFG Scale Fix)": "启用动态阈值(提示词相关性修复 - CFG Scale Fix)", "Enable Jinja2 templates": "启用 Jinja2 模板", "Enable Maintenance tab": "启用 维护 选项卡", "Enable MultiDiffusion": "启用 MultiDiffusion", "Enable Tag Autocompletion": "启用Tag自动补全", "Enable full page image viewer": "启用整页图像查看器（建议开启）", "Enable optimized monocular depth estimation": "启用优化单色深度估算(optimized monocular depth estimation)", "Enable pixelization": "启用像素化", "Enable postprocessing operations in txt2img and img2img tabs": "在文生图/图生图选项卡中启用后处理操作", "Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply.": "在 K 采样器中启用量化以获得更清晰、干净的结果。这可能会改变现有的随机种子。需要保存设置并重启才能应用", "Enabled": "启用", "Encoder Tile Size": "编码器图块尺寸(Encoder Tile Size)", "End Page": "尾页", "Enter hypernetwork layer structure": "输入超网络层结构", "Enter words and color hexes to mark weights on the sliders for guidance. Hint: Use the txt2img prompt token counter or": "输入文字和颜色十六进制代码以在滑块上标记权重作为引导。 提示：使用文生图提示词词元计数器或使用", "Envelope (Outer Fit)": "信封模式（裁切原图）", "Error": "错误", "Escape brackets": "转义括号(防止误识别为权重信息，推荐勾选)", "Escape parentheses on insertion": "对插入的括号进行转义", "Eta noise seed delta": "Eta 噪声种子偏移(ENSD - Eta noise seed delta，建议值31337)", "Examples": "示例", "Exclude tags (split by comma)": "排除以下标签(逗号分隔)", "Excudes (split by comma)": "排除项(逗号分隔)", "Existing Caption Action": "对已有的描述文本的行为", "Existing Caption txt Action": "对已有的 txt 描述文本的行为", "Experimental features (May be solve the problem of erratic training and difficult to reproduce [set EMA to 0.97])": "实验性功能（可能解决训练不稳定和难以重现的问题 [将 EMA 设置为 0.97]）", "Extension": "扩展", "Extension index URL": "扩展列表网址", "Extension script for AUTOMATIC1111/stable-diffusion-webui to travel between prompts in latent space.": "一个在潜空间中对不同提示词之间进行插值渐变，并生成其渐变过程的扩展脚本", "Extensions": "扩展", "Extra": "▼", "Extra Networks": "附加网络", "Extra filename (for small sets of custom tags)": "附加词库文件（用于少量自定义标记）", "Extra generation params": "从生成参数的文本提取潜空间分区参数", "Extra networks tab order": "附加网络标签的顺序", "Extra path to scan for ControlNet models (e.g. training output directory)": "检索 ControlNet 模型的附加目录（如训练输出目录）", "Extra paths to scan for LoRA models, comma-separated. Paths containing commas must be enclosed in double quotes. In the path, \" (one quote) must be replaced by \"\" (two quotes).": "扫描 LoRA 模型的附加目录，以逗号分隔。包含逗号的路径必须用双引号括起来。 在路径中，\"（一个引号）必须替换为\"\"（两个引号）。", "Extract Frames": "提取帧", "Extract every nth frame": "每第 n 帧提取一次", "Extracted Frame Set": "提取好的帧", "Extras": "附加功能", "Face Restore Model": "面部修复模型", "Face restoration": "面部修复", "Fall-off exponent (lower=higher detail)": "衰减指数(越小细节越好)", "Fast Mode": "快速模式", "Favicon": "网页图标", "Favorites": "收藏夹(已保存)", "File": "文件", "File Name": "文件名", "File format for grids": "宫格图的文件格式", "File format for images": "图像的文件格式", "File size limit for the above option, MB": "上述选项的文件大小限制，单位：MB", "Filename join string": "文件名连接用字符串", "Filename word regex": "文件名用词的正则表达式", "Filter models by path name": "下面的模型列表将仅显示此路径下的模型", "First Page": "首页", "Fixed seed": "固定随机种子", "Fixed size to resize images to": "调整图像大小到固定大小", "Float value from 0 to 1": "从 0 到 1 的浮点数数值", "Focal point edges weight": "焦点线条权重", "Focal point entropy weight": "焦点熵权重", "Focal point face weight": "焦点面部权重", "Font for image grids that have text": "有文字的宫格图使用的字体（避免出现X/Y表中文无法显示，可设置为 \"simhei.ttf\"）", "For": "用于", "For hires fix, use width/height sliders to set final resolution rather than first pass (disables Upscale by, Resize width/height to).": "在高分辨率修复中，使用长宽滑块设置最终分辨率(恢复旧版高清修复界面，关闭放大倍率和自适应分辨率设置)", "Force Reset": "强制重置", "Force convert half to float on interpolation (for some platforms)": "插值时强制将半精度转化为单精度浮点（对于某些平台有效，详见 GitHub）", "Found tags": "找到的标签(tags)", "Frames per second": "每秒多少帧", "GFPGAN": "面部修复(GFPGAN)", "GFPGAN visibility": "GFPGAN 可见度", "Gelbooru Prompt": "Gelbooru标签自动摘录", "Generate": "生成", "Generate Captions": "生成描述文本", "Generate Ckpt": "创建模型(ckpt)", "Generate Info": "生成信息", "Generate Preview": "生成预览", "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.": "根据提示词生成一系列关注逐渐转移的图像。此脚本使你能够在提示词中为词元(token)的权重指定一个范围，然后生成从一端到另一端的一系列图像", "Generate random prompts from lexica.art (your prompt is used as a search query).": "从 lexica.art 生成随机提示词（你的提示词会被用作搜索查询）", "Get Tags": "从Gelbooru获取标签 (图像必须是原图且以Gelbooru原始的MD5哈希值命名)", "Gradient Accumulation Steps": "梯度累加步数(Gradient Accumulation Steps)", "Gradient Checkpointing": "梯度进度记录(Gradient Checkpointing) - 以时间换显存", "Gradient accumulation steps": "梯度累加步数(Gradient Accumulation Steps)", "Grid margins (px)": "宫格图边框（像素）", "Grid row count; use -1 for autodetect and 0 for it to be same as batch size": "宫格图行数； 使用 -1 进行自动检测，使用 0 使其与每批数量相同", "Guess Mode": "无提示词(prompt)模式（需在设置中启用\"基于CFG的引导\"）", "Guidance End (T)": "引导退出时机（End）", "Guidance Start (T)": "引导介入时机（Start）", "Guidance strength (T)": "引导强度（迭代参与%，Guidance strength）", "Half Model": "半模型", "Height": "高度", "Help": "帮助", "Help for Jinja2 templates": "Jinja2 模板帮助", "Here, a random number between 1 and 3 words from adjective.txt will be chosen and joined together with the word 'and' instead of the default comma.": "此处，会从 adjective.txt 中选取随机 1 至 3 行，以 'and' (而不是默认的逗号)拼接", "Hide annotator result": "隐藏预处理预览", "Hide extensions with tags": "隐藏含有以下标签的扩展", "Hide samplers in user interface (requires restart)": "在用户界面中隐藏采样器（需要保存设置并重启）", "Highres. Denoising Strength": "高清修复：重绘幅度", "Highres. Height": "高清修复：第一遍高度", "Highres. Width": "高清修复：第一遍宽度", "Highres. percentage chance": "高清修复：随机概率", "Hires steps": "高清修复采样次数", "Hires upscaler": "高清修复放大算法", "Hires. fix": "高清修复", "History": "历史记录", "Horizontal Mirroring": "水平镜像", "Horizontal+Vertical Mirroring": "垂直+水平镜像", "How many results to load at once": "单次加载的结果数量", "HuggingFace Token": "HuggingFace 令牌(Token)", "Hypernetwork": "超网络(Hypernetwork)", "Hypernetwork Learning rate": "超网络学习率", "Hypernetwork strengths": "超网络强度", "Hypernetworks": "超网络(Hypernetwork)", "Hypernetworks List": "可选的超网络列表", "I know it lives as a tab, but this was meant to be a demo at first, now it's growing to something more": "虽然当前它以 选项卡 的形式呈现，但仅作为演示，后续将会有进一步更新（这个页面纯属摆设）", "I know what I am doing.": "我知道我在做什么。", "I'm feeling lucky": "手气不错", "ID input": "ID 输入", "IN00": "输入层00", "IN01": "输入层01", "IN02": "输入层02", "IN03": "输入层03", "IN04": "输入层04", "IN05": "输入层05", "IN06": "输入层06", "IN07": "输入层07", "IN08": "输入层08", "IN09": "输入层09", "IN10": "输入层10", "IN11": "输入层11", "IN_A_00": "模型A 输入层00", "IN_A_01": "模型A 输入层01", "IN_A_02": "模型A 输入层02", "IN_A_03": "模型A 输入层03", "IN_A_04": "模型A 输入层04", "IN_A_05": "模型A 输入层05", "IN_A_06": "模型A 输入层06", "IN_A_07": "模型A 输入层07", "IN_A_08": "模型A 输入层08", "IN_A_09": "模型A 输入层09", "IN_A_10": "模型A 输入层10", "IN_A_11": "模型A 输入层11", "IN_B_00": "模型B 输入层00", "IN_B_01": "模型B 输入层01", "IN_B_02": "模型B 输入层02", "IN_B_03": "模型B 输入层03", "IN_B_04": "模型B 输入层04", "IN_B_05": "模型B 输入层05", "IN_B_06": "模型B 输入层06", "IN_B_07": "模型B 输入层07", "IN_B_08": "模型B 输入层08", "IN_B_09": "模型B 输入层09", "IN_B_10": "模型B 输入层10", "IN_B_11": "模型B 输入层11", "Ids for tokenization (example: 9061, 631, 736)": "用于词元化的 ID (例： 9061, 631, 736)", "If $$ is not provided, then 1$$ is assumed.": "若没提供 $$，默认为 1$$", "If the chosen number of terms is greater than the available terms, then some terms will be duplicated, otherwise chosen terms will be unique. This is useful in the case of wildcards, e.g.": "选的项数多于提供的项数时，有些项会重复，其余情况各选项会保持唯一；\n重复对于通配符很有用，例如：", "If the saved image file size is above the limit, or its either width or height are above the limit, save a downscaled copy as JPG": "如果保存的图像文件大小超过限制，或者其宽度或高度超过限制，将其缩小的副本另存为 JPG 格式", "If this is set, then random prompts are generated, even if the seed is the same.": "如果设置了此项，则会生成随机提示词，即使种子相同", "If you are using these templates, please let me know if they are useful.": "如果你在用这些模板，请告诉我它们是否有用", "Ignore selected VAE for stable diffusion checkpoints that have their own .vae.pt next to them": "对于拥有同名 .vae.pt 的模型，忽略掉选中的 VAE", "Image": "图像", "Image Browser": "图库浏览器", "Image Parameters": "图像参数", "Image Tags": "图像标签(Tags)", "Image border outfill method:": "图像边缘的填充方法：", "Image browser": "图库浏览器", "Image creation progress preview mode": "图像生成过程预览的模式", "Image for img2img": "图生图的图像", "Image for inpainting with mask": "用于局部重绘并手动画蒙版的图像", "Image height": "图像高度", "Image width": "图像宽度", "Image with MD5 Hash": "以MD5哈希值命名的图片文件", "Images directory": "图像目录", "Images filename pattern": "图像文件名格式", "Implements an expressive template language for random or combinatorial prompt generation along with features to support deep wildcard directory structures.": "为随机或组合式提示词的生成实现了一种表达性模板语言，并支持深层目录结构中的通配符", "Import Background Images": "导入 背景图像", "Import CSS file": "导入 CSS 文件", "Import Files": "导入文件", "Import Logo's (png)": "导入 Logo（PNG格式）", "Import favicons (svg)": "导入 网页图标（SVG格式）", "In this case, a random number of artists between 1 and 3 is chosen.": "此例中，会从中随机选 1 至 3 个艺术家", "Include Sub Grids": "预览子宫格图", "Include Sub Images": "预览子图像", "Include artist tags in tag string": "在标签字串中包含画师标签", "Include character tags in tag string": "在标签字串中包含角色标签", "Include confident of tags matches in results": "将置信度作为权重写入生成的Tags (不推荐勾选)", "Include copyright tags in tag string": "在标签字串中包含版权标签", "Include images in sub directories": "显示子目录中的图片（建议开启）", "Include meta tags in tag string": "在标签字串中包含属性标签", "Increase coherency by padding from the last comma within n tokens when using more than 75 tokens": "当使用超过 75 个词元(tokens)时，通过从 n 个词元中的最后一个逗号留空来提高一致性", "Info object": "全部信息", "Init": "初始", "Initialization text": "初始化文字", "Inpaint": "局部重绘", "Inpaint area": "重绘区域", "Inpaint at full resolution": "全分辨率局部重绘", "Inpaint at full resolution padding, pixels": "预留像素", "Inpaint masked": "重绘蒙版内容", "Inpaint model B detections before model A runs": "在模型 A 运行之前，先局部重绘模型 B 的检测", "Inpaint not masked": "重绘非蒙版内容", "Inpaint sketch": "局部重绘(手涂蒙版)", "Inpaint upload": "局部重绘(上传蒙版)", "Inpainting conditioning mask strength": "局部重绘时图像调节的蒙版屏蔽强度", "Input directory": "输入目录", "Input images directory": "输入图像目录", "Insert after": "在后面插入", "Insert before": "在前面插入", "Inspiration": "灵感", "Install": "安装", "Install from URL": "从网址安装", "Installed": "已安装", "Interpolation": "插值", "Interpolation Method": "合并算法（具体说明会显示在页面顶部）", "Interrogate": "开始反推", "Interrogate\nCLIP": "　　CLIP　　\n反推提示词", "Interrogate\nDeepBooru": "DeepBooru\n反推提示词", "Interrogate Options": "反推提示词（图生图页面）", "Interrogate: deepbooru score threshold": "deepbooru 最低置信度阈值（仅摘录高于此置信度的tag）", "Interrogate: deepbooru sort alphabetically": "deepbooru 反推结果按字母顺序排序（不推荐开启）", "Interrogate: include ranks of model tags matches in results (Has no effect on caption-based interrogators).": "将置信度作为tag权重写入结果（对基于生成自然语言描述的反推没有影响）", "Interrogate: keep models in VRAM": "将模型保存在显存(VRAM)中（不建议开启）", "Interrogate: maximum description length": "最大描述长度", "Interrogate: minimum description length (excluding artists, etc..)": "最小描述长度（不包括艺术家等）", "Interrogate: num_beams for BLIP": "BLIP 的 num_beams", "Interrogator": "反推算法", "Interrupt": "中止", "Invert Input Color": "反色模式", "Invert colors if your image has white background.": "使用白色背景图片时请启用\"反色模式\"", "Is negative text": "是反向提示词", "Iterate seed every line": "每行输入都换一个随机种子", "Iterations": "迭代", "Jinja2 documentation.": "Jinja2 文档", "Jinja2 templates": "Jinja2 模板", "Jinja2 templates are based on the Jinja2 template engine. For more information see the": "Jinja2 模板基于 Jinja2 模板引擎，更多信息参见", "Jinja2 templates is an experimental feature for advanced template generation. It is not recommended for general use unless you are comfortable with writing scripts.": "Jinja2 模板是一个用于高级模板生成的实验特性。如果不熟悉编写脚本，正常使用时不推荐启用", "Just Resize": "仅调整大小（拉伸）", "Just resize": "拉伸", "Just resize (latent upscale)": "直接缩放 (放大潜变量)", "KaimingNormal": "Kaiming 正态", "KaimingUniform": "Kaiming 均匀", "Keep -1 for seeds": "保持随机种子为-1", "Keep empty if dont use.": "不使用请留空", "Keep input image size": "保持输入图像尺寸", "Keep resolution": "保持分辨率不变", "Keyframes": "关键帧", "Keywords": "关键词", "Kitchen Theme": "Kitchen 主题", "Krita Plugin.": "Krita 插件", "LDSR processing steps. Lower = faster": "LDSR 处理步数。越少越快", "LLuL": "潜变量局部放大器", "Label": "标记", "Latent": "潜变量", "Latent (antialiased)": "潜变量 (抗锯齿)", "Latent (bicubic antialiased)": "潜变量 (bicubic 抗锯齿)", "Latent (bicubic)": "潜变量 (bicubic)", "Latent (nearest)": "潜变量 (最近邻)", "Latent (nearest-exact)": "潜变量 (最近邻-整数)", "Latent Couple": "潜变量成对", "Latent Mirror mode": "镜像潜变量模式", "Latent Mirror style": "潜变量镜像方式", "Latent Mirroring": "镜像潜变量", "Latent tile batch size": "潜变量分块(Latent tile)批处理规模", "Latent tile height": "潜变量分块(Latent tile)高度", "Latent tile overlap": "潜变量分块(Latent tile)重叠", "Latent tile width": "潜变量分块(Latent tile)宽度", "Learning Rate": "学习率", "Learning Rate Scheduler": "学习率调度器(Scheduler)", "Learning Rate Warmup Steps": "学习率的预热步数", "Leave blank to save images to the default path.": "留空以将图像保存到默认路径", "Leave blank to save images to the same path.": "留空则输出到输入目录下", "Leave blank to use base model VAE.": "留空以使用基底模型的 VAE", "Leave blank to use same filename as original.": "留空以使用与原始文件相同的文件名", "Leave empty for auto": "留空时自动生成", "Legacy hash": "旧哈希值", "Lerp": "线性插值", "License: MIT": "许可: MIT", "Licenses": "许可协议", "Link to image page": "链接到图片页面", "List of model names (with file extension) or their hashes to use as black/whitelist, separated by commas.": "模型黑/白名单列表（用于区分自然语言模型，填入模型哈希值或其文件名（带后缀），逗号分隔）", "List of prompt inputs": "提示词输入列表", "List-Up checkpoints": "列出模型(ckpts)", "Literals": "字面量", "Live preview subject": "实时预览的主体", "Live previews": "实时预览", "LoRA model name filter": "LoRA 模型名称过滤器", "Load": "载入", "Load Settings": "载入设定", "Load Video Settings": "载入视频设置", "Load from JSON": "从 JSON文件 加载", "Load from:": "加载自：", "Load results": "加载结果", "Loading...": "载入中...", "Local directory name": "本地目录名", "Localization (requires restart)": "本地化翻译（需要保存设置并重启）", "Localization dirs": "本地化文件目录", "Localization file (Please leave `User interface` - `Localization` as None)": "本地化翻译文件 (请保持 `用户界面` - `本地化` 的选项为 None/无)", "Log directory": "日志目录", "Loop back to initial seed": "再变迁回初始种子", "Loopback": "回送", "Loops": "迭代次数", "Low VRAM": "低显存优化（需配合启动参数\"--lowvram\"）", "M00": "中间层", "MBW": "分块设置权重(MBW)", "MBW Each": "AB模型分别分块设置权重(MBW Each)", "M_A_00": "模型A 中间层", "M_B_00": "模型B 中间层", "Magic prompt": "魔法提示词", "Magic prompt creativity": "魔法提示词创意", "Maintenance": "维护", "Make K-diffusion samplers produce same images in a batch as when making a single image": "使 K-diffusion 采样器 批量生成与生成单个图像时，产出相同的图像", "Make a backup copy of the model being edited when saving its metadata.": "保存元数据时，备份正在编辑的模型", "Mask": "蒙版", "Mask blur": "蒙版模糊", "Mask mode": "蒙版模式", "Mask transparency": "蒙版透明度", "Masked content": "蒙版蒙住的内容", "Match Frame 0 HSV": "匹配帧 0 HSV", "Match Frame 0 LAB": "匹配帧 0 LAB", "Match Frame 0 RGB": "匹配帧 0 RGB", "Max Batch Count": "最大批次数量", "Max Image Size": "最大图像尺寸", "Max Token Length": "最大词元(Token)长度", "Max magic prompt length": "魔法提示词最大长度", "Max number of dataset folders to show": "要显示的最大数据集文件夹数", "Max number of top tags to show": "要显示的最大常见标签数", "Max prompt words for [prompt_words] pattern": "[prompt_words] 格式的最大提示词数量", "Max steps": "最大迭代步数", "Maximum number of images in upscaling cache": "图像放大缓存中的最大图片数量", "Maximum results": "单页最大结果数量", "Maximum steps fraction to mirror at": "镜像干涉止步于总迭代步数的", "Memory": "内存及显存用量", "Memory Attention": "内存注意", "Memory optimization": "显存优化选项", "Merge": "合并", "Merge Block Weighted": "模型合并(分块加权)", "Merge Board": "合并面板", "Meta Tags": "属性标签(Tags)", "Metadata to show in XY-Grid label for Model axes, comma-separated (example: \"ss_learning_rate, ss_num_epochs\")": "显示在X/Y表标签下的元数据选项，逗号分隔（示例：\"ss_learning_rate, ss_num_epochs\"）", "Mimic CFG Scale": "模拟提示词相关性(Mimic CFG Scale)", "Minimum number of pages per load": "每次加载的最小页数", "Mixed Precision": "混合精度", "Mode to add the extra tags to the main tag list": "将额外标记添加到主标记列表的模式", "Mode to use for model list": "将以上列表内的模型设为", "Model": "模型", "Model 1": "模型 1", "Model 2": "模型 2", "Model 3": "模型 3", "Model 4": "模型 4", "Model 5": "模型 5", "Model A": "模型A", "Model B": "模型B", "Model Converter": "模型格式转换", "Model Path": "模型路径", "Model cache size (requires restart)": "模型缓存数量（需要保存设置并重启）", "Model description/readme/notes/instructions": "模型的描述信息", "Model hash": "模型哈希值", "Model path": "模型路径", "Model path filter": "模型路径过滤", "Model_A": "模型A", "Model_B": "模型B", "Models": "模型", "Models...": "模型列表", "Modules": "模块", "Most frequent tags in captions": "训练用描述文本里tags的频率列表", "Move VAE and CLIP to RAM when training if possible. Saves VRAM.": "训练时将 VAE 和 CLIP 从显存(VRAM)移放到内存(RAM)如果可行的话，节省显存(VRAM)", "Move VAE to GPU": "将 VAE 移放到 GPU", "Move buttons copy instead of move": "将图库浏览器内所有\"移动\"按钮改为\"复制\"按钮", "Move completion popup together with text cursor": "补全弹窗随文本光标一起移动（建议开启）", "Move face restoration model from VRAM into RAM after processing": "面部修复处理完成后，将其模型从显存(VRAM)移至内存(RAM)", "Move to directory": "将图片移动到目标路径", "Move to favorites": "移动到收藏夹", "Move/Copy/Delete matching .txt files": "将图片的移动、复制、删除操作应用到与之同名的 txt 文件（建议开启）", "Multi ControlNet: Max models amount (requires restart)": "Multi ControlNet 的最大网络数量（需要保存设置并重启，启用后可同时设置多个 ControlNet，允许不同模型联合控制与相同模型叠加控制，可用于约束多人动作，也可用于多维度约束）", "Multi Merge": "多重合并", "Multi Model Merge": "多重模型合并", "Multi Proc Cmd": "多进程命令", "MultiDiffusion with Tiled VAE": "MultiDiffusion 与 分块 VAE", "Multiple Hypernetworks": "加载多个超网络(Hypernetworks)", "Multiple lane merge support(up to 10). Save and Load your merging combination as Recipes, which is simple text.": "多通道合并支持（最多 10 个）。 保存或加载你的合并组合为配方，也就是一些简单的文本", "Multiplication (2^N)": "放大指数（2^N）", "Multiplier (M) - set to 0 to get model A": "倍率(M) - 设为0时输出模型与A完全相同", "Multiplier for extra networks": "附加网络默认倍率", "NAIConvert": "NAI 转换", "NSFW": "成人内容", "NSFW checker": "成人内容检测器", "Name": "名称", "Nearest": "最邻近(整数缩放)", "Negative lr weight": "反向的学习率权重", "Negative prompt": "反向提示词", "Negative prompt (press Ctrl+Enter or Alt+Enter to generate)": "反向提示词（按 Ctrl+Enter 或 Alt+Enter 生成）\nNegative prompt", "Network module": "附加网络模式", "Network module 1": "附加网络类型 1", "Network module 2": "附加网络类型 2", "Network module 3": "附加网络类型 3", "Network module 4": "附加网络类型 4", "Network module 5": "附加网络类型 5", "Next Page": "下一页", "No": "否", "No interpolation": "无插值", "Noise multiplier for img2img": "图生图噪声倍率", "None": "无", "Normal": "正态", "Nothing": "无", "Nothing here. Add some content to the following directories:": "无内容，请将模型添加到以下目录:", "Number": "数量", "Number of Samples to Generate": "要生成的样本数量", "Number of clusters:": "簇数：", "Number of columns on image gallery": "图库显示图像列数", "Number of columns on the page": "每页列数", "Number of frames for lead in/out": "渐入/渐出帧数", "Number of negative vectors per token": "每个词元(token)的反向向量数", "Number of random seed(s)": "随机种子数量", "Number of repeats for a single input image per epoch; used only for displaying epoch number": "每期(epoch)中单个输入图像的重复次数； 仅用于显示期数", "Number of rows on the page": "每页行数", "Number of vectors per token": "每个词元(token)的向量数", "OUT00": "输出层00", "OUT01": "输出层01", "OUT02": "输出层02", "OUT03": "输出层03", "OUT04": "输出层04", "OUT05": "输出层05", "OUT06": "输出层06", "OUT07": "输出层07", "OUT08": "输出层08", "OUT09": "输出层09", "OUT10": "输出层10", "OUT11": "输出层11", "OUT_A_00": "模型A 输出层00", "OUT_A_01": "模型A 输出层01", "OUT_A_02": "模型A 输出层02", "OUT_A_03": "模型A 输出层03", "OUT_A_04": "模型A 输出层04", "OUT_A_05": "模型A 输出层05", "OUT_A_06": "模型A 输出层06", "OUT_A_07": "模型A 输出层07", "OUT_A_08": "模型A 输出层08", "OUT_A_09": "模型A 输出层09", "OUT_A_10": "模型A 输出层10", "OUT_A_11": "模型A 输出层11", "OUT_B_00": "模型B 输出层00", "OUT_B_01": "模型B 输出层01", "OUT_B_02": "模型B 输出层02", "OUT_B_03": "模型B 输出层03", "OUT_B_04": "模型B 输出层04", "OUT_B_05": "模型B 输出层05", "OUT_B_06": "模型B 输出层06", "OUT_B_07": "模型B 输出层07", "OUT_B_08": "模型B 输出层08", "OUT_B_09": "模型B 输出层09", "OUT_B_10": "模型B 输出层10", "OUT_B_11": "模型B 输出层11", "Old unmaintained localizations that used to be a part of main repository": "曾经在主分支上但现在不再维护的旧语言包", "Once again, this `dynamic` demo has not removed/re-implemented all features present": "再次声明，这个选项卡现在只是个摆设，所有操作都要自己去改 CSS 文件，单击\"应用风格\"与\"应用设置\"重启后生效", "Only": "只有", "Only copy to models with no metadata": "仅复制到没有元数据的模型（不覆盖原有元数据）", "Only copy to models with same session ID": "仅复制到具有相同 session ID 的模型", "Only extract keyframes (recommended)": "只提取关键帧（推荐）", "Only masked": "仅蒙版", "Only masked padding, pixels": "仅蒙版模式的边缘预留像素", "Only show .safetensors format models": "只显示 .safetensors 格式的模型", "Only show alias": "仅显示别称", "Only show models that have/don't have user-added metadata": "仅显示(有/无)用户自行添加元数据的模型", "Only use Random seeds (Unless comparing paths)": "只用随机种子 (除非需要对比变迁轨迹)", "Only use mid-control when inference": "仅在生成图片(推理 - inference)时使用中间层控制(mid-control)", "Opacity": "透明度", "Open for Clip Aesthetic!": "打开以调整 Clip 的美术风格！", "Open...": "打开...", "OpenPose Editor": "OpenPose 编辑器", "Optionally use [filewords] to read image captions from files.": "可选择使用 [filewords] 去从文件中读取图像的描述", "Order": "排序方式", "Original First": "原文在上面", "Original file's hash (good for deleting duplication)": "原文件哈希(sha1算法)+输出文件后缀（方便去重）", "Original filename without extension": "原文件名+输出文件后缀", "Original negative prompt": "初始反向提示词", "Original prompt": "初始提示词", "Others": "其他", "Outfill border color:": "填充颜色：", "Outfill method:": "填充方法：", "Outpainting direction": "向外绘制的方向", "Outpainting mk2": "向外绘制第二版", "Output Model Name": "输出模型文件名", "Output directory": "输出目录", "Output directory for grids; if empty, defaults to two directories below": "宫格图的输出目录； 如果为空，则默认为以下两个目录", "Output directory for images from extras tab": "附加功能选项卡的输出目录", "Output directory for images; if empty, defaults to three directories below": "图像的输出目录； 如果为空，则默认为以下三个目录", "Output directory for img2img grids": "图生图宫格的输出目录", "Output directory for img2img images": "图生图的输出目录", "Output directory for mask previews": "蒙版预览的输出目录", "Output directory for masks": "蒙版输出目录", "Output directory for txt2img grids": "文生图宫格的输出目录", "Output directory for txt2img images": "文生图的输出目录", "Output filename format": "输出文件名格式", "Output filename formats": "输出文件名格式说明", "Override `Denoising strength` to 1?": "覆写 `重绘幅度` 为 1?", "Override `Sampling Steps` to the same value as `Decode steps`?": "覆写 `采样迭代步数` 为 `解码迭代步数`?", "Override `Sampling method` to Euler?(this method is built for it)": "覆写 `采样方法` 为 Euler?(这个方法就是为它设计的)", "Override `prompt` to the same value as `original prompt`?(and `negative prompt`)": "覆写 `提示词` 为 `初始提示词`?(`反向提示词` 同理)", "Override settings": "覆盖设置", "Overwrite Old Embedding": "覆写旧的 Embedding", "Overwrite Old Hypernetwork": "覆写旧的超网络", "Overwrite image size": "覆写图像尺寸设置", "PNG Info": "图片信息", "Pad Tokens": "词元(Tokens)垫齐", "Pad begin/end frames": "预留开始/结束帧", "Page Index": "页码", "Page Number": "页数", "Parse Recipe": "剖析配方", "Parse Result": "剖析结果", "Path to JSON file with concepts to train.": "用于训练概念的 JSON 文件路径", "Path to classifier ckpt, can be empty": "分类器的路径，可留空", "Path to directory where to write outputs": "进行输出的目录路径", "Path to directory with input images": "带有输入图像的目录路径", "Path to read videos from": "读取视频的路径", "Path to store extracted frame sets in": "储存截取帧的路径", "Paths for saving": "保存路径", "Pixel size": "像素块大小", "Pixels to expand": "拓展的像素数", "Platform": "运行平台", "Please use smaller tile size when see CUDA error: out of memory.": "当显存溢出(CUDA error: out of memory)时，请调小图块尺寸(Tile Size)", "Plot": "绘表", "Poor man's outpainting": "效果稍差的向外绘制", "Posex": "3D OpenPose 编辑器(Posex)", "Positions": "位置", "Positive \"filewords\" only": "只限正向 \"filewords\"", "Post-Processing": "后处理", "Postprocessing": "后处理", "Postprocessing operation order": "后处理操作顺序", "Precision": "精度", "Preload images at startup": "在启动时预加载图像", "Preprocess": "预处理", "Preprocess images": "图像预处理", "Preprocessor": "预处理器（直接上传模式图或草稿时可选\"无\"）", "Preset": "预设", "Preset Weights": "预设权重", "Preset_Weights": "预设权重", "Pretrained VAE Name or Path": "预训练的 VAE 名字或者路径", "Prev Page": "上一页", "Prevent empty spots in grid (when set to autodetect)": "启用自动检测时，宫格图中不用空位填充（不开启时3张图会以2*2的形式排列，其中第四幅图为空，开启后行列仅可能为图片数量的因数）", "Preview annotator result": "预览预处理结果", "Previous Page": "前一页", "Primary detection model (A)": "首要检测模型 (A)", "Primary model (A)": "模型 A", "Print debug logs to the console": "将调试日志输出到控制台", "Print extra hypernetwork information to console.": "将额外的超网络(hypernetwork)信息输出到控制台", "Print image deletion messages to the console": "将 \"删除图片\" 的动作作为信息输出到控制台", "Print warning logs to the console": "将警告信息输出到控制台", "Prior Loss Weight": "先验损失权重(Prior Loss Weight)", "Process images in a directory on the same machine where the server is running.": "处理服务器主机上某一目录里的图像", "Progressbar/preview update period, in milliseconds": "进度条/预览更新周期(毫秒)", "Prompt": "提示词", "Prompt (press Ctrl+Enter or Alt+Enter to generate)": "提示词（按 Ctrl+Enter 或 Alt+Enter 生成）\nPrompt", "Prompt S/R": "提示词搜索/替换", "Prompt Travel": "提示词变迁", "Prompt for tokenization": "给词元化准备的提示词", "Prompt matrix": "提示词矩阵", "Prompt order": "提示词顺序", "Prompt template file": "提示词模版文件", "Prompts": "提示词", "Prompts from file or textbox": "从文本框或文件载入提示词", "Provides an interface to browse created images in the web browser.": "在网页浏览器里提供一个查看生成图像历史的界面", "Pruning Methods": "压缩方案", "Put variable parts at start of prompt": "把可变部分放在提示词文本的开头", "Put weight sets. float number x 25": "输入权重，共25个浮点数，逗号分隔", "Quality for saved jpeg images": "保存的 JPEG 图像的质量", "Quicksettings list": "快捷设置列表（将显示在页面最上方，建议填入\"sd_model_checkpoint,sd_vae\"）", "RGB to BGR": "RGB格式法线贴图转BGR", "Random choices": "随机选择", "Randomize": "随机化", "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.": "随机显示一位艺术家或某艺术流派的图像，选择后会显示更多该艺术家或艺术流派的图像。所以你不用担心在创作时难以选择出想要的艺术风格", "Randomness": "随机度", "Range of stepped values (min, max, step)": "含步幅的随机范围 (最小, 最大, 步幅)", "Rating": "评分", "Rating confidents": "分级信息置信度", "Read parameters (prompt, etc...) from txt2img tab when making previews": "进行预览时，从文生图选项卡中读取参数（提示词等）", "Recipe": "配方", "Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8": "推荐设置：采样迭代步数：80-100，采样器：Euler a，重绘幅度：0.8", "Recommended settings: Use from inpaint tab, inpaint at full res ON, denoise <0.5": "推荐设置：于局部重绘选项卡使用，开启全分辨率局部重绘，重绘幅度(Denoising) < 0.5", "Reconstruction loss weight": "重建 损失(loss) 权重", "Reflect image around border": "从边缘镜像图像内容", "Refresh": "刷新", "Refresh Embeddings": "刷新 Embeddings", "Refresh List": "刷新列表", "Refresh data": "刷新数据", "Refresh models": "刷新模型列表", "Regions": "分区", "Related to original file": "与原文件相关的命名参数", "Related to output file": "与输出文件有关的命名参数", "Reload Checkpoints": "重载模型(ckpt)", "Reload UI": "重启 WebUI", "Reload checkpoint": "刷新模型列表", "Reload custom script bodies (No ui updates, No restart)": "重新加载自定义脚本主体（无用户界面更新，无重启）", "Remove": "移除", "Remove All": "移除所有", "Remove Stylesheet": "移除 风格样式表", "Remove results with the \"animated\" tag": "删除带有\"animated\"(动图)标签的结果", "Renew Page": "刷新页面", "Replace Class with Subject in Caption": "将描述文本中的类(Class)替换成主体(Subject)", "Replace order": "取代顺序", "Replace spaces with a comma and a space": "用逗号', '替换空格", "Replace underscores with spaces": "用空格替换下划线'_'", "Replace underscores with spaces on insertion": "将下划线替换为空格", "Replaces NSFW images with black.": "将含有成人内容的图像以纯黑图替换", "Request browser notifications": "请求浏览器通知（生成完成时在屏幕右下角显示通知）", "Reset": "清空画面", "Reset Aspect Ratio": "重置纵横比", "Reset Tile Size": "重设图块尺寸(Tile Size)", "Reset recipe text area": "重置配方文本区域", "Reset vars": "重置变量(vars)", "Resize": "缩放比例", "Resize Mode": "画面缩放模式", "Resize and fill": "填充", "Resize crops to 512x512": "缩放剪裁至 512x512", "Resize height to": "将高度调整到", "Resize mode": "缩放模式", "Resize seed from height": "高度(Resize seed)", "Resize seed from width": "宽度(Resize seed)", "Resize width to": "将宽度调整到", "Resolution": "分辨率", "Restore Faces": "面部修复", "Restore faces": "面部修复", "Reuse original image": "复用原图", "Reverse model sort order": "逆序排序", "Roll Channels": "色彩通道轮替", "Run": "运行", "Run Merge": "开始合并", "Run benchmark": "跑分", "SD VAE": "模型的 VAE (SD VAE)", "SD upscale": "使用 SD 放大(SD upscale)", "SD-latent-mirroring": "镜像潜变量", "SLerp": "球面线性插值", "Sample CFG Scale": "样本提示词相关性(CFG Scale)", "Sample Image Prompt": "样本图像的提示词", "Sample Seed": "样本种子", "Sample Steps": "样本迭代步数", "Sampler": "采样方法 (Sampler)", "Sampler parameters": "采样器参数", "Sampling Steps": "采样迭代步数(Steps)", "Sampling method": "采样方法(Sampler)", "Sampling steps": "采样迭代步数(Steps)", "Save": "保存", "Save & Restart": "保存并重启", "Save Embedding": "保存 Embedding", "Save JSON": "储存为 JSON文件", "Save Metadata": "保存元数据", "Save PNG": "保存为 PNG图片", "Save Settings": "储存设置", "Save Video Settings": "保存视频设置", "Save a copy of embedding to log directory every N steps, 0 to disable": "每 N 步将 Embedding 的副本保存到日志目录，0 表示禁用", "Save a copy of image before applying color correction to img2img results": "在对图生图结果应用颜色校正之前保存图像副本", "Save a copy of image before applying highres fix.": "在做高清修复之前保存初始图像副本", "Save a copy of image before doing face restoration.": "在进行面部修复之前保存图像副本", "Save an csv containing the loss to log directory every N steps, 0 to disable": "每 N 步保存一个包含 loss 的 csv 表格到日志目录，0 表示禁用", "Save an image to log directory every N steps, 0 to disable": "每 N 步保存一张图像到日志目录，0 表示禁用", "Save as float16": "以 float16 储存", "Save as half": "以 float16 保存", "Save as safetensors": "存为safetensors格式", "Save crops to:": "储存裁剪好的成品到：", "Save grids to a subdirectory": "将宫格图保存到子目录", "Save images to a subdirectory": "将图像保存到子目录", "Save images with embedding in PNG chunks": "保存图像，并在 PNG 图片文件中嵌入 Embedding 文件", "Save mask previews": "保存蒙版预览", "Save masks": "保存蒙版", "Save results as video": "保存结果为视频", "Save text information about generation parameters as chunks to png files": "将有关生成参数的文本信息，作为块保存到 PNG 图片文件中（强烈建议开启）", "Save with JSON": "保存JSON文件", "Saved directories": "已保存的路径", "Saving images/grids": "保存图像/宫格图", "Saving to a directory": "保存到目录", "Scale Factor": "缩放系数", "Scale by": "等比缩放", "Scale to": "指定分辨率缩放", "Scale to Fit (Inner Fit)": "缩放模式（扩展原图，推荐）", "Scan Exif-/.txt-data (slower, but required for exif-keyword-search)": "扫描图片的 Exif 信息与同名 txt 文件（会拖慢读取速度，但使用搜索生成信息关键字的时候必须开启）", "Scheduler": "调度器(Scheduler)", "Scribble Mode (Invert colors)": "涂鸦模式（反色，强制预处理器重新识别）", "Script": "脚本", "Seamless Image Fusion, along with vram efficient tiled vae script.": "无缝图像融合，配合显存(VRAM)优化过的 分块 VAE 脚本", "Search": "搜索", "Search Booru": "搜 Booru", "Search Results": "搜寻结果", "Search by alias": "使用别称搜索", "Search by translation": "使用译名搜索", "Search for Loras": "搜索 LoRA 模型", "Search for embeddings": "搜索 嵌入式(Embedding)", "Search for hypernetworks": "搜索 超网络(Hypernetwork)", "Search for wildcards": "使用通配符", "Search negative prompt": "检索范围是否包含负面提示词", "Search string": "搜字串", "Search...": "搜索...", "Secondary detection model (B) (optional)": "次要检测模型 (B) (可选)", "Secondary model (B)": "模型 B", "See": "查看", "Seed": "随机种子(seed)", "Seed travel": "种子变迁", "Select": "选择", "Select Image": "选择图像", "Select Layer weights initialization. Recommended: Kaiming for relu-like, Xavier for sigmoid-like, Normal otherwise": "选择初始化层权重的方案。建议：类relu 用 Kaiming； 类sigmoid 用 Xavier；其它就用正态", "Select activation function of hypernetwork. Recommended : Swish / Linear(none)": "选择超网络的激活函数。建议：Swish / Linear(线性，等于不用)", "Select joining char": "选择分隔符", "Select prompt": "选择提示词(prompt)", "Selected": "已选择的", "Send image to tag selection": ">> 标签(Tag)选择", "Send interrupt": "发送中断指令", "Send seed when sending prompt or image to other interface": "将提示词或者图像发送到 >> 其他界面时，把随机种子也传送过去（建议开启）", "Send size when sending prompt or image to another interface": "将提示词或者图像发送到 >> 其他界面时，把尺寸数据也传送过去", "Send this image to ControlNet.": "将此图像发送到 ControlNet", "Send to": "发送到", "Send to Multi-Merge": ">> 多重合并", "Send to Recipe": ">> 配方", "Send to extras": ">> 附加功能", "Send to img2img": ">> 图生图", "Send to img2img:": "将模型发送到图生图页面\n（数字按钮1-5对应模型1-5）", "Send to inpaint": ">> 局部重绘", "Send to txt2img": ">> 文生图", "Send to txt2img:": "将模型发送到文生图页面\n（数字按钮1-5对应模型1-5）", "Separate UNet/Text Encoder weights": "单独设置 UNet/Text Encoder 的权重", "Server start time": "服务器启动时间", "Settings": "设置", "Shift attention": "关注转移", "Show '?' next to tags, linking to its Danbooru or e621 wiki page (Warning: This is an external site and very likely contains NSFW examples!)": "在tag一侧显示‘?’用于链接到其danbooru或e621 wiki页面（警告：页面含有成人内容，谨慎浏览，需要科学上网）", "Show Width/Height and Batch sliders in same row": "将批次与批量设置整合到长宽设置的右侧", "Show all pages": "显示所有页面", "Show all results": "显示所有结果", "Show extra options": "显示额外设置", "Show generated images in ui": "在用户界面上显示生成了的图像", "Show generation progress in window title.": "在窗口标题中显示生成进度", "Show grid in results for web": "在网页的结果中显示宫格图（建议开启）", "Show images zoomed in by default in full page image viewer": "在整页图像查看器中，默认放大显示图像（建议开启）", "Show live previews of the created image": "显示已生成图像的实时预览（不建议开启）", "Show new live preview image every N sampling steps. Set to -1 to show after completion of batch.": "每N个采样步骤更新一次实时预览图像，设置为-1以在每批次完成后显示，设置为0关闭实时预览 (建议设为0，开启会占用大量显存和显卡算力)", "Show previews of all images generated in a batch as a grid": "以宫格图的形式，预览批量生成的所有图像（建议开启）", "Show progressbar": "显示进度条", "Show result images": "显示输出图像", "Show warnings in console.": "将警告信息输出到控制台", "Shows a gallery of generated pictures by artists separated into categories.": "将艺术家按类别划分，并显示其生成出来的图像", "Shuffle tags by ',' when creating prompts.": "创建提示词时按 ',' 打乱标签(tags)", "Sigma adjustment for finding noise for image": "为寻找图中噪点的 Sigma 调整", "Sigma max": "最大 Sigma", "Sigma min": "最小 Sigma", "Sigma noise": "Sigma 噪声", "Simplified Chinese localization, recommend using with Bilingual Localization.": "简体中文本地化，推荐与双语对照翻译插件共同使用。", "Single Image": "单张图像", "Single process": "单张图片", "Sketch": "绘图", "Skip": "跳过", "Skip img2img processing when using img2img initial image": "使用图生图初始化图像时跳过图生图处理", "Skip/Reset CLIP position_ids": "跳过或重置CLIP position_ids键值", "Slerp angle": "球面线性插值角度", "Slerp interpolation": "球面线性插值", "Small script for AUTOMATIC1111/stable-diffusion-webui to create images that exists between seeds.": "一个用于生成不同随机种子之间的渐变过程的小脚本", "Smart Preprocess": "智能预处理", "Smart Process": "智能预处理", "Smart pre-process including auto subject identification, caption subject swapping, and upscaling/facial restoration.": "智能预处理，包括自动主体识别、描述文本主体切换和放大/面部恢复", "Solid color": "纯色", "Some instructions": "一些操作说明", "Sort LoRA models by": "LoRA 模型的排序方式", "Sort by alphabetical order": "按首字母排序 (不推荐勾选)", "Source": "来源", "Source Checkpoint": "源模型(ckpt)", "Source URL where this model could be found": "发布该模型的网址", "Source directory": "源目录", "Split image overlap ratio": "分割图像重叠的比率", "Split image threshold": "图像分割阈值", "Split oversized images": "分割过大的图像", "Stable Diffusion checkpoint": "Stable Diffusion 模型(ckpt)", "Start steps": "起始迭代步数", "State": "运行状态", "Steps": "采样迭代步数(Steps)", "Stop at CLIP layers": "在 CLIP 模型的最后哪一层停下 (Clip skip)", "Stretch image": "拉伸图像", "Stretch pixels at border": "延伸边缘的像素", "StylePile": "风格加码", "Styles": "模板风格", "Subject Class": "主体类别(Subject Class)", "Subject Name": "主体(Subject)名", "Subject class to crop (leave blank to auto-detect)": "要裁剪的主体类别(Subject class)（留空以自动检测）", "Swap X/Y axes": "XY互换", "Swap X/Z axes": "XZ互换", "Swap Y/Z axes": "YZ互换", "System": "系统", "System Info": "系统信息", "System data": "系统信息", "TEnc Weight 1": "Text Encoder 权重 1", "TEnc Weight 2": "Text Encoder 权重 2", "TEnc Weight 3": "Text Encoder 权重 3", "TEnc Weight 4": "Text Encoder 权重 4", "TEnc Weight 5": "Text Encoder 权重 5", "Tag Autocomplete": "Tag自动填充", "Tag confidents": "标签置信度", "Tag filename": "词库文件", "Tagger": "Tag反推(Tagger)", "Tags": "标签(Tags)", "Target ControlNet number": "接收此图像的 ControlNet 编号", "Tertiary model (C)": "模型 C", "Text": "文本", "Text input": "文本输入", "Textbox": "文本框", "Textual Inversion": "嵌入式(T.I. Embedding)", "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，一个用于 2D 和 3D 动画的扩展脚本，支持关键帧序列、动态数学参数（甚至可用于提示词内）、动态蒙版、深度预测和变形", "Theme": "主题", "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.": "此扩展允许你将来自各种 booru 的图帖转换为提示词。它通过从对应的 API 中提取标签(tags)列表来实现。你可以自己复制粘贴你需要的图帖的链接，或者使用内置的搜索功能在不离开 webui 的情况下完成所有操作", "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": "这是在运行时重新实现的局部重绘图像调节蒙版强度(相对于重绘强度)的扩展。这对于局部重绘专用的模型(例如 sd-v1-5-inpainting.ckpt)很有用", "This is a mix from old style to new style. It is not in it's finished state": "此插件尚处于新旧交接之际，并非最终版本", "This is your models list.": "这是您的模型列表", "This text is used to rotate the feature space of the imgs embs": "此文本用于旋转图集 Embeddings 的特征空间", "This will produce one prompt for each colour in the wildcard.txt file.": "会为 colours.txt 中的每个颜色产生一条提示词", "This will produce the following prompts:": "会产生下列提示词", "This will produce three prompts, one for each color. The prompt tag is used to mark the text that will be used as the prompt. If no prompt tag is present then only one prompt is assumed": "会产生三条提示词，每个颜色各一条；\n prompt 标签用于标记作为提示词的文本；\n 如果没有 prompt 标签则默认为仅一条提示词", "This will randomly choose one of the three colors.": "会随机从三种颜色中选一个", "This won't break your system, if you find you can't update, try `git checkout webui.py` ~~`git fetch --all` `git reset --hard origin/master`~~": "操作不会破坏系统，如发现不能更新，请尝试 'git checkout webui.py' ~~'git fetch --all' 'git reset --hard origin/master'~~", "Threshold": "阈值", "Threshold A": "阈值A（此值根据预处理器选项不同发生变化，滑动条不可用时代表此预处理器无该项设置）", "Threshold B": "阈值B（此值根据预处理器选项不同发生变化，滑动条不可用时代表此预处理器无该项设置）", "Tile overlap": "图块重叠的像素(Tile overlap)", "Tile overlap, in pixels for ESRGAN upscalers. Low values = visible seam.": "ESRGAN 的图块重叠(Tile overlap)像素。较小时可见接缝", "Tile overlap, in pixels for SwinIR. Low values = visible seam.": "SwinIR 的图块重叠(Tile overlap)像素。较小时可见接缝", "Tile size for ESRGAN upscalers. 0 = no tiling.": "ESRGAN 的图块尺寸(Tile size)。0 为不分块(no tiling)", "Tile size for all SwinIR.": "适用所有 SwinIR 系算法的图块尺寸(Tile size)", "Tiled VAE": "分块 VAE", "Tiling": "平铺/分块 (Tiling)", "Time in ms to wait before triggering completion again (Requires restart)": "触发补全前的等待时间（单位:毫秒，需要保存设置并重启）", "To do this, open file, search for `prevent_thread_lock` add comma, paste in text, save.": "具体操作请打开文件并搜索 \"prevent_thread_lock\" ，在结尾添加逗号，粘贴并保存", "To see effects, you must use dropdown, select as sheet, click apply, click restart. More options will be available on restart": "想要查看效果，必须使用\"模板风格\"下拉菜单，选择并单击\"应用风格\"与\"应用设置\"， 重启后生效", "To see favicon take affect, you will need to add `favicon_path=\"favicon.svg\"` to webui.py": "想要 网页图标 设置生效，必须在 webui.py 中加入 'favicon_path=\"favicon.svg\"'", "Tokenize": "词元拆分(Tokenize)", "Tokenizer": "词元分析器(Tokenizer)", "Tokens": "词元(Tokens)", "Towards Controllable One-Shot Text-to-Image Generation via Contrastive Prompt-Tuning.": "通过对比调整提示词，实现可控的单发文本到图像生成", "Traditional Chinese localization": "正體中文本地化", "Train": "训练", "Train Embedding": "训练 Embedding", "Train Hypernetwork": "训练超网络", "Train an embedding or Hypernetwork; you must specify a directory with a set of 1:1 ratio images": "训练嵌入式(Embedding)或者超网络(Hypernetwork)；必须指定一个具有一组 1:1 比例图像的目录", "Train with DreamArtist": "使用梦作家训练", "Train with reconstruction": "训练时开启重建", "Training": "训练", "Training Picker": "训练图挑选器", "Training Wizard (Object/Style)": "训练配置器 (物件/风格)", "Training Wizard (Person)": "训练配置器 (人物)", "Training info": "训练信息", "Training parameters": "训练参数", "Translation First": "翻译在上面", "Translation display order": "翻译的显示顺序", "Translation file uses old 3-column translation format instead of the new 2-column one": "使用旧的三列翻译文件格式取代新的两列格式", "Translation filename": "词库翻译文件", "Transparent": "透明", "Travel mode": "变迁模式", "Travel steps between stages": "每个阶段变迁的迭代步数", "UI related": "UI界面相关", "UNet Weight 1": "UNet 权重 1", "UNet Weight 2": "UNet 权重 2", "UNet Weight 3": "UNet 权重 3", "UNet Weight 4": "UNet 权重 4", "UNet Weight 5": "UNet 权重 5", "URL": "网址", "URL for extension's git repository": "扩展的 git 仓库网址", "Unlink seed from prompt": "将随机种子与提示词解绑", "Unload all interrogate models": "卸载显存中所有反推模型(使用完毕后请务必卸载，反推模型将占用大量宝贵显存)", "Unload model after running": "完成后从显存中卸载模型 (推荐勾选)", "Unprompted": "非文本（代码化）提示词", "Upcast cross attention layer to float32": "将交叉关注层向上转型到float32", "Update": "更新", "Upload prompt inputs": "上传提示词输入文件", "Upscale": "图像放大", "Upscale Ratio": "放大比例", "Upscale and Resize": "放大并调整大小", "Upscale by": "放大倍率", "Upscaler": "放大算法", "Upscaler 2 visibility": "放大算法 2 (Upscaler 2) 可见度", "Upscaler for img2img": "图生图的放大算法", "Upscaling": "放大", "Use BLIP for caption": "使用 BLIP 生成说明文字(自然语言描述)", "Use Concepts List": "使用概念列表", "Use Lora in uc diffusion model": "在扩散模型降噪过程中对反向提示词也开启 LoRA（不建议开启）", "Use Lora in uc text model encoder": "在文字模型编码过程中对反向提示词也开启 LoRA（不建议开启）", "Use an empty output directory to save pictures normally instead of writing to the output directory.": "输出图像到一个空目录，而非设置里指定的输出目录", "Use cross attention optimizations while training": "训练时开启 cross attention 优化", "Use deepbooru for caption": "使用 deepbooru 生成说明文字(tags)", "Use different seed for each picture": "为每张图片使用不同随机种子", "Use dropdown for sampler selection instead of radio group": "使用下拉菜单取代单选列表", "Use dropout": "采用 dropout 防止过拟合", "Use mid-control on highres pass (second pass)": "进行高清修复时使用中间层控制(mid-control)", "Use old emphasis implementation. Can be useful to reproduce old seeds.": "使用旧的强调符实现。可用于复现旧随机种子", "Use old karras scheduler sigmas (0.1 to 10).": "使用旧的Karras调度器sigma值(0.1-10)", "Use original name for output filename during batch process in extras tab": "在附加功能选项卡中的批量处理过程中，使用原始名称作为输出文件名", "Use recursive with glob pattern": "全局递归查找", "Use recycle bin when deleting images": "将删除的图片放入回收站而非直接彻底删除（建议开启）", "Use same random seed for all lines": "每行输入都使用同一个随机种子", "Use spaces instead of underscore": "使用空格替代下划线 (推荐勾选)", "Use the same seed for all prompts in this batch": "对这批次中的所有提示词使用相同的种子", "Use upscaler name as filename suffix in the extras tab": "在附加功能选项卡中使用放大算法作为文件名后缀", "Use via API": "使用了 via API", "User interface": "用户界面", "Username": "用户名", "VAE Checkpoints to cache in RAM": "在内存中缓存的 VAE 数量", "VRAM Estimator": "显存(VRAM)评估", "VRAM usage polls per second during generation. Set to 0 to disable.": "生成图像时，每秒轮询显存(VRAM)使用情况的次数。设置为 0 以禁用", "Var. seed": "差异随机种子", "Var. strength": "差异强度", "Variation seed": "差异随机种子", "Variation strength": "差异强度", "Vector": "向量", "Version": "版本信息", "Vertical Mirroring": "垂直镜像", "Video": "视频", "Video FPS": "视频 FPS", "Video Input": "视频输入", "Video file format": "视频格式", "Video to extract frames from:": "要从中提取帧的视频：", "Visualize": "预览", "Visualize Cross-Attention": "Cross-Attention 可视化", "WD 1.4 Tagger": "WD 1.4 标签器", "Weight": "权重（Weight）", "Weight 1": "权重 1", "Weight 2": "权重 2", "Weight 3": "权重 3", "Weight 4": "权重 4", "Weight 5": "权重 5", "Weight values": "权重值", "Weight_values": "权重值(手动输入)", "Weighted sum": "加权和", "Weights": "权重", "When reading generation parameters from text into UI (from PNG info or pasted text), do not change the selected model/checkpoint.": "从 图片信息 或 粘贴文本 自动读取并填写生成参数时，不要更改选定的模型(ckpt)（建议开启）", "When using \"Save\" button, save images to a subdirectory": "使用“保存”按钮时，将图像保存到子目录", "When using 'Save' button, only save a single selected image": "使用“保存”按钮时，只保存一个选定的图像", "Whitelist": "白名单（启用tag自动填充）", "Whole picture": "全图", "Width": "宽度", "Width/height limit for the above option, in pixels": "上述选项的宽、高限制，单位：像素", "Wildcards": "通配符", "Wildcards can be used and the joiner can also be specified:": "可以用通配符，也可以指定拼接符", "With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising).": "在进行图生图的时候，确切地执行滑块指定的迭代步数（正常情况下更弱的重绘幅度需要更少的迭代步数）", "With img2img, fill image's transparent parts with this color.": "在图生图中使用以下颜色填充透明区域", "Write all generated prompts to a file": "将所有生成的提示词写入文件", "Write prompts to file": "将提示词写入文件", "X offset (A)": "X 偏移 (A)", "X offset (B)": "X 偏移 (B)", "X panning": "沿 X 轴滚动", "X type": "X轴类型", "X values": "X轴值", "X/Y/Z plot": "X/Y/Z 图表", "XavierNormal": "Xavier 正态", "XavierUniform": "Xavier 均匀", "Y offset (A)": "Y 偏移 (A)", "Y offset (B)": "Y 偏移 (B)", "Y panning": "沿 Y 轴滚动", "Y type": "Y轴类型", "Y values": "Y轴值", "Yes": "是", "You can try it by own, to dig more deeper into Abyss ...": "可自行探索，以窥深渊", "You may need to undo this for an update, if you have git issues and don't know how to deal with them": "如果更新时出现问题，请还原以上所有操作至初始状态", "Z type": "Z轴类型", "Z values": "Z轴值", "[ControlNet] Guidance Strength": "[ControlNet] 引导强度", "[ControlNet] Model": "[ControlNet] 模型", "[ControlNet] Pre Resolution": "[ControlNet] 预处理器 分辨率", "[ControlNet] Pre Threshold A": "[ControlNet] 预处理器 阈值A", "[ControlNet] Pre Threshold B": "[ControlNet] 预处理器 阈值B", "[ControlNet] Preprocessor": "[ControlNet] 预处理器", "[ControlNet] Resize Mode": "[ControlNet] 缩放模式", "[ControlNet] Weight": "[ControlNet] 权重", "[hash:]": "[hash:<算法>]", "[wiki]": "[wiki文档]", "a1111-sd-webui-locon": "LoCon 插件", "a1111-sd-webui-tagcomplete": "Tag自动补全", "a1111-stable-diffusion-webui-vram-estimator": "显存评估插件(VRAM Estimator)", "ads": "含广告", "aesthetic_score": "美学评分", "all": "全部", "animation": "动画", "append": "放后面", "auto": "自动", "auto-sd-paint-ext": "画图工具扩展", "base_alpha": "文本编码器比例", "booru2prompt": "booru转提示词", "border": "边框", "built-in": "内置", "by AUTOMATIC1111": "来自 AUTOMATIC1111", "canny": "Canny 边缘检测（Canny edge detection）", "cards": "卡牌视图（大预览图，竖图，占用页面空间非常大）", "cfg scale": "提示词相关性(CFG Scale)", "checkpoint": "模型", "comma": "逗号", "conditioning-highres-fix": "高清修复原图调节", "config": "配置", "constant": "常量(constant)", "constant_with_warmup": "含预热的常量(constant)", "controlnet m2m": "ControlNet-视频转绘", "convert": "转换", "copy": "复制", "copy to clipboard": "复制", "cosine": "余弦(cosine)", "cosine_with_restarts": "含重启的余弦(cosine)", "date": "日期", "ddetailer": "检测细致化", "default": "默认", "deforum-for-automatic1111-webui": "Deforum", "delete": "删除", "delete next": "删除后 N 张", "depth": "MiDaS 深度信息估算（MiDaS depth estimation）", "depth_leres": "LeReS 深度信息估算（LeReS depth estimation）", "depthmap2mask": "深度图转蒙版", "deterministic": "多次平均", "different": "差异", "directory.": "目录", "disabled": "禁用", "display_samples": "显示样本", "down": "下", "dropdown": "下拉菜单", "e.g. A portrait photo of embedding_name": "示例： A portrait photo of embedding_name", "editing": "编辑", "ema-only": "仅保留ema权重", "end at this step": "迭代止步于", "escape (\\) brackets in deepbooru (so they are used as literal brackets and not for emphasis)": "在 deepbooru 中使用转义括号（防止被误读为强调符）", "eta (noise multiplier) for DDIM": "DDIM 的 eta (噪声乘数) ", "eta (noise multiplier) for ancestral samplers": "ancestral 采样器的 eta (噪声乘数，建议值0.67)", "exif keyword": "搜索生成信息关键字（按回车开始检索）", "extension by": "扩展来自", "fake_scribble": "伪涂鸦（fake_scribble）", "filename": "文件名", "filename keyword": "搜索文件名关键字（按回车开始检索）", "fill": "填充", "filter out those tags from deepbooru output (separated by comma)": "从deepdanbooru的标签库中过滤掉以下标签，用逗号分隔", "fixed": "固定", "for detailed explanation.": "以了解详细说明", "frappe": "frappe/冰沙（深色-亮）", "has metadata": "有元数据", "hash": "哈希", "hed": "HED 边缘检测（soft HED edge detection, 保留细节）", "height": "高度", "here": "这里", "ignore": "无视", "img2img": "图生图", "img2img DDIM discretize": "图生图 DDIM 离散化", "img2img alternative test": "图生图的另一种测试", "img2img-grids": "宫格图(i2i)", "inpaint": "局部重绘", "inpaint sketch": "局部重绘(手涂蒙版)", "installed": "已安装", "internal order": "内部排序", "interpolation method": "插值算法", "is equivalent to": "等同于", "iter": "迭代器", "latent noise": "潜变量噪声", "latent nothing": "潜变量数值零", "latte": "latte/拿铁（浅色）", "left": "左", "linear": "线性(linear)", "load_switch": "载入开关", "localization": "本地化翻译", "macchiato": "macchiato/玛奇朵（深色）", "max_frames": "最大帧数", "minimum aesthetic_score": "美学评分下限", "missing metadata": "缺失元数据", "mlsd": "M-LSD 线条检测（M-LSD line detection）", "mocha": "mocha/摩卡（深色-暗）", "model": "模型", "model hash": "模型(ckpt)哈希值", "model_name": "模型名", "models": "模型", "multi-subject-render": "多主体渲染器", "multidiffusion-upscaler-for-automatic1111": "MultiDiffusion 放大器", "name": "名称", "negative": "负面", "newest first": "最新", "no": "否", "no-ema": "舍弃ema权重", "none": "无", "normal_map": "法线贴图（Normal map）", "novelai-2-local-prompt": "novelai 转 webui 括号", "oldest first": "发布时间", "once": "单次复用", "online": "线上", "openpose": "OpenPose 姿态检测（OpenPose pose detection）", "openpose-editor": "OpenPose 编辑器插件", "or": "或", "or to CTRL+SHIFT": "将 CTRL 绑定更改为 CTRL+SHIFT", "original": "原图", "others": "其他", "path name": "路径名", "pidinet": "PiDiNet 边缘检测（像素差分网络，配合HED模型）", "polynomial": "多项式(polynomial)", "posex": "3D OpenPose 编辑器插件(Posex)", "positive": "正面", "prepend": "放前面", "prompt travel": "提示词变迁", "prompting": "提示词编写", "quad": "二阶", "query": "查询", "random": "随机", "ranking": "评分", "ranking filter": "评级筛选", "replace": "取代", "replace preview": "用当前生成图片替换预览", "right": "右", "sampler": "采样方法(Sampler)", "save_samples": "储存样本", "save_settings": "储存设定", "schedule": "调度", "science": "科学", "scribble": "涂鸦（scribble）", "script": "脚本", "sd-dynamic-prompts": "动态提示词", "sd-extension-aesthetic-scorer": "美学评分插件", "sd-extension-system-info": "系统信息面板", "sd-web-ui-kitchen-theme": "Kitchen 主题", "sd-webui-additional-networks": "可选附加网络(LoRA插件)", "sd-webui-bilingual-localization": "双语对照翻译插件", "sd-webui-controlnet": "ControlNet 插件", "sd-webui-gelbooru-prompt": "Gelbooru标签自动摘录插件", "sd-webui-llul": "潜变量局部放大器", "sd-webui-model-converter": "模型格式转换插件", "sd-webui-multiple-hypernetworks": "复数超网络加载", "sd_dreambooth_extension": "dreambooth 扩展", "sd_smartprocess": "智能预处理", "sdweb-merge-block-weighted-gui": "分块加权模型合并插件(MBW)", "sdweb-merge-board": "合并面板", "seed": "随机种子(seed)", "seed travel": "种子变迁", "seed_schedule": "种子调度(seed_schedule)", "seed_travel": "种子变迁", "segmentation": "ADE20k 语义分割（Semantic segmentation）", "set_index": "设置索引", "shift-attention": "关注转移", "should be 2 or lower.": "应小于等于2", "sigma noise": "sigma 噪声", "sigma tmin": "最小(tmin) sigma", "similar": "相似", "size": "大小", "sketch": "绘图", "sort by": "排序方式", "space": "空格", "stable-diffusion-webui-aesthetic-gradients": "美术风格梯度", "stable-diffusion-webui-aesthetic-image-scorer": "美术风格评分", "stable-diffusion-webui-artists-to-study": "艺术家图库", "stable-diffusion-webui-auto-tls-https": "自动 tls-https", "stable-diffusion-webui-composable-lora": "可自组 LoRA", "stable-diffusion-webui-conditioning-highres-fix": "高清修复原图调节强度", "stable-diffusion-webui-dataset-tag-editor": "数据集标签编辑器", "stable-diffusion-webui-embedding-editor": "Embedding 编辑器", "stable-diffusion-webui-images-browser": "图库浏览器", "stable-diffusion-webui-inspiration": "灵感", "stable-diffusion-webui-localization-zh_CN": "简体中文语言包", "stable-diffusion-webui-pixelization": "像素化插件", "stable-diffusion-webui-prompt-travel": "提示词变迁", "stable-diffusion-webui-randomize": "随机化", "stable-diffusion-webui-tokenizer": "词元分析器(tokenizer)", "stable-diffusion-webui-two-shot": "潜变量成对(双人特写)", "stable-diffusion-webui-wd14-tagger": "Waifu Diffusion 1.4 标签器", "steps": "采样迭代步数(Steps)", "strength": "强度", "symbol:color-hex, symbol:color-hex, ...": "文字:颜色代码, 文字:颜色代码, ...", "tab": "选项卡", "threshold": "阈值", "thumbs": "拇指视图（小预览图，方图，真的只有大拇指甲盖大小，文字看不太清）", "title": "标题", "to": " 调整至 ", "to see which words are constructed using multiple sub-words, e.g. 'computer' doesn't exist in stable diffusion's CLIP dictionary and instead 'compu' and 'ter' are used (1 word but 2 embedding vectors). Currently buggy and needs a moment to process before pressing the button. If it doesn't work after a moment, try adding a random space to refresh it.": "查看哪些词是使用多个子词构成的，例如 Stable Diffusion 的 CLIP 字典中不存在 'computer'，而是使用 'compu' 以及 'ter'（1 个单词但使用 2 个 Embedding 向量）。目前这个扩展还有点问题，在按下按钮之前需要一点时间来处理。如果过了一会还是不行，试试随便加个空格刷新一下", "tokenizer": "词元分析器(tokenizer)", "training": "训练相关", "training-picker": "训练图挑选器", "turn_page_switch": "翻页开关", "txt2img": "文生图", "txt2img-grids": "宫格图(t2i)", "txt2img/img2img UI item order": "文生图/图生图界面UI顺序", "uniform": "均匀", "unknown": "未知", "unprompted": "非文本（代码化）提示词", "up": "上", "use spaces for tags in deepbooru": "deepbooru 反推结果中使用空格替代下划线（推荐开启）", "verbose console output": "将详细信息输出到控制台", "webui-tokenizer": "词元分析器(tokenizer)扩展", "width": "宽度", "wiki": "wiki文档", "will then become available.": "文件放在相应目录就能被识别", "zh_CN Localization": "简体中文语言包", "zh_TW Localization": "正體中文語言包", "{1-3$$artist1|artist2|artist3}": "{1-3$$艺术家1|艺术家2|艺术家3}", "{2$$__artist__|__artist__}": "{2$$__艺术家__|__艺术家_}", "{2$$__artist__}": "{2$$__艺术家__}", "{2$$artist1|artist2|artist3}": "{2$$艺术家1|艺术家2|艺术家3}", "{{1-$$and$$__adjective__}}": "{{1-3$$and$$__adjective__}}", "----not work----": "----以下内容无法被翻译，Bug----", "Allowed categories for random artists selection when using the Roll button": "使用抽选艺术家按钮时将会随机的艺术家类别", "Face restoration model": "面部修复模型", "Select which Real-ESRGAN models to show in the web UI. (Requires restart)": "选择要在 Web UI 中显示的 Real-ESRGAN 系列放大算法（需要保存设置并重启）", "Upscaler 1": "放大算法 1 (Upscaler 1)", "Upscaler 2": "放大算法 2 (Upscaler 2)", "----deprecated----": "----以下内容在webUI新版本已移除----", "\"Hug the middle\" during interpolation": "在插值的途中 \"主动去找中间点\"", "# Training Epochs": "训练多少期(Epochs)", "* change 'type' to clear/reload dropdowns.": "改变坐标轴类型可清空、刷新选项", "- Background": "--背景参考图--", "- Body": "--人体模型--", "- Camera": "--镜头--", "- Canvas Size": "--画布大小--", "- Joints and Limbs": "--关节和肢体--", "- Others": "--其他设置--", "/path/to/images/* or /path/to/images/**/*": "/图像/的/路径/* 或 /图像/的/路径/**/*", "2D and 3D settings": "2D 及 3D 设定", "3D Fov settings:": "3D 视野设置:", "3D settings": "3D 设定", "A merger of the two checkpoints will be generated in your": "合并后的模型(ckpt)会生成在你的", "A negative prompt to use when generating class images. Can be empty.": "生成类图像时使用的否定提示。 可以为空。", "A negative prompt to use when generating preview images.": "生成预览图像时使用的反向提示词", "A prompt for generating classification/regularization images. See the readme for more info.": "生成分类/规范化图像用的提示词。详细信息请参阅 readme", "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": "一个固定随机数生成器输出的值 - 以相同参数和随机种子生成的图像会得到相同的结果\n🎲 将随机种子设置为-1，则每次都会使用一个新的随机数\n♻️ 重用上一次使用的随机种子，如果想要固定输出结果就会很有用", "API Keys": "API 密钥", "Action on exiting caption": "对退出符的响应方式", "Adam Epsilon": "Adam Epsilon (替代 0 的常量，防止直接除以 0)", "Adam Weight Decay": "Adam 权重衰减(Weight Decay)", "Add a random artist to the prompt.": "随机添加一个艺术家到提示词中", "Add background image": "添加背景图片", "Adjusts the generated prompt. You will need to experiment with this setting.": "调整生成的提示词，使用时要尝试调整此设置", "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.": "按比例放大原分辨率，单独设定目标长宽时被忽略", "Advanced Seed Blending": "高阶种子混合", "All Reste": "全部重置", "Allows for random parameters during txt2img generation. This script is processed for all generations, regardless of the script selected, meaning this script will function with others as well, such as AUTOMATIC1111/stable-diffusion-webui-wildcards": "允许在文生图的生成期间使用随机的参数。无论选择哪种脚本，此脚本都会针对所有的生成进行处理，这意味着此脚本也可以与其他脚本一起使用，例如通配符脚本", "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.": "允许你在提示词中包含各种短代码。 你可以从文件中提取文本、设置自己的变量、通过条件函数处理文本等等 - 就像是增强版的通配符", "Animation settings": "动画设定", "Append Caption to File Name": "把描述文本接在文件名后面", "Append DeepDanbooru to Caption": "把 DeepDanbooru 的结果接在已有的描述文本后面", "Append commas": "附加逗号", "Apply horizontal Flip": "应用水平翻转", "Apply selected styles to current prompt": "将已选择的模板风格写入当前的提示词(prompt)", "Attempt to automatically set training parameters based on total VRAM. Still under development.": "尝试根据总显存(VRAM)自动设置训练参数。仍在开发中", "Auto-Adjust (WIP)": "自动调整 (施工中)", "Autocomplete options": "Tag自动补全选项", "Batch img2img": "批量图生图", "Batch settings": "批次设定", "Be sure to check the 'Write prompts to file' checkbox if you don't want to lose the generated prompts. Note, one image is still generated.": "不想丢失生成的提示词的话，需确保勾选 “将提示词写入文件”\n注意依然会生成一张图像", "Bulk process frames with chosen outfill method": "使用选定的填充方法批量处理截取的帧", "Bump seed (If > 0 do a Compare Paths but only one image. No video)": "自动递增种子 (大于 0 的时候会对比变迁轨迹，但不会生成视频而是只是一张图)", "CFG scale": "提示词相关性(CFG Scale)", "Calculate training parameters for a human subject. Enables prior preservation.": "计算训练人物主体需要的参数。并启用先验存留(prior preservation)", "Calculate training parameters for a non-human subject. Disables prior preservation.": "计算训练非人物主体需要的参数。并禁用先验存留(prior preservation)", "Cancel generate forever": "停止无限生成", "Cancel training.": "取消训练", "Canny high threshold": "强边缘判断阈值（Canny high threshold）", "Canny low threshold": "弱边缘判断阈值（Canny low threshold）", "Center Crop": "中心裁切", "Check console log window for detail, after clicking Scan button": "开始扫描后，请打开控制台以获得详细信息和日志，如遇报错，请先访问C站网页确认C站是否崩溃，C站恢复访问后，可再次开始扫描，扫描继承之前的进度，其他详细信息见插件GitHub页面", "Check progress": "查看进度", "Check progress (first)": "(首次)查看进度", "Check this if you want to generate random prompts, even if your seed is fixed": "勾选此选项以在固定随机种子的情况下依然生成随机提示词", "Checkpoint Dropdown": "模型(ckpt)列表", "Civitai Helper": "C站助手", "Civitai Helper's extension tab": "C站助手插件选项卡", "Class Token + Description": "类的词元(Token) + 描述", "Class prompt": "类(Class)提示词", "Class token(s) to swap, can be comma-separated": "要互换的类的词元(Token)，可以是以英文逗号分割的", "Classification dataset directory (optional).": "分类(Classification)数据集目录（可选）", "Classifier Free Guidance Scale - how strongly the image should conform to prompt - lower values produce more creative results": "无分类器指导信息影响尺度(Classifier Free Guidance Scale) - 图像应在多大程度上服从提示词 - 较低的值会产生更有创意的结果", "Clear prompt": "清空提示词(prompt)", "Coherence:": "相干性:", "Collect": "收藏(保存)", "Comma separated list": "以逗号分割的列表", "Comma separated list. Specify ckpt OR ckpt:word": "以逗号分割的列表。用以指定 ckpt 或 ckpt:字词", "Concepts List (Overrides instance/class settings below)": "概念列表（将取代下面实例/类这两项设置）", "Connection errored out.": "连接出错", "Controls the maximum length in tokens of the generated prompt.": "按 token 数控制提示词生成的最大长度", "Copy Metdata": "开始复制元数据", "Copy image to: ": "将图片发送到:", "Copy to clipboard": "复制到剪贴板", "Copy to directory": "将图片复制到目标路径", "Copy to favorites": "复制到收藏夹", "Create a grid where images will have different parameters. Use inputs below to specify which parameters will be shared by columns and rows": "创建一个网格，图像将有不同的参数。使用下面的输入来指定哪些参数将由列和行共享", "Create aesthetic images embedding": "创建美术风格图集 Embedding", "Create an embedding from one or few pictures and use it to apply their style to generated images.": "用一张或多张图像创建一个 Embedding，并用它将图集的风格转移到要生成的图像上", "Create the danged model already.": "创建一个本就很牛的模型", "Date to": "日期至", "Deforum-webui (use tab extension instead!)": "Deforum-webui (请使用选项卡上的扩展版本)", "Del": "删除", "Denoising Diffusion Implicit Models - best at inpainting": "Denoising Diffusion Implicit models - 最擅长局部重绘", "Depth Library": "深度图编辑器", "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.": "决定算法对图像内容的影响程度。设置 0 时，什么都不会改变，而在 1 时，你将获得不相关的图像。\n值低于 1.0 时，处理的迭代步数将少于“采样迭代步数”滑块指定的步数", "Disable dynamic prompts by unchecking this box.": "取消勾选来禁用动态提示词", "Disable image generation. Useful if you only want to generate text prompts.": "禁用图像生成。如果你只想生成文本提示词的话", "Disable negative prompt": "禁用反向提示词", "Disabled when launched with --hide-ui-dir-config.": "启动 --hide-ui-dir-config 时禁用", "Dismiss": "屏蔽", "Do not do anything special": "什么都不做", "Don't Cache Latents": "不要缓存潜变量", "Don't cache latents": "不要缓存潜变量", "Don't checkpoint the gradients, Duh. Set to False to slightly increase speed at the cost of a bit of VRAM.": "保存权重进度时不要保存梯度，啊不废话。设置为 False 以消耗一点显存(VRAM)为代价略微提高速度", "Download image": "下载图片", "Draw Legends": "输出坐标轴名字", "Draw a mask over an image, and the script will regenerate the masked area with content according to prompt": "在图像上画一个蒙版，脚本会根据提示重新生成蒙版区域的内容", "Draw mask": "绘制蒙版", "Dropout tags when create texts": "创建文本时随机丢弃一些 tags", "Elliptic Limbs": "椭圆形肢体", "Embedding to Shareable PNG": "将 Embedding 转换为可分享的 PNG 图片文件", "Embedding token": "Embedding 的词元(Token) / 关键词", "Enable Autocomplete": "启用Tag自动补全", "Enable Randomize extension": "启用随机化扩展", "Enable extras": "打开 ▼", "Enable scribble mode if your image has white background.": "使用白色背景图片时请启用涂鸦模式", "Enable this to save VRAM.": "启用此项以节省显存(VRAM)", "Enables using AND keyword(composable diffusion) to limit LoRAs to subprompts. Related to Latent Couple extension.": "启用使用 AND 关键字（composable diffusion）将 LoRA 的作用范围限制在一部分提示词上。 与潜变量成对扩展相关。", "Enabling this will provide better results and editability, but cost more VRAM.": "启用此功能将提供更好的结果和可编辑性，但会消耗更多显存(VRAM)", "Euler Ancestral - very creative, each can get a completely different picture depending on step count, setting steps to higher than 30-40 does not help": "Euler Ancestral - 非常有创意，可以根据迭代步数获得完全不同的图像，将迭代步数设置为高于 30-40 不会有正面作用", "Existing Prompt Contents": "现存的提示词内容", "Extra file in alias only format": "附加词库文件使用仅别称格式", "Extra filename (do not use e621.csv here!)": "附加词库文件（不要使用e621.csv）", "Extra path to scan for LoRA models (e.g. training output directory)": "检索 LoRA 模型的附加目录", "File with inputs": "含输入内容的文件", "Filter NSFW content": "过滤成人内容(NSFW)（不建议开启）", "Firstpass height": "首次高度", "Firstpass width": "首次宽度", "Fixed Roll": "滚转修复", "Flatfile": "纯文字文件", "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(SD upscale)时，图块(Tiles)之间应该有多少像素重叠。图块(Tiles)之间需要重叠才可以让它们在合并回一张图像时，没有清晰可见的接缝", "Generate a checkpoint at the current training level.": "生成当前训练级别的模型权重进度(ckpt)", "Generate a checkpoint at the current training lvel.": "生成当前训练级别的模型权重进度(ckpt)", "Generate a preview image every N steps, 0 to disable": "每隔 N 步生成一次预览图，设置为 0 以禁用", "Generate all possible prompts up to a maximum of Batch count * Batch size)": "生成不超过（生成批次 * 每批数量）的所有可能的提示词", "Generate forever": "无限生成", "Generate preview images every N steps.": "每 N 步生成一次预览图像", "Generation settings:": "一般设置:", "Get List": "获取列表", "Get comma-separated list of models (for XY Grid)": "生成逗号分隔的模型列表(方便X/Y表使用)", "Grad Accumulation Steps": "梯度累加步数(Grad Accumulation Steps)", "Guess what - this will be incredibly slow, but it will work for < 8GB GPUs.": "你猜怎么着 - 这将非常地慢我的老伙计，但它适用于 < 8GB 显存(VRAM)的 GPU", "H": "高", "HED Resolution": "HED 分辨率（HED Resolution）", "Half": "一半", "Hands": "手部", "Highres. fix": "高清修复", "Hough Resolution": "霍夫分辨率（Hough Resolution）", "Hough distance threshold (MLSD)": "霍夫距离阈值（Hough distance threshold）（MLSD）", "Hough value threshold (MLSD)": "霍夫值阈值（Hough value threshold）（MLSD）", "How many batches of images to create": "创建多少批次的图像", "How many classifier/regularization images to generate at once.": "一次生成多少分类/规范化图像。", "How many image to create in a single batch": "每批创建多少图像", "How many images to process at once per training step?": "每步训练要处理多少张图像？", "How many samples to generate per subject.": "每个主体生成多少样本", "How many times to improve the generated image iteratively; higher values take longer; very low values can produce bad results": "迭代改进生成的图像多少次；更高的值需要更长的时间；非常低的值会产生不好的结果", "How many times to repeat processing an image and using it as input for the next iteration": "重复处理图像并用作下次迭代输入的次数", "How much to blur the mask before processing, in pixels.": "处理前要对蒙版进行多强的模糊，以像素为单位", "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).": "想要产生多强烈的变化。设为 0 时，将没有效果。设为 1 时，你将获得完全产自差异随机种子的图像（此功能对带有 a 后缀的采样器无效）", "Hypernet str.": "超网络(Hypernetwork) 强度", "Hypernetwork strength": "超网络(Hypernetwork) 强度", "If PNG image is larger than 4MB or any dimension is larger than 4000, downscale and save copy as JPG": "如果 PNG 图像大于 4MB 或宽高之一大于 4000，则缩小并保存副本为 JPG 图片", "If an image is too large, crop it from the center.": "如果图像太大，裁掉边缘", "If the groups wont drop down click": "如果无法下拉组，点击", "If this option is enabled, watermark will not be added to created images. Warning: if you do not add watermark, you may be behaving in an unethical manner.": "如果启用此选项，水印将不会添加到生成出来的图像中。警告：如果你不添加水印，你的行为可能是不符合专业操守的", "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.": "如果这个值不为零，它将被添加到随机种子中，并在使用带有 Eta 的采样器时用于初始化随机噪声。你可以使用它来产生更多的图像变化，或者你可以使用它来模仿其他软件生成的图像，如果你知道你在做什么", "Ignore the negative prompt. Magic Prompt and I'm feeling lucky generate negative prompts by default, check this to disable that functionality.": "忽略反向提示词\n魔法提示词和手气不错默认生成反向提示词，勾选此选项以禁用这种功能", "Images Browser": "图库浏览器", "Import Model from Huggingface Hub": "自 Huggingface Hub 载入模型", "Import a model from Huggingface.co instead of using a local checkpoint.": "从 Huggingface.co 导入模型而非使用本地的模型(ckpt)", "Import settings from file": "从文件导入设置", "In loopback mode, on each loop the denoising strength is multiplied by this value. <1 means decreasing variety so your sequence will converge on a fixed picture. >1 means increasing variety so your sequence will become more and more chaotic.": "在回送模式下，在每个循环中，重绘幅度都会乘以该值。<1 表示减少多样性，因此你的这一组图将集中在固定的图像上。>1 意味着增加多样性，因此你的这一组图将变得越来越混乱", "Include Separate Images": "生成图表时，保留每一张图像", "Info and links": "资讯和链接", "Insert selected styles into prompt fields": "在提示词中插入选定的模版风格", "Installing...": "安装中…", "Instance Token + Class Token + Description": "实例的词元 + 类的词元 + 描述", "Instance Token + Description": "实例的词元(Token) + 描述", "Instance prompt": "实例(Instance)提示词", "Instance prompt(Optional)": "实例(Instance)提示词 (可选)", "Instance token to swap": "要互换的实例的词元(Token)", "Instead of generating random prompts from a template, combinatorial generation produces every possible prompt from the given string.\nThe prompt 'I {love|hate} {New York|Chicago} in {June|July|August}' will produce 12 variants in total.\nDon't forget to increase the 'Batch count'/'Batch size' value accordingly.\n\t\nThe value of the 'Seed' field is only used for the first image. To change this, look for 'Fixed seed' in the 'Advanced options' section.": "组合生成从给定的字符串中生成所有可能的提示词，而非随机其中一个\n'I {love|hate} {New York|Chicago} in {June|July|August}' 总共会生成 12 句提示词变体\n别忘记相应地增加 “批次（Batch count）” 和 “批量（Batch size）” 值\n\t\n“随机种子” 的值只用于第一图像，可在 “高级选项” 中的 “固定随机种子” 修改此行为", "Interrogate: use artists from artists.csv": "反推：使用 artists.csv 中的艺术家", "Jinja2 templates are an expressive alternative to the standard syntax. See the Help section below for instructions.": "Jinja2 模板是标准语法富有表现力的一种替代品，相关说明参见下方帮助栏", "Join the official Deforum Discord discord.gg/deforum to share your creations and suggestions": "加入官方 Deforum 的 Discord discord.gg/deforum 分享您的创作和建议", "Laters": "层", "LeReS Resolution": "LeReS 分辨率（LeReS Resolution）", "Learning rate": "学习率", "Leave blank to use instance prompt.": "留空以使用实例提示词", "Lets you edit captions in training datasets.": "让你可以在这里编辑训练数据集的描述文本", "Limb Width": "肢体粗细", "List of active tabs (separated by commas). Available options are txt2img, img2img, txt2img-grids, img2img-grids, Extras, Favorites, Others. Custom folders are also supported by specifying their path.": "选项卡列表，以逗号分隔（可用选项有 txt2img、img2img、txt2img-grids、img2img-grids、Extras、Favorites、Others， 支持写入指定路径自定义文件夹）", "List of setting names, separated by commas, for settings that should go to the quick access bar at the top, rather than the usual setting tab. See modules/shared.py for setting names. Requires restarting to apply.": "设置项名称的列表，以英文逗号分隔，该设置会移动到顶部的快速访问栏，而不是默认的设置选项卡。有关设置名称，请参见 modules/shared.py。需要保存设置并重启才能应用", "Load Params": "载入参数", "Load model paramters from the last training session.": "从上次训练中加载模型参数", "Loads weights from checkpoint before making images. You can either use hash or a part of filename (as seen in settings) for checkpoint name. Recommended to use with Y axis for less switching.": "在生成图像之前从模型(ckpt)中加载权重。你可以使用哈希值或文件名的一部分（如设置中所示）作为模型(ckpt)名称。建议用在Y轴上以减少过程中模型的切换", "Loss for cond match (grad mode)": "匹配文字调节(cond)损失 (梯度模式)", "Loss for latent match (grad mode)": "匹配潜变量(latent)损失 (梯度模式)", "Low VRAM (8GB or below)": "低显存（8GB以下）模式（需配合启动参数\"--lowvram\"）", "Low fps": "低帧率模式", "Made by deforum.github.io, port for AUTOMATIC1111's webui maintained by kabachuha": "由 deforum.github.io 制作，AUTOMATIC1111 的 webui 移植版本由 kabachuha 维护", "Magic Prompt adds interesting modifiers to your prompt for a little bit of extra spice.\nThe first time you use it, the MagicPrompt model is downloaded so be patient.\nIf you're running low on VRAM, you might get a CUDA error.": "魔法提示词在提示词中加入有趣的修饰，额外增添趣味\n首次使用时会下载 MagicPrompt 模型，请耐心等待\n在低显存情况下可能会导致 CUDA 报错", "Make Zip when Save?": "保存时创建zip压缩文件?", "Make an attempt to produce a picture similar to what would have been produced with same seed at specified resolution": "尝试生成图像，与同一随机种子在指定分辨率下生成的图像相似", "Mask source": "蒙版来源", "Masking mode": "蒙版模式", "Math keyframing explanation docs.google.com/document/d/1pfW1PwbDIuW0cv-dnuyYj1UzPqe23BlSLTJsqazffXM/edit?usp=sharing": "数学关键帧(Math keyframing)解释 docs.google.com/document/d/1pfW1PwbDIuW0cv-dnuyYj1UzPqe23BlSLTJsqazffXM/edit?usp=sharing", "Max Caption length (0=unlimited)": "最大描述长度 (0 为无限制)", "Max Grad Norms": "最大梯度范数(Max Grad Norms)", "Max Gradient norms.": "最大梯度范数(Max Gradient norms)", "Max Token Length (Requires Pad Tokens for > 75)": "最大词元(Token)长度 (词元(Token) > 75 时会进行留空)", "Memory Optimised SHA256": "SHA256哈希值 计算时优化内存用量", "Midas Resolution": "MiDaS 分辨率（MiDaS Resolution）", "Model directory": "模型目录", "Model list": "模型列表", "Model list will be output here": "模型列表将会在此处输出", "Motion parameters:": "运动参数：", "Move VAE and CLIP to RAM when training hypernetwork. Saves VRAM.": "训练超网络(Hypernetwork)时将 VAE 和 CLIP 从显存(VRAM)转移至内存(RAM)，节省显存(VRAM)", "NOTE: If the 'Generate' button doesn't work, go in Settings and click 'Restart Gradio and Refresh...'.": "注意：如果“生成”按钮不起作用，请进入“设置”并单击“重启 Gradio 及刷新...”。", "Network module (used throughout this tab)": "附加网络类型(仅此页面使用)", "New preset name ": "新预设的名称", "Next batch": "下一批", "No interpolation will be used. Requires one model; A. Allows for format conversion and VAE baking.": "不添加差值，仅填入模型A即可，主要用于压缩、格式转换及整合 VAE (生成自带 VAE 颜色校正的模型)", "Normal Resolution": "法线贴图分辨率（Normal Resolution）", "Normal background threshold": "背景识别阈值（Normal background threshold）", "Number of grids in each row": "每行显示多少格", "Number of pictures displayed on each page": "每页显示的图像数量", "Number of samples to generate": "要生成的样本数", "Number of sampling steps for upscaled picture. If 0, uses same as for original.": "设置进行高清修复时的采样迭代次数，0表示沿用原始采样迭代次数", "Number of sampling steps to use when generating preview images.": "生成预览图像时要使用的采样迭代步数", "Number of steps for the warmup in the lr scheduler.": "学习率调度器中的预热步数", "Only applies to inpainting models. Determines how strongly to mask off the original image for inpainting and img2img. 1.0 means fully masked, which is the default behaviour. 0.0 means a fully unmasked conditioning. Lower values will help preserve the overall composition of the image, but will struggle with large changes.": "仅适用于局部重绘专用的模型（模型后缀为 inpainting.ckpt 的模型）。决定了蒙版在局部重绘以及图生图中屏蔽原图内容的强度。 1.0 表示完全屏蔽原图，这是默认行为。0.0 表示完全不屏蔽让原图进行图像调节。较低的值将有助于保持原图的整体构图，但很难遇到较大的变化", "Open drawing canvas!": "创建绘图画布（使用手绘草稿而非上传的图片）", "Open images output directory": "打开图像输出目录", "Open output directory": "打开输出目录", "Optional, uses selected model's directory if blank": "可选，若留空则使用默认目录", "Original Deforum Github repo github.com/deforum/stable-diffusion": "原始 Deforum Github 仓库 github.com/deforum/stable-diffusion", "Output type": "输出类型", "Pad the input images token lenght to this amount. You probably want to do this.": "将输入图像的词元长度垫齐到此数量。你可能会想要这样做", "Pages: ": "页码：", "Path relative to the webui folder": "webui文件夹的相对路径", "Path to JSON file with concepts to train, or a JSON string.": "包含要训练的概念的 JSON 文件的路径，或 JSON 字符串", "Path to directory with classification images": "分类图像的目录路径", "Pick every n-th frame": "每 n 帧挑选 1 帧", "Pick frames every n-th": "每 n 帧挑选 1 帧", "Prespective flip — Low VRAM pseudo-3D mode:": "透视翻转 — 低显存(VRAM)伪3D模式:", "Prev batch": "上一批", "Preview image negative prompt": "预览图反向提示词", "Preview image prompt": "预览图提示词", "Process an image, use it as an input, repeat.": "处理一张图像，将其作为输入，并重复", "Produce an image that can be tiled.": "生成可用于平铺(tiled)的图像", "Provide Simplified Chinese localization for the WebUI": "提供简体中文本地化翻译", "Randomize CFG Scale": "随机化 提示词相关性(CFG Scale)", "Randomize CLIP skip": "随机化 在 CLIP 模型的最后哪一层停下 (Clip skip)", "Randomize Height": "随机化 高度", "Randomize Highres. Denoising Strength": "随机化 高清修复的重绘幅度(Denoising)", "Randomize Highres. Height": "随机化 高清修复的第一遍的高度", "Randomize Highres. Width": "随机化 高清修复的第一遍的宽度", "Randomize Highres. percentage": "随机化 启用高清修复的几率", "Randomize Sampler": "随机化 采样器", "Randomize Steps": "随机化 采样迭代步数", "Randomize Width": "随机化 宽度", "Randomly decide to flip images horizontally.": "随机决定要不要水平翻转图像", "Randomly selects a keyword from the prompt and adds emphasis to it. Try this with Fixed Seed enabled.": "随机强调提示词中的一个关键词，尝试前要启用固定随机种子", "Re-run your combinatorial batch this many times with a different seed each time.\nThe maximum number of outputs = Combinatorial batches * Batch size * Batch count.\nTo specify the maximum number of prompt combinations use 'Batch count'/'Batch size' options.": "重复做多批次组合生成，每次用不同的随机种子\n最大输出数为 组合批次 * 批量（Batch size） * 批次（Batch count）\n在 “批次” 和 “批量” 处指定提示词组合的最大数量", "Read generation parameters from prompt or last generation if prompt is empty into user interface.": "从提示词(prompt)中自动提取生成参数，若当前提示词为空则从上次的生成信息中读取（允许将包含正面、负面、采样器、步数、模型等信息的整段生成信息全部粘贴到提示词区域，点击后可自动将对应信息填入并删除多余内容）", "Reconstruct prompt from existing image and put it into the prompt field.": "从现有的图像中重构出提示词，并将其放入提示词的输入文本框", "Record accessable images directories": "在 \"其他\" 标签下记录访问过的目录", "Refresh Civitai Helper": "刷新C站助手", "Refresh page": "刷新页面", "Regular expression; if weights's name matches it, the weights is not written to the resulting checkpoint. Use ^model_ema to discard EMA weights.": "与写入内容名称匹配的权重信息将不会写入输出的模型（可以通过写入\"^model_ema\"以舍弃模型中的EMA信息）", "Reloading...": "正在重新加载...", "Remove Background %": "背景排除（%）", "Remove Near %": "近景排除（%）", "Remove background image": "移除背景图片", "Remove selected": "移除已选中的", "Replace order (replace mode)": "取代顺序 (取代模式)", "Reset Camera": "重置镜头", "Reset Pose": "重置动作", "Resize image to target resolution. Unless height and width match, you will get incorrect aspect ratio.": "将图像大小调整为目标分辨率。除非高度和宽度匹配，否则你将获得不正确的纵横比", "Resize the image so that entirety of image is inside target resolution. Fill empty space with image's colors.": "调整图像大小，使整个图像在目标分辨率内。用图像的颜色填充空白区域", "Resize the image so that entirety of target resolution is filled with the image. Crop parts that stick out.": "调整图像大小，使整个目标分辨率都被图像填充。裁剪多出来的部分", "Resizes image to this height. If 0, height is inferred from either of two nearby sliders.": "将高度调整到此值，0表示根据目标宽度或放大倍率自适应调整", "Resizes image to this width. If 0, width is inferred from either of two nearby sliders.": "将宽度调整到此值，0表示根据目标高度或放大倍率自适应调整", "Restart Gradio and Refresh components (Custom Scripts, ui.py, js and css only)": "重启 Gradio 及刷新组件（仅限自定义脚本、ui.py、js 和 css）", "Restore Checkpoint after process": "完成后恢复开始前选择的模型(ckpt)", "Restore low quality faces using GFPGAN neural network": "使用 GFPGAN 神经网络修复低质量面部", "Result = A": "获得与A完全相同的模型", "Result = A * (1 - M) + B * M": "结果 = A * (1 - M) + B * M", "Result = A + (B - C) * M": "结果 = A + (B - C) * M", "Reuse seed from last generation, mostly useful if it was randomed": "重用上一次使用的随机种子，如果想要固定结果就会很有用", "Roll three": "抽三位出来", "Run Python code. Advanced user only. Must run program with --allow-code for this to work": "运行 Python 代码。仅限老手使用。必须以 --allow-code 来开启程序，才能使其运行", "Run settings": "运行设置", "SKip NSFW Preview images": "跳过成人内容预览图", "Sample Image Negative Prompt": "样本图像的反向提示词", "Sample extension. Allows you to use __name__ syntax in your prompt to get a random line from a file named name.txt in the wildcards directory. Also see Dynamic Prompts for similar functionality.": "扩展示例。允许你在提示词中使用 __name__ 语法时，会从 wildcards 目录中一个名为 name.txt 的文件中随机获取一行作为输入。动态提示词扩展也有类似功能", "Sample guidance scale": "样本的指导尺度(guidance scale) - 类似基准 CFG scale 的概念", "Sample steps": "样本迭代步数", "Sampling settings": "采样设置", "Save Caption to .txt File": "储存描述文本为 .txt 文件", "Save Checkpoint Frequency": "保存模型权重进度(ckpt)的频率", "Save PNGinfo to grid": "将生成参数写入宫格图（可用图片信息直接识别宫格图）", "Save Pose": "保存动作", "Save Preview(s) Frequency": "保存预览的频率", "Save a checkpoint every N steps, 0 to disable": "每隔 N 步保存一次模型权重进度(ckpt)，设置为 0 以禁用", "Save a checkpoint every N steps. ": "每 N 步保存一次模型权重进度(ckpt)", "Save current prompts as a style. If you add the token {prompt} to the text, the style use that as placeholder for your prompt when you use the style in the future.": "将当前的提示词保存为模版风格。如果你在文本中添加{prompt}标记，那么将来你使用该模版风格时，你现有的提示词会替换模版风格中的{prompt}", "Save ranking in image's pnginfo": "将分级保存到 PNG 文件信息", "Save style": "将当前的提示词(prompt)保存为模板风格", "Saves Optimizer state as separate *.optim file. Training can be resumed with HN itself and matching optim file.": "将优化器状态保存为单独的 *.optim 文件。可以使用超网络(HN)本身和匹配的 optim 文件继续中断了的训练。", "Scale Learning Rate": "缩放学习率", "Scale the learning rate by the number of GPUs, gradient accumulation steps, and batch size.": "通过 GPU 数量、梯度累加步数(gradient accumulation steps)和每批数量(batch size)来缩放学习率", "Scan model": "扫描模型（通过 SHA256哈希值 为所有模型匹配C站信息，不会重复扫描，不会覆盖原有预览图）", "Schedule to use for official training stuff.": "选择要用于训练官方东西的调度器", "Scribble Mode": "涂鸦模式（反色，强制预处理器重新识别）", "Scribble Mode (Reverse color)": "涂鸦模式（反色，强制预处理器重新识别）", "Seed of a different picture to be mixed into the generation.": "将要参与生成的另一张图的随机种子", "Seeds": "随机种子", "Select Layer weights initialization. relu-like - Kaiming, sigmoid-like - Xavier is recommended": "选择初始化层权重的方案，类relu - Kaiming，类sigmoid - Xavier 都是比较推荐的选项", "Select activation function of hypernetwork": "选择超网络的激活函数", "Select this if you want to use the same seed for every generated image.\nThis is useful if you want to test prompt variations while using the same seed.\nIf there are no wildcards then all the images will be identical.": "勾选此选项以对每张生成的图像用同样的随机种子\n这在想用同样的随机种子测试提示词变化时会有用\n没有通配符则所有图像会相同", "Send to ControlNet": "发送到 ControlNet", "Separate a list of words with commas, and the first word will be used as a keyword: script will search for this word in the prompt, and replace it with others": "以逗号分割的单词列表，第一个单词将被用作关键词：脚本将在提示词中搜索这个单词，并用其他单词替换它", "Separate a list of words with commas, and the script will make a variation of prompt with those words for their every possible order": "以逗号分割的单词列表，脚本会排列出这些单词的所有排列方式，并加入提示词各生成一次", "Separate prompts into parts using vertical pipe character (|) and the script will create a picture for every combination of them (except for the first part, which will be present in all combinations)": "用竖线分隔符(|)将提示词分成若干部分，脚本将为它们每个可能的组合创建一个图像（始终保留提示的第一部分，使用相同的种子）", "Separate values for X axis using commas.": "使用逗号分隔 X 轴的值", "Separate values for Y axis using commas.": "使用逗号分隔 Y 轴的值", "Set": "设为", "Set seed to -1, which will cause a new random number to be used every time": "将随机种子设置为 -1，则每次都会使用一个新的随机数", "Set the maximum number of words to be used in the [prompt_words] option; ATTENTION: If the words are too long, they may exceed the maximum length of the file path that the system can handle": "设置在[prompt_words]选项中要使用的最大字数；注意：如果字数太长，可能会超过系统可处理的文件路径的最大长度", "Set this or number of steps to train for, not both.": "设置这个或者'训练迭代步数'，两者不能同时用", "Set this to 2 to increase speed?": "将此设置为 2 以提高速度？", "Shapes": "图形", "Show Ad": "显示广告", "Show Textbox": "显示文本框", "Show console debug": "在控制台显示调试信息", "Show extra networks": "显示附加网络面板", "Show image creation progress every N sampling steps. Set 0 to disable.": "每 N 个采样迭代步数显示图像生成进度。设置 0 禁用", "Show image creation progress every N sampling steps. Set to 0 to disable. Set to -1 to show after completion of batch.": "每 N 个采样迭代步数显示图像生成进度。设置 0 禁用，设置 -1 使预览在批量生成完成之后再显示", "Show only favorite Axis Option": "仅显示常用坐标轴类型", "Show verbose debug info at console": "在控制台中输出详尽的调试信息", "Shuffleing tags by ',' when create texts.": "创建文本时打乱以 ',' 分割的 tags", "Simplified Chinese localization": "简体中文本地化", "Sort models by": "排序方式", "Source embedding to convert": "用于转换的源 Embedding", "Split over-sized images": "分割过大的图像", "Split oversized images into two": "将过大的图像分为两份", "Stable-Diffusion-Webui-Civitai-Helper": "C站助手(Civitai Helper)", "Start drawing": "开始绘制", "Start from Axis": "优先遍历的坐标轴", "Start training.": "开始训练", "Step count": "步数 (梯度模式)", "Step count (grad mode)": "步数 (梯度模式)", "Step method": "步进方法 (梯度模式)", "Step method (grad mode)": "步进方法 (梯度模式)", "Step size": "步幅 (梯度模式)", "Step size (grad mode)": "步幅 (梯度模式)", "Steps between prompts": "每个提示词之间的迭代步伐", "Stop At last layers of CLIP model": "在 CLIP 模型的最后哪一层停下 (Clip skip)", "Stop processing current image and continue processing.": "停止处理当前图像，并继续处理下一个", "Stop processing images and return any results accumulated so far.": "停止处理图像，并返回迄今为止累积的任何结果", "Style 1": "模版风格 1", "Style 2": "模版风格 2", "Style to apply; styles have components for both positive and negative prompts and apply to both": "要使用的模版风格； 模版风格包含正向和反向提示词，并应用于两者\n🎨 随机添加一个艺术家到提示词中\n ↙️ 从提示词中读取生成参数，如果提示词为空，则读取上一次的生成参数到用户界面\n💾 将当前的提示词保存为模版风格(保存在styles.csv)\n📋 将所选模板风格，应用于当前提示词\n如果你在文本中添加{prompt}标记，并保存为模版风格\n那么将来你使用该模版风格时，你现有的提示词会替换模版风格中的{prompt}", "Subject Name to replace class with in cations": "描述文本中要替换类(class)的主体名(subject)", "Swap axes": "交换XY轴", "SwinIR_4x": "SwinIR 4x", "The Classifier-Free Guidance Scale to use for classifier/regularization images.": "用于分类/规范化图像的提示词相关性(CFG Scale - 无分类器指导信息影响尺度(Classifier-Free Guidance Scale))", "The URL to the model on huggingface. Should be in the format of 'developer/model_name'.": "huggingface 模型的 URL。应为 'developer/model_name' 的格式", "The beta1 parameter for the Adam optimizer.": "Adam 优化器的 beta1 参数", "The beta2 parameter for the Adam optimizer.": "Adam 优化器的 beta2 参数", "The difference between the last two models will be added to the first. Requires three models; A, B and C. The result is calculated as A + (B - C) * M": "将模型B与C的差值添加到模型A，需要同时填入模型A、B和C，公式：A + (B-C)*M，倍率(M)为添加的差值比例", "The directory containing classification/regularization images.": "包含分类/规范化图像的目录", "The directory containing training images.": "包含训练图像的目录", "The generated file is a slugified version of the prompt and can be found in the same directory as the generated images.\nE.g. in ./outputs/txt2img-images/.": "生成的文件包含处理过的提示词，和生成的图像在同一目录\n例如 ./outputs/txt2img-images/", "The learning rate scheduler to use.": "要使用的学习率调度器", "The model to train.": "要训练的模型", "The name of the model to create.": "要创建的模型的名称", "The number of steps to use when generating classifier/regularization images.": "生成分类/规范化图像时使用的步数", "The path to the concepts JSON file, or a JSON string.": "储存概念的 JSON 文件的路径，或 JSON 字符串", "The prompt to use when generating preview images.": "生成预览图像时使用的提示词", "The rate at which the model learns. Default is 0.000005. Use a lower value like 0.000002 or 0.000001 for more complex subjects...like people.": "模型的学习速率。默认为 0.000005。对于更复杂的主体......比如人物，使用较低的值，如 0.000002 或 0.000001", "The resolution of input images. You probably want to pre-process them to match this.": "输入图像的分辨率。你可能希望对它们进行预处理以匹配它", "The seed to use when generating samples. Set to -1 to use a random seed every time.": "生成样本时使用的随机种子。设置为 -1 时每次都使用随机的种子", "The source checkpoint to extract for training.": "用于训练的要提取的源模型(ckpt)", "This fork for auto1111's webui github.com/deforum-art/deforum-for-automatic1111-webui": "此克隆用于 auto1111 的 webui github.com/deforum-art/deforum-for-automatic1111-webui", "This regular expression will be used extract words from filename, and they will be joined using the option below into label text used for training. Leave empty to keep filename text as it is.": "此正则表达式将用于从文件名中提取单词，并将使用以下选项将它们接合到用于训练的标签文本中。留空以保持文件名文本不变", "This script is deprecated. Please use the full Deforum extension instead.": "此脚本已弃用。请改用完整的 Deforum 扩展", "This string will be used to join split words into a single line if the option above is enabled.": "如果启用了上述选项，则此处的字符会用于将拆分的单词接合为同一行", "To enable seed schedule select seed behavior — 'schedule'": "要启用种子调度，请选择随机种子行为——“调度”", "Torch active: Peak amount of VRAM used by Torch during generation, excluding cached data.\nTorch reserved: Peak amount of VRAM allocated by Torch, including all active and cached data.\nSys VRAM: Peak amount of VRAM allocation across all applications / total GPU VRAM (peak utilization%).": "Torch active： 在生成过程中，Torch使用的显存(VRAM)峰值，不包括缓存的数据。\nTorch reserved： Torch 分配的显存(VRAM)的峰值量，包括所有活动和缓存数据。\nSys VRAM： 所有应用程序分配的显存(VRAM)的峰值量 / GPU 的总显存(VRAM)（峰值利用率%）", "Total Number of Class/Reg Images": "用于分类/规范化的图像总数", "Total number of classification images to use. Set to 0 to disable.": "要使用的分类(classification)图像总数。设置为 0 以禁用", "Total number of classification/regularization images to use. If no images exist, they will be generated. Set to 0 to disable prior preservation.": "要使用的分类/规范化图像总数。如果没有图像，就生成一些。设置为 0 以禁用先验存留(prior preservation)", "Total number of training steps to perform. If provided, overrides num_train_epochs.": "要执行的训练迭代步数总数。如果填了，则覆盖 '训练多少期(num_train_epochs)'", "Train EMA": "训练 EMA", "Train Model": "训练模型", "Train Text Encoder": "训练文本编码器", "Train an embedding; must specify a directory with a set of 1:1 ratio images": "训练 Embedding； 必须指定一组具有 1:1 比例图像的目录", "Train multiple concepts from a JSON file or string.": "从 JSON 文件或字符串训练多个概念", "Training Epochs": "训练多少期(Epochs)", "Training Steps": "训练迭代步数", "Training steps": "训练迭代步数", "Unload VAE and CLIP from VRAM when training": "训练时从 显存(VRAM) 卸载 VAE 和 CLIP ", "Update instructions:": "更新指引（英文）：", "Upload mask": "上传蒙版", "Upscale Before Restoring Faces": "放大后再进行面部修复", "Upscale image normally, split result into tiles, improve each tile using img2img, merge whole image back": "正常放大图像，将结果分割成图块(tiles)，用图生图改进每个图块，最后将整个图像合并回来", "Upscale latent space image when doing hires. fix": "做高清修复时，也放大潜变量", "Upscale masked region to target resolution, do inpainting, downscale back and paste into original image": "将蒙版区域（包括预留像素长度的缓冲区域）放大到目标分辨率，进行局部重绘。\n然后缩小并粘贴回原始图像中", "Uscale the image in latent space. Alternative is to produce the full image from latent representation, upscale that, and then move it back to latent space.": "放大潜空间中的图像。而另一种方法是，从潜变量表达中直接解码并生成完整的图像，接着放大它，然后再将其编码回潜空间", "Use 8bit Adam": "使用 8bit Adam", "Use CPU Only (SLOW)": "只用 CPU (很慢)", "Use EMA for finetuning": "使用 EMA 进行微调", "Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition": "使用两步处理的时候，以较小的分辨率生成初步图像，接着放大图像，然后在不更改构图的情况下改进其中的细节", "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime], [datetime