Skip to content

Instantly share code, notes, and snippets.

@journey-ad

journey-ad/I18N_sd-webui-zh_CN.json

Last active October 9, 2024 00:50
Show Gist options
  • Save journey-ad/d98ed173321658be6e51f752d6e6163c to your computer and use it in GitHub Desktop.
Save journey-ad/d98ed173321658be6e51f752d6e6163c to your computer and use it in GitHub Desktop.
Download ZIP
Raw
_README.md
Raw
I18N_sd-webui-zh_CN.json
{
"⤡": "⤡",
"⊞": "⊞",
"×": "×",
"❮": "❮",
"❯": "❯",
"Loading...": "加载中...",
"Waiting...": "等待中...",
"In queue...": "队列中...",
"@@/^Waiting (.*)$/": "等待中 $1",
"@@/^processing (.*)$/": "处理中 $1",
"@@/^queue(.*)$/": "队列$1",
"@@/^(\\d{1,3}%) ETA: (\\d+:\\d+|\\d+s)$/": "进度$1 剩余$2",
"Use via API": "使用了 via API",
"·": "·",
"Built with Gradio": "基于 Gradio 构建",
"Stable Diffusion checkpoint": "Stable Diffusion 模型",
"txt2img": "文生图",
"img2img": "图生图",
"Extras": "附加功能",
"PNG Info": "图片信息",
"Checkpoint Merger": "模型合并",
"Train": "训练",
"Settings": "设置",
"Extensions": "扩展",
"Prompt": "提示词",
"Negative prompt": "反向提示词",
"Interrupt": "中止",
"Skip": "跳过",
"Generate": "生成",
"Run": "运行",
"Styles": "模板风格",
"Label": "标记",
"File": "文件",
"Drop File Here": "拖拽文件到此",
"-": "-",
"or": "或",
"- or -": "- 或 -",
"Click to Upload": "点击上传",
"Textual Inversion": "文本反转",
"Hypernetworks": "超网络",
"Checkpoints": "ckpt模型",
"Lora": "Lora模型",
"Refresh": "刷新",
"Close": "关闭",
"replace preview": "用当前生成图片替换预览",
"Nothing here. Add some content to the following directories:": "无内容，请将模型添加到以下目录:",
"Textbox": "文本框",
"Save preview": "保存预览",
"Sampling method": "采样方法",
"Euler a": "Euler a",
"Euler": "Euler",
"LMS": "LMS",
"Heun": "Heun",
"DPM2": "DPM2",
"DPM2 a": "DPM2 a",
"DPM++ 2S a": "DPM++ 2S a",
"DPM++ 2M": "DPM++ 2M",
"DPM++ SDE": "DPM++ SDE",
"DPM fast": "DPM fast",
"DPM adaptive": "DPM adaptive",
"LMS Karras": "LMS Karras",
"DPM2 Karras": "DPM2 Karras",
"DPM2 a Karras": "DPM2 a Karras",
"DPM++ 2S a Karras": "DPM++ 2S a Karras",
"DPM++ 2M Karras": "DPM++ 2M Karras",
"DPM++ SDE Karras": "DPM++ SDE Karras",
"DDIM": "DDIM",
"PLMS": "PLMS",
"Sampling steps": "采样迭代步数",
"Restore faces": "面部修复",
"Tiling": "可平铺",
"Hires. fix": "高清修复",
"Upscaler": "放大算法",
"Latent": "潜变量",
"Latent (antialiased)": "潜变量 (抗锯齿)",
"Latent (bicubic)": "潜变量 (bicubic)",
"Latent (bicubic antialiased)": "潜变量 (bicubic 抗锯齿)",
"Latent (nearest)": "潜变量 (最近邻)",
"Latent (nearest-exact)": "潜变量 (最近邻-整数)",
"None": "无",
"Lanczos": "Lanczos",
"Nearest": "Nearest",
"ESRGAN_4x": "ESRGAN_4x",
"R-ESRGAN 4x+": "R-ESRGAN 4x+",
"R-ESRGAN 4x+ Anime6B": "R-ESRGAN 4x+ Anime6B",
"LDSR": "LDSR",
"ScuNET GAN": "ScuNET GAN",
"ScuNET PSNR": "ScuNET PSNR",
"SwinIR 4x": "SwinIR 4x",
"Hires steps": "高清修复采样次数",
"Denoising strength": "重绘幅度",
"Upscale by": "放大倍率",
"Resize width to": "将宽度调整到",
"Resize height to": "将高度调整到",
"Width": "宽度",
"Height": "高度",
"⇅": "⇅",
"Batch count": "生成批次",
"Batch size": "每批数量",
"CFG Scale": "提示词相关性",
"Seed": "随机种子",
"Extra": "▼",
"Variation seed": "差异随机种子",
"Variation strength": "差异强度",
"Resize seed from width": "宽度(Resize seed)",
"Resize seed from height": "高度(Resize seed)",
"Override settings": "覆盖设置",
"ControlNet": "扩散控制网络",
"Image": "图像",
"Drop Image Here": "拖拽图像到此",
"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",
"Invert colors if your image has white background.": "使用白色背景图片时请启用\"反色模式\"",
"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",
"Enable": "启用",
"Scribble Mode (Invert colors)": "涂鸦模式（反色，强制预处理器重新识别）",
"Invert Input Color": "反色模式",
"RGB to BGR": "RGB转BGR",
"Low VRAM": "低显存优化",
"Guess Mode": "无提示词模式",
"Preprocessor": "预处理器（直接上传模式图或草稿时可选\"无\"）",
"none": "无",
"canny": "Canny 边缘检测",
"depth": "MiDaS 深度信息估算",
"depth_leres": "LeReS 深度信息估算",
"hed": "HED 边缘检测（保留细节）",
"mlsd": "M-LSD 线条检测",
"normal_map": "法线贴图",
"openpose": "OpenPose 姿态检测",
"openpose_hand": "OpenPose 姿态及手部检测",
"pidinet": "PiDiNet 边缘检测（像素差分网络，可尝试配合HED模型）",
"scribble": "涂鸦",
"fake_scribble": "伪涂鸦",
"segmentation": "ADE20k 语义分割",
"Model": "模型",
"Weight": "权重",
"Guidance strength (T)": "引导强度（迭代参与%）",
"Annotator resolution": "预处理器分辨率",
"Threshold A": "阈值A",
"Threshold B": "阈值B",
"Resize Mode": "画面缩放模式",
"Envelope (Outer Fit)": "信封模式（裁切原图）",
"Scale to Fit (Inner Fit)": "缩放模式（扩展原图，推荐）",
"Just Resize": "仅调整大小（拉伸）",
"Canvas Width": "画布宽度",
"Canvas Height": "画布高度",
"Create blank canvas": "创建空白画布",
"Preview annotator result": "预览预处理结果",
"Hide annotator result": "隐藏预处理预览",
"Script": "脚本",
"Prompt matrix": "提示词矩阵",
"Prompts from file or textbox": "从文本框或文件加载提示词",
"X/Y/Z plot": "X/Y/Z 图表",
"Put variable parts at start of prompt": "把可变部分放在提示词文本的开头",
"Use different seed for each picture": "为每张图片使用不同随机种子",
"Select prompt": "选择提示词",
"positive": "正面",
"negative": "负面",
"Select joining char": "选择分隔符",
"comma": "逗号",
"space": "空格",
"Grid margins (px)": "宫格图边框（像素）",
"Iterate seed every line": "每行输入都换一个随机种子",
"Use same random seed for all lines": "每行输入都使用同一个随机种子",
"List of prompt inputs": "提示词输入列表",
"Upload prompt inputs": "上传提示词输入文件",
"X type": "X轴类型",
"Nothing": "无",
"Var. seed": "差异随机种子",
"Var. strength": "差异强度",
"Steps": "采样迭代步数",
"Prompt S/R": "提示词搜索/替换",
"Prompt order": "提示词顺序",
"Sampler": "采样方法",
"Checkpoint name": "模型名",
"Sigma Churn": "Sigma Churn",
"Sigma min": "最小 Sigma",
"Sigma max": "最大 Sigma",
"Sigma noise": "Sigma 噪声",
"Eta": "Eta",
"Clip skip": "Clip 跳过层",
"Denoising": "重绘幅度",
"Hires upscaler": "高清修复放大算法",
"VAE": "VAE",
"[ControlNet] Model": "[ControlNet] 模型",
"[ControlNet] Weight": "[ControlNet] 权重",
"[ControlNet] Guidance Strength": "[ControlNet] 引导强度",
"[ControlNet] Resize Mode": "[ControlNet] 缩放模式",
"[ControlNet] Preprocessor": "[ControlNet] 预处理器",
"[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",
"X values": "X轴值",
"Y type": "Y轴类型",
"Y values": "Y轴值",
"Z type": "Z轴类型",
"Z values": "Z轴值",
"Draw legend": "显示轴类型和值",
"Keep -1 for seeds": "保持随机种子为-1",
"Include Sub Images": "预览子图像",
"Include Sub Grids": "预览子宫格图",
"Swap X/Y axes": "XY互换",
"Swap Y/Z axes": "YZ互换",
"Swap X/Z axes": "XZ互换",
"Save": "保存",
"Zip": "打包",
"Send to img2img": ">> 图生图",
"Send to inpaint": ">> 局部重绘",
"Send to extras": ">> 附加功能",
"Interrogate\nCLIP": "CLIP\n反推",
"Interrogate\nDeepBooru": "DeepBooru\n反推",
"Sketch": "绘图",
"Inpaint": "局部重绘",
"Inpaint sketch": "局部重绘(手涂蒙版)",
"Inpaint upload": "局部重绘(上传蒙版)",
"Batch": "批量处理",
"Image for img2img": "图生图的图像",
"Copy image to:": "将图片复制到:",
"sketch": "绘图",
"inpaint": "局部重绘",
"inpaint sketch": "局部重绘(手涂蒙版)",
"Image for inpainting with mask": "用于局部重绘并手动画蒙版的图像",
"Color sketch inpainting": "彩色草图修复",
"Mask": "蒙版",
"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",
"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",
"Add inpaint batch mask directory to enable inpaint batch processing.": "添加局部重绘批量处理蒙版目录以启用局部重绘批处理",
"Input directory": "输入目录",
"Output directory": "输出目录",
"Inpaint batch mask directory (required for inpaint batch processing only)": "修复批处理掩码目录（仅用于修复批处理）",
"Resize mode": "缩放模式",
"Just resize": "拉伸",
"Crop and resize": "裁剪",
"Resize and fill": "填充",
"Just resize (latent upscale)": "直接缩放 (放大潜变量)",
"Mask blur": "蒙版模糊",
"Mask transparency": "蒙版透明度",
"Mask mode": "蒙版模式",
"Inpaint masked": "重绘蒙版内容",
"Inpaint not masked": "重绘非蒙版内容",
"Masked content": "蒙版蒙住的内容",
"fill": "填充",
"original": "原图",
"latent noise": "潜变量噪声",
"latent nothing": "潜变量数值零",
"Inpaint area": "重绘区域",
"Whole picture": "全图",
"Only masked": "仅蒙版",
"Only masked padding, pixels": "仅蒙版模式的边缘预留像素",
"Image CFG Scale": "Image CFG Scale",
"img2img alternative test": "图生图的另一种测试",
"Loopback": "回送",
"Outpainting mk2": "向外绘制第二版",
"Poor man's outpainting": "效果稍差的向外绘制",
"SD upscale": "使用 SD 放大",
"should be 2 or lower.": "应小于等于2",
"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)",
"Original prompt": "初始提示词",
"Original negative prompt": "初始反向提示词",
"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`?",
"Decode steps": "解码迭代步数",
"Override `Denoising strength` to 1?": "覆写 `重绘幅度` 为 1?",
"Decode CFG scale": "解码提示词相关性",
"Randomness": "随机度",
"Sigma adjustment for finding noise for image": "为寻找图中噪点的 Sigma 调整",
"Loops": "迭代次数",
"Denoising strength change factor": "重绘幅度的调整系数",
"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",
"Pixels to expand": "拓展的像素数",
"Outpainting direction": "向外绘制的方向",
"left": "左",
"right": "右",
"up": "上",
"down": "下",
"Fall-off exponent (lower=higher detail)": "衰减指数(越小细节越好)",
"Color variation": "色彩变化",
"Will upscale the image by the selected scale factor; use width and height sliders to set tile size": "Will upscale the image by the selected scale factor; use width and height sliders to set tile size",
"Tile overlap": "图块重叠的像素",
"Scale Factor": "Scale Factor",
"Cond. Image Mask Weight": "图像调节屏蔽度",
"Single Image": "单张图像",
"Batch Process": "批量处理",
"Batch from Directory": "从目录进行批量处理",
"Source": "来源",
"Show result images": "显示输出图像",
"Scale by": "等比缩放",
"Scale to": "指定分辨率缩放",
"Resize": "缩放比例",
"Crop to fit": "裁剪以适应宽高比",
"Upscaler 2 visibility": "放大算法 2 可见度",
"GFPGAN visibility": "GFPGAN 可见度",
"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)",
"Send to txt2img": ">> 文生图",
"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",
"Primary model (A)": "模型 A",
"Secondary model (B)": "模型 B",
"Tertiary model (C)": "模型 C",
"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）",
"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",
"Interpolation Method": "合并算法（具体说明会显示在页面顶部）",
"No interpolation": "无插值",
"Weighted sum": "加权和",
"Add difference": "加上差值",
"Checkpoint format": "模型格式",
"ckpt": "ckpt",
"safetensors": "safetensors",
"Save as float16": "以 float16 储存",
"Copy config from": "从...复制配置文件",
"A, B or C": "A, B或C",
"B": "B",
"C": "C",
"Don't": "不复制配置文件（推荐）",
"Bake in VAE": "整合入模型的VAE",
"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",
"Merge": "合并",
"See": "查看",
"wiki": "wiki文档",
"for detailed explanation.": "以了解详细说明",
"Create embedding": "创建 Embedding",
"Create hypernetwork": "创建超网络",
"Preprocess images": "图像预处理",
"Name": "名称",
"Initialization text": "初始化文字",
"Number of vectors per token": "每个词元的向量数",
"Overwrite Old Embedding": "覆写旧的 Embedding",
"Modules": "模块",
"Enter hypernetwork layer structure": "输入超网络层结构",
"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)",
"linear": "linear",
"relu": "relu",
"leakyrelu": "leakyrelu",
"elu": "elu",
"swish": "swish",
"tanh": "tanh",
"sigmoid": "sigmoid",
"celu": "celu",
"gelu": "gelu",
"glu": "glu",
"hardshrink": "hardshrink",
"hardsigmoid": "hardsigmoid",
"hardtanh": "hardtanh",
"logsigmoid": "logsigmoid",
"logsoftmax": "logsoftmax",
"mish": "mish",
"prelu": "prelu",
"rrelu": "rrelu",
"relu6": "relu6",
"selu": "selu",
"silu": "silu",
"softmax": "softmax",
"softmax2d": "softmax2d",
"softmin": "softmin",
"softplus": "softplus",
"softshrink": "softshrink",
"softsign": "softsign",
"tanhshrink": "tanhshrink",
"threshold": "阈值",
"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",
"##tab_ti##Normal": "正态",
"##tab_ti##threshold": "threshold",
"KaimingUniform": "Kaiming 均匀",
"KaimingNormal": "Kaiming 正态",
"XavierUniform": "Xavier 均匀",
"XavierNormal": "Xavier 正态",
"Add layer normalization": "添加层归一化",
"Use dropout": "采用 dropout 防止过拟合",
"Enter hypernetwork Dropout structure (or empty). Recommended : 0~0.35 incrementing sequence: 0, 0.05, 0.15": "输入超网络的 Dropout 结构（或留空）。建议：0~0.35 递增序列：0, 0.05, 0.15",
"Overwrite Old Hypernetwork": "覆写旧的超网络",
"Source directory": "源目录",
"Destination directory": "目标目录",
"Existing Caption txt Action": "对已有的 txt 描述文本的行为",
"ignore": "忽略",
"copy": "复制",
"prepend": "放前面",
"append": "放后面",
"Create flipped copies": "创建镜像副本",
"Split oversized images": "分割过大的图像",
"Auto focal point crop": "自动焦点裁切",
"Auto-sized crop": "自动尺寸裁切",
"Use BLIP for caption": "使用 BLIP 生成说明文字(自然语言描述)",
"Use deepbooru for caption": "使用 deepbooru 生成说明文字(tags)",
"Split image threshold": "图像分割阈值",
"Split image overlap ratio": "分割图像重叠的比率",
"Focal point face weight": "焦点面部权重",
"Focal point entropy weight": "焦点熵权重",
"Focal point edges weight": "焦点线条权重",
"Create debug image": "创建调试图像",
"Each image is center-cropped with an automatically chosen width and height.": "Each image is center-cropped with an automatically chosen width and height.",
"Dimension lower bound": "Dimension lower bound",
"Dimension upper bound": "Dimension upper bound",
"Area lower bound": "Area lower bound",
"Area upper bound": "Area upper bound",
"Resizing objective": "Resizing objective",
"Maximize area": "Maximize area",
"Minimize error": "Minimize error",
"Error threshold": "Error threshold",
"Preprocess": "预处理",
"Train an embedding or Hypernetwork; you must specify a directory with a set of 1:1 ratio images": "训练嵌入式模型或者超网络模型；必须指定一个具有一组 1:1 比例图像的目录",
"[wiki]": "[wiki文档]",
"Embedding": "嵌入式",
"Hypernetwork": "超网络",
"Embedding Learning rate": "嵌入式学习率",
"Hypernetwork Learning rate": "超网络学习率",
"Gradient Clipping": "渐变剪裁",
"disabled": "禁用",
"value": "value",
"norm": "norm",
"Gradient accumulation steps": "梯度累加步数",
"Dataset directory": "数据集目录",
"Log directory": "日志目录",
"Prompt template": "提示词模板",
"Do not resize images": "不调整图像大小",
"Max steps": "最大迭代步数",
"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 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 images with embedding in PNG chunks": "保存图像，并在 PNG 图片文件中嵌入 Embedding 文件",
"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）",
"Shuffle tags by ',' when creating prompts.": "创建提示词时按 ',' 打乱标签",
"Drop out tags when creating prompts.": "创建提示词时丢弃标签",
"Choose latent sampling method": "选择潜变量的采样方法",
"once": "单次复用",
"deterministic": "多次平均",
"random": "随机",
"Train Embedding": "训练 Embedding",
"Train Hypernetwork": "训练超网络",
"Apply settings": "保存设置",
"Reload UI": "重载用户界面",
"Saving images/grids": "保存图像/宫格图",
"Paths for saving": "保存路径",
"Saving to a directory": "保存到目录",
"Upscaling": "放大",
"Face restoration": "面部修复",
"System": "系统",
"Training": "训练",
"Stable Diffusion": "稳定扩散",
"Compatibility": "兼容性",
"Interrogate Options": "反推提示词（图生图页面）",
"Extra Networks": "附加网络",
"User interface": "用户界面",
"Live previews": "实时预览",
"Sampler parameters": "采样器参数",
"Postprocessing": "后处理",
"Actions": "其他操作",
"Licenses": "许可协议",
"Always save all generated images": "始终保存所有生成的图像",
"File format for images": "图像的文件格式",
"Images filename pattern": "图像文件名格式",
"Add number to filename when saving": "储存的时候在文件名里添加数字",
"Always save all generated image grids": "始终保存所有生成的宫格图",
"File format for grids": "宫格图的文件格式",
"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",
"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）",
"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）",
"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",
"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）",
"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）",
"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 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 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",
"For inpainting, save a copy of the greyscale mask": "对于局部重绘，保存一份灰度蒙版的副本",
"For inpainting, save a masked composite": "对于局部重绘，保存蒙版合成",
"Quality for saved jpeg images": "保存的 JPEG 图像的质量",
"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",
"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 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",
"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",
"Do not add watermark to images": "不要给图像加水印（建议开启）",
"Directory for temporary images; leave empty for default": "临时图像目录，默认为空",
"Cleanup non-default temporary directory when starting webui": "启动WebUI时清理非默认临时目录",
"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 txt2img images": "文生图的输出目录",
"Output directory for img2img images": "图生图的输出目录",
"Output directory for images from extras tab": "附加功能选项卡的输出目录",
"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 txt2img grids": "文生图宫格的输出目录",
"Output directory for img2img grids": "图生图宫格的输出目录",
"Directory for saving images using the Save button": "使用“保存”按钮保存图像的目录",
"Save images to a subdirectory": "将图像保存到子目录",
"Save grids to a subdirectory": "将宫格图保存到子目录",
"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",
"Directory name pattern": "目录名称格式",
"Max prompt words for [prompt_words] pattern": "[prompt_words] 格式的最大提示词数量",
"Tile size for ESRGAN upscalers. 0 = no tiling.": "ESRGAN 的图块尺寸。0 为不分块",
"Tile overlap, in pixels for ESRGAN upscalers. Low values = visible seam.": "ESRGAN 的图块重叠像素。较小时可见接缝",
"Upscaler for img2img": "图生图的放大算法",
"LDSR processing steps. Lower = faster": "LDSR 处理步数。越少越快",
"Cache LDSR model in memory": "把LDSR模型缓存在内存中",
"Tile size for all SwinIR.": "适用所有 SwinIR 系算法的图块尺寸",
"Tile overlap, in pixels for SwinIR. Low values = visible seam.": "SwinIR 的图块重叠像素。较小时可见接缝",
"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",
"Move face restoration model from VRAM into RAM after processing": "面部修复处理完成后，将其模型从显存移至内存",
"Show warnings in console.": "将警告信息输出到控制台",
"VRAM usage polls per second during generation. Set to 0 to disable.": "生成图像时，每秒轮询显存使用情况的次数。设置为 0 以禁用",
"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)",
"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",
"Print extra hypernetwork information to console.": "将额外的超网络信息输出到控制台",
"Move VAE and CLIP to RAM when training if possible. Saves VRAM.": "如果可行，在训练时将 VAE 和 CLIP 移至到内存，从而节省显存占用",
"Turn on pin_memory for DataLoader. Makes training slightly faster but can increase memory usage.": "打开DataLoader的pin_memory选项，可以略微加速训练，但会增加内存占用",
"Saves Optimizer state as separate *.optim file. Training of embedding or HN can be resumed with the matching optim file.": "将Optimizer状态保存为单独的*.optim文件。embedding或HN的训练可以使用匹配的optim文件恢复",
"Save textual inversion and hypernet settings to a text file whenever training starts.": "训练开始时将文本反转和超网络设置保存到一个文本文件中",
"Filename word regex": "文件名用词的正则表达式",
"Filename join string": "文件名连接用字符串",
"Number of repeats for a single input image per epoch; used only for displaying epoch number": "每期中单个输入图像的重复次数； 仅用于显示期数",
"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",
"Use cross attention optimizations while training": "训练时开启 cross attention 优化",
"Enable tensorboard logging.": "启用tensorboard日志",
"Save generated images within tensorboard.": "在 tensorboard 中保存生成的图像",
"How often, in seconds, to flush the pending tensorboard events and summaries to disk.": "记录tensorboard事件和摘要信息到磁盘频率，单位秒",
"Checkpoints to cache in RAM": "缓存在内存中的模型数",
"VAE Checkpoints to cache in RAM": "在内存中缓存的VAE数量",
"SD VAE": "模型的 VAE",
"Automatic": "自动（仅加载与模型同名的vae，未找到时不加载）",
"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",
"Inpainting conditioning mask strength": "局部重绘时图像调节的蒙版屏蔽强度",
"Noise multiplier for img2img": "图生图噪声倍率",
"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",
"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",
"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",
"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",
"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",
"Increase coherency by padding from the last comma within n tokens when using more than 75 tokens": "当使用超过 75 个词元时，通过从 n 个词元中的最后一个逗号留空来提高一致性",
"Upcast cross attention layer to float32": "将交叉关注层向上转型到float32",
"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)",
"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)",
"Interrogate: keep models in VRAM": "将模型保存在显存中（不建议开启）",
"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: num_beams for BLIP": "BLIP 的 num_beams",
"Interrogate: minimum description length (excluding artists, etc..)": "最小描述长度（不包括artist等）",
"Interrogate: maximum description length": "最大描述长度",
"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",
"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）",
"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）",
"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）",
"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",
"Default view for Extra Networks": "附加网络默认视图",
"cards": "卡片",
"thumbs": "缩略图",
"Multiplier for extra networks": "附加网络默认倍率",
"Card width for Extra Networks (px)": "卡片宽度（像素）",
"Card height for Extra Networks (px)": "卡片高度（像素）",
"Add hypernetwork to prompt": "将超网络添加到提示词",
"Add Lora to prompt": "将 LoRA 模型添加到提示词",
"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)",
"Show grid in results for web": "在网页的结果中显示宫格图（建议开启）",
"For inpainting, include the greyscale mask in results for web": "对于局部重绘，在网页的结果中显示灰度遮罩",
"For inpainting, include masked composite in results for web": "对于局部重绘，在网页的结果中显示遮罩合成图",
"Do not show any images in results for web": "不在网页的结果中显示任何图像",
"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）",
"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（建议开启）",
"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",
"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\"）",
"Enable full page image viewer": "启用整页图像查看器（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 generation progress in window title.": "在窗口标题中显示生成进度（建议开启）",
"Use dropdown for sampler selection instead of radio group": "使用下拉菜单取代单选列表",
"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",
"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 <extra networks:0.9>": "使用 Ctrl + ↑/↓ 设置 \"<extra networks:0.9>\" 时的精度",
"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\"）",
"txt2img/img2img UI item order": "文生图/图生图界面UI顺序",
"Extra networks tab order": "附加网络标签的顺序",
"Localization (requires restart)": "本地化翻译（需要保存设置并重启）",
"Show progressbar": "显示进度条（建议开启）",
"Show live previews of the created image": "显示已生成图像的实时预览（建议开启）",
"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 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)",
"Image creation progress preview mode": "图像生成过程预览的模式",
"Full": "Full",
"Approx NN": "Approx NN",
"Approx cheap": "Approx cheap",
"Live preview subject": "实时预览的主体",
"Combined": "兼有",
"Progressbar/preview update period, in milliseconds": "进度条/预览更新周期(毫秒)",
"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）",
"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)",
"img2img DDIM discretize": "图生图 DDIM 离散化",
"uniform": "均匀",
"quad": "二阶",
"sigma churn": "sigma churn",
"sigma tmin": "最小 sigma",
"sigma noise": "sigma 噪声",
"Eta noise seed delta": "Eta 噪声种子偏移(建议值31337)",
"Always discard next-to-last sigma": "始终舍弃倒数第二个sigma",
"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",
"Postprocessing operation order": "后处理操作顺序",
"Maximum number of images in upscaling cache": "图像放大缓存中的最大图片数量",
"Config file for Control Net models": "扩散控制网络模型的配置文件",
"Config file for Adapter models": "自适应模型的配置文件",
"Directory for detected maps auto saving": "探测模式图保存路径",
"Extra path to scan for ControlNet models (e.g. training output directory)": "检索扩散控制网络模型的附加目录（如训练输出目录）",
"Multi ControlNet: Max models amount (requires restart)": "多网络联合扩散控制的最大网络数量（需要保存设置并重启，启用后可同时设置多个扩散控制网络，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）",
"Model cache size (requires restart)": "模型缓存数量（需要保存设置并重启）",
"Apply transfer control when loading models": "加载模型时应用传输控制",
"Do not append detectmap to output": "不输出探测模式图（如深度估算图、动作检测图等）",
"Allow detectmap auto saving": "允许自动保存探测模式图",
"Use mid-control on highres pass (second pass)": "进行高清修复时使用中间层控制",
"Use mid-layer control on highres pass (second pass)": "进行高清修复时使用中间层控制",
"Allow other script to control this extension": "允许其他脚本对此扩展插件进行控制",
"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",
"Enable optimized monocular depth estimation": "启用优化单色深度估算",
"Only use mid-control when inference": "仅在生成图片时使用中间层控制",
"Enable CFG-Based guidance": "启用基于CFG的引导（配合无提示词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）",
"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）",
"Download localization template": "下载本地化模板",
"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）",
"Unload SD checkpoint to free VRAM": "卸载SD模型以释放显存",
"Reload the last SD checkpoint back into VRAM": "重新加载最后一个SD模型到显存",
"Show all pages": "显示所有页面",
"Installed": "已安装",
"Available": "可用",
"Install from URL": "从网址安装",
"Apply and restart UI": "应用并重启用户界面",
"Check for updates": "检查更新",
"Disable all extensions": "禁用这些扩展",
"extra": "第三方",
"Extension": "扩展",
"URL": "网址",
"Update": "更新",
"unknown": "未知",
"built-in": "内置",
"ScuNET": "ScuNET",
"prompt-bracket-checker": "prompt-bracket-checker",
"Load from:": "加载自：",
"Extension index URL": "扩展列表网址",
"Hide extensions with tags": "隐藏含有以下标签的扩展",
"script": "脚本",
"ads": "含广告",
"localization": "本地化翻译",
"installed": "已安装",
"training": "训练相关",
"models": "模型相关",
"UI related": "UI界面相关",
"prompting": "提示词相关",
"editing": "图像编辑(外部)",
"manipulations": "图像变换(内部)",
"online": "在线功能",
"animation": "动画相关",
"query": "图像信息",
"science": "测试性功能",
"integrations": "集成功能",
"Order": "排序方式",
"newest first": "最新",
"oldest first": "发布时间",
"a-z": "名字顺序",
"z-a": "名字倒序",
"internal order": "内部排序",
"URL for extension's git repository": "扩展的 git 仓库网址",
"Local directory name": "本地目录名",
"Install": "安装",
"@@/^Added: (.*)$/": "添加于: $1",
"@@/^Extension hidden: (\\d+)$/": "隐藏扩展数: $1",
"Use checkbox to enable the extension; it will be enabled or disabled when you click apply button": "此列勾选的扩展将会被启用",
"Extension version": "扩展版本",
"Use checkbox to mark the extension for update; it will be updated when you click apply button": "使用复选框标记要更新的扩展，点击“应用并重启”按钮更新",
"a general extension that adds functionality": "通用类的扩展，用于添加某种功能",
"a localization extension that translates web ui into another language": "本地化翻译类的扩展，用于将界面翻译成其他语言",
"adds a tab": "添加一个标签页",
"adds a dropbear in the ui": "添加一个下拉框",
"contains ads": "此类扩展可能含有广告内容",
"an extension that is already installed": "此扩展已经安装",
"new type of training, assists with training, and/or merging related.": "模型训练相关的扩展，包括新的训练方式、辅助训练、合并训练结果等",
"new type of training / assists with training.": "模型训练相关的扩展，包括新的训练方式、辅助训练等",
"conversion and merging related.": "模型转换/合并相关的扩展",
"enhances the display or user interface experience.": "增强界面的显示效果或用户体验",
"assists with writing words, for prompts.": "书写prompt词的辅助工具",
"an extension that changes images, not using stable diffusion.": "此类扩展会以非扩散模型的方式改变图像",
"an extension that changes images with stable diffusion.": "此类扩展会作用在扩散模型内部，从而改变图像",
"an extension which requires wifi to use, often API related.": "此类扩展需要连接网络才能使用，通常是与API相关的",
"an extension related to creating videos with stable diffusion.": "此类扩展可以借助稳定扩散模型生成视频",
"extracting info from images.": "从图像中提取信息",
"experimentation with stable diffusion.": "稳定扩散的实验性功能",
"plugins, apis, and other ML models that work/ align with user workflow.": "此类扩展会添加一些插件、API或其他机器学习模型，用于与用户的工作流程对齐",
"AssertionError: extension access disabled because of command line flags": "验证失败：命令行启动参数禁止了不安全的扩展访问",
"API": "API",
"•": "・",
"Github": "Github",
"Gradio": "Gradio",
"python:": "python:",
"N/A": "N/A",
"Change checkpoint": "Change checkpoint",
"Prompt (press Ctrl+Enter or Alt+Enter to generate)": "提示词（按 Ctrl+Enter 或 Alt+Enter 生成）",
"Negative prompt (press Ctrl+Enter or Alt+Enter to generate)": "反向提示词（按 Ctrl+Enter 或 Alt+Enter 生成）",
"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",
"Stop processing current image and continue processing.": "停止处理当前图像，并继续处理下一个",
"Read generation parameters from prompt or last generation if prompt is empty into user interface.": "从提示词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）",
"Clear prompt": "清空提示词",
"Show extra networks": "显示附加网络面板",
"Apply selected styles to current prompt": "将已选择的模板风格写入当前的提示词",
"Save style": "将当前的提示词保存为模板风格",
"Remove All": "全部移除",
"Search...": "搜索...",
"Which algorithm to use to produce the image": "使用哪种算法生成图像",
"Euler Ancestral - very creative, each can get a completely different picture depending on step count, setting steps higher than 30-40 does not help": "Euler Ancestoral - 此方法非常有创意，每个人都可以根据不同步数获得完全不同的画面，设置超过30-40的步数没有用",
"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",
"Produce an image that can be tiled.": "生成可用于平铺的图像",
"Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition": "使用两步处理的时候，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",
"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",
"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",
"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",
"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",
"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",
"How many batches of images to create": "创建多少批次的图像",
"How many image to create in a single batch": "每批创建多少图像",
"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 - 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",
"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",
"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",
"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",
"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",
"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）",
"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",
"Do not do anything special": "什么都不做",
"Separate values for X axis using commas.": "使用逗号分隔 X 轴的值",
"Paste available values into the field": "Paste available values into the field",
"Separate values for Y axis using commas.": "使用逗号分隔 Y 轴的值",
"Open images output directory": "打开图像输出目录",
"Write image to a directory (default - log/images) and generation parameters into csv file.": "将图像写入目录（默认 - log/images）并将生成参数写入 csv 表格文件",
"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 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",
"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",
"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",
"What to put inside the masked area before processing it with Stable Diffusion.": "在使用 Stable Diffusion 处理蒙版区域之前要在蒙版区域内放置什么",
"fill it with colors of the image": "用图像的颜色(高强度模糊)填充它",
"keep whatever was there originally": "保留原来的图像，不进行预处理",
"fill it with latent space noise": "于潜空间填充噪声",
"fill it with latent space zeroes": "于潜空间填零",
"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",
"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",
"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 放大时，图块之间应该有多少像素重叠。图块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",
"A directory on the same machine where the server is running.": "服务器主机上某一目录",
"Leave blank to save images to the default path.": "留空以将图像保存到默认路径",
"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",
"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）",
"If the number of tokens is more than the number of vectors, some may be skipped.\nLeave the textbox empty to start with zeroed out vectors": "If the number of tokens is more than the number of vectors, some may be skipped.\nLeave the textbox empty to start with zeroed out vectors",
"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'",
"1st and last digit must be 0 and values should be between 0 and 1. ex:'0, 0.01, 0'": "1st and last digit must be 0 and values should be between 0 and 1. ex:'0, 0.01, 0'",
"Gradient clip value": "Gradient clip value",
"Path to directory with input images": "带有输入图像的目录路径",
"Path to directory where to write outputs": "进行输出的目录路径",
"Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
"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",
"Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg],[prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg],[prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
"Restore low quality faces using GFPGAN neural network": "使用 GFPGAN 神经网络修复低质量面部",
"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 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",
"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",
"Early stopping parameter for CLIP model; 1 is stop at last layer as usual, 2 is stop at penultimate layer, etc.": "Early stopping parameter for CLIP model; 1 is stop at last layer as usual, 2 is stop at penultimate layer, etc.",
"When adding extra network such as Hypernetwork or Lora to prompt, use this multiplier for it.": "When adding extra network such as Hypernetwork or Lora to prompt, use this multiplier for it.",
"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",
"Comma-separated list of tab names; tabs listed here will appear in the extra networks UI first and in order lsited.": "Comma-separated list of tab names; tabs listed here will appear in the extra networks UI first and in order lsited.",
"Cheap neural network approximation. Very fast compared to VAE, but produces pictures with 4 times smaller horizontal/vertical resolution and lower quality.": "Cheap neural network approximation. Very fast compared to VAE, but produces pictures with 4 times smaller horizontal/vertical resolution and lower quality.",
"Very cheap approximation. Very fast compared to VAE, but produces pictures with 8 times smaller horizontal/vertical resolution and extremely low quality.": "Very cheap approximation. Very fast compared to VAE, but produces pictures with 8 times smaller horizontal/vertical resolution and extremely low quality.",
"Ignores step count - uses a number of steps determined by the CFG and resolution": "Ignores step count - uses a number of steps determined by the CFG and resolution",
"Denoising Diffusion Implicit Models - best at inpainting": "Denoising Diffusion Implicit models - 最擅长局部重绘",
"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",
"Leave empty for auto": "留空时自动生成",
"s": "s",
"Additional Networks": "可选附加网络",
"Create aesthetic embedding": "创建美术风格",
"parameters": "参数",
"BSRGAN": "BSRGAN",
"R-ESRGAN General 4xV3": "R-ESRGAN General 4xV3",
"R-ESRGAN 2x+": "R-ESRGAN 2x+",
"SwinIR_4x": "SwinIR_4x",
"▼": "▼",
"Separate UNet/Text Encoder weights": "单独设置 UNet/Text Encoder 的权重",
"Network module 1": "附加网络类型 1",
"LoRA": "LoRA",
"Model 1": "模型 1",
"Weight 1": "权重 1",
"UNet Weight 1": "UNet 权重 1",
"TEnc Weight 1": "Text Encoder 权重 1",
"Network module 2": "附加网络类型 2",
"Model 2": "模型 2",
"Weight 2": "权重 2",
"UNet Weight 2": "UNet 权重 2",
"TEnc Weight 2": "Text Encoder 权重 2",
"Network module 3": "附加网络类型 3",
"Model 3": "模型 3",
"Weight 3": "权重 3",
"UNet Weight 3": "UNet 权重 3",
"TEnc Weight 3": "Text Encoder 权重 3",
"Network module 4": "附加网络类型 4",
"Model 4": "模型 4",
"Weight 4": "权重 4",
"UNet Weight 4": "UNet 权重 4",
"TEnc Weight 4": "Text Encoder 权重 4",
"Network module 5": "附加网络类型 5",
"Model 5": "模型 5",
"Weight 5": "权重 5",
"UNet Weight 5": "UNet 权重 5",
"TEnc Weight 5": "Text Encoder 权重 5",
"Extra args": "额外参数",
"mask image:": "蒙版图像:",
"Refresh models": "刷新模型列表",
"Open for Clip Aesthetic!": "打开以调整 Clip 的美术风格！",
"Aesthetic weight": "美术风格权重",
"Aesthetic steps": "美术风格迭代步数",
"Aesthetic learning rate": "美术风格学习率",
"Slerp interpolation": "球面线性插值",
"Aesthetic imgs embedding": "美术风格图集 Embedding",
"Aesthetic text for imgs": "该图集的美术风格描述",
"Slerp angle": "球面线性插值角度",
"Is negative text": "是反向提示词",
"Combinations": "组合",
"Choose a number of terms from a list, in this case we choose two artists": "从列表中选择一些术语，在本例中，我们选择两位画师",
"{2$$artist1|artist2|artist3}": "{2$$artist1|artist2|artist3}",
"If $$ is not provided, then 1$$ is assumed.": "若没提供 $$，默认为 1$$",
"A range can be provided:": "项数可以有范围",
"{1-3$$artist1|artist2|artist3}": "{1-3$$artist1|artist2|artist3}",
"In this case, a random number of artists between 1 and 3 is chosen.": "在这个示例中，会从中随机选 1 至 3 个画师",
"Wildcards": "通配符",
"Available wildcards": "可用的通配符",
"WILDCARD_DIR: scripts/wildcards": "WILDCARD_DIR: scripts/wildcards",
"You can add more wildcards by creating a text file with one term per line and name is mywildcards.txt. Place it in scripts/wildcards.": "您可以通过创建一个文本文件来添加更多通配符，该文件每行包含一个术语，名称为mywildcards.txt。请将其放在scripts/wildcards中",
"__mywildcards__": "__mywildcards__",
"will then become available.": "文件放在相应目录就能被识别",
"Variables": "变量",
"Set a variable like so:": "通过这种方式设置变量",
"Now use it like this:": "，然后像这样来使用",
"For more details, and functionality, see the documentation (coming soon)": "，更多详细信息和功能请参阅文档（即将推出）",
"AddNet Model 1": "[可选附加网络] 模型 1",
"AddNet Weight 1": "[可选附加网络] 权重 1",
"AddNet UNet Weight 1": "[可选附加网络] UNet 权重 1",
"AddNet TEnc Weight 1": "[可选附加网络] Text Encoder 权重 1",
"AddNet Model 2": "[可选附加网络] 模型 2",
"AddNet Weight 2": "[可选附加网络] 权重 2",
"AddNet UNet Weight 2": "[可选附加网络] UNet 权重 2",
"AddNet TEnc Weight 2": "[可选附加网络] Text Encoder 权重 2",
"AddNet Model 3": "[可选附加网络] 模型 3",
"AddNet Weight 3": "[可选附加网络] 权重 3",
"AddNet UNet Weight 3": "[可选附加网络] UNet 权重 3",
"AddNet TEnc Weight 3": "[可选附加网络] Text Encoder 权重 3",
"AddNet Model 4": "[可选附加网络] 模型 4",
"AddNet Weight 4": "[可选附加网络] 权重 4",
"AddNet UNet Weight 4": "[可选附加网络] UNet 权重 4",
"AddNet TEnc Weight 4": "[可选附加网络] Text Encoder 权重 4",
"AddNet Model 5": "[可选附加网络] 模型 5",
"AddNet Weight 5": "[可选附加网络] 权重 5",
"AddNet UNet Weight 5": "[可选附加网络] UNet 权重 5",
"AddNet TEnc Weight 5": "[可选附加网络] Text Encoder 权重 5",
"Disabled when launched with --hide-ui-dir-config.": "启动 --hide-ui-dir-config 时禁用",
"Append interrogated prompt at each iteration": "Append interrogated prompt at each iteration",
"CLIP": "CLIP",
"DeepBooru": "DeepBooru",
"Use PNG alpha channel as loss weight": "使用PNG alpha通道作为损失权重",
"Model path filter": "模型路径过滤",
"Network module": "附加网络模式",
"Model hash": "模型哈希",
"Legacy hash": "旧哈希",
"Model path": "模型路径",
"Send to txt2img:": "发送模型到文生图",
"1️⃣": "1️⃣",
"2️⃣": "2️⃣",
"3️⃣": "3️⃣",
"4️⃣": "4️⃣",
"5️⃣": "5️⃣",
"Send to img2img:": "发送模型到图生图",
"Copy metadata to other models in directory": "将元数据复制到其他目录中的模型",
"Containing directory": "目标模型目录",
"Only copy to models with same session ID": "仅复制到具有相同 session ID 的模型",
"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）",
"Copy Metadata": "开始复制元数据",
"Author": "作者",
"Keywords": "关键词",
"Description": "描述",
"Rating": "评分",
"Tags": "标签",
"Editing Enabled": "开启元数据编辑",
"Save Metadata": "保存元数据",
"Cover image": "封面图像",
"Image Parameters": "图像参数",
"Training info": "训练信息",
"Most frequent tags in captions": "训练用描述文本里tags的频率列表",
"Dataset folder structure": "数据集文件夹结构",
"Image Count": "图像计数",
"Repeats": "重复次数",
"Total Images": "图像总数",
"Training parameters": "训练参数",
"copy to clipboard": "复制",
"{": "{",
"}": "}",
"Generate Info": "生成信息",
"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 images embedding": "创建图集 Embedding",
"Tag Autocomplete": "Tag自动填充",
"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",
"File size limit for the above option, MB": "上述选项的文件大小限制，单位：MB",
"Width/height limit for the above option, in pixels": "上述选项的宽、高限制，单位：像素",
"Maximum image size, in megapixels": "最大图像尺寸，单位：百万像素",
"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)",
"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）",
"Sort LoRA models by": "LoRA 模型的排序方式",
"name": "名称",
"date": "日期",
"path name": "路径名",
"rating": "评分",
"has user metadata": "具有用户元数据",
"Reverse model sort order": "逆序排序",
"LoRA model name filter": "LoRA 模型名称过滤器",
"Metadata to show in XY-Grid label for Model axes, comma-separated (example: \"ss_learning_rate, ss_num_epochs\")": "显示在X/Y图标签下的元数据选项，逗号分隔（示例：\"ss_learning_rate, ss_num_epochs\"）",
"# 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）",
"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",
"Only show .safetensors format models": "只显示 .safetensors 格式的模型",
"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",
"has metadata": "有元数据",
"missing metadata": "缺失元数据",
"Max number of top tags to show": "要显示的最大常见标签数",
"Max number of dataset folders to show": "要显示的最大数据集文件夹数",
"Tag filename": "词库文件",
"Enable Tag Autocompletion": "启用Tag自动补全",
"Active in txt2img (Requires restart)": "在文生图页面启用（需要保存设置并重启）",
"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)": "在反向提示词中启用（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）",
"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）",
"Mode to use for model list": "将以上列表内的模型设为",
"Blacklist": "黑名单（禁用tag自动填充）",
"Whitelist": "白名单（启用tag自动填充）",
"Maximum results": "单页最大结果数量",
"Show all results": "显示所有结果",
"How many results to load at once": "单次加载的结果数量",
"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）",
"Search for wildcards": "使用通配符",
"Search for embeddings": "搜索嵌入式",
"Search for hypernetworks": "搜索超网络",
"Search for Loras": "搜索 LoRA",
"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：页面含有色情内容，谨慎浏览，需要科学上网）",
"Replace underscores with spaces on insertion": "将下划线替换为空格",
"Escape parentheses on insertion": "对插入的括号进行转义",
"Append comma on tag autocompletion": "自动添加逗号",
"Search by alias": "使用别称搜索",
"Only show alias": "仅显示别称",
"Translation filename": "词库翻译文件",
"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",
"Search by translation": "使用译名搜索",
"Extra filename (for small sets of custom tags)": "附加词库文件（用于少量自定义标记）",
"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",
"Insert before": "在前面插入",
"Insert after": "在后面插入",
"Configure Hotkeys. For possible values, see https://www.w3.org/TR/uievents-key, or leave empty / set to 'None' to disable. Must be valid JSON.": "快捷键配置 键值参考 https://www.w3.org/TR/uievents-key，或将其留空/设置为\"None\"以禁用，必须是合法 JSON",
"Configure colors. See https://github.com/DominikDoom/a1111-sd-webui-tagcomplete#colors for info. Must be valid JSON.": "颜色配置 参考 https://github.com/DominikDoom/a1111-sd-webui-tagcomplete#colors，必须是合法 JSON",
"Version": "版本信息",
"stable-diffusion-webui-aesthetic-gradients": "美术风格梯度",
"How many batches of images to create (has no impact on generation performance or VRAM usage)": "要生成多少批图像（不影响生成性能或显存占用）",
"How many image to create in a single batch (increases generation performance at cost of higher VRAM usage)": "在批量生成中单次创建多少图像（代价是更高的显存占用）",
"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",
"Filter models by path name": "下面的模型列表将仅显示此路径下的模型",
"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",
"Display name for this model": "此模型显示的名称",
"Author of this model": "此模型的作者",
"Activation keywords, comma-separated": "该模型的触发词，逗号分隔",
"Model description/readme/notes/instructions": "模型的描述信息",
"Source URL where this model could be found": "发布该模型的网址",
"Comma-separated list of tags (\"artist, style, character, 2d, 3d...\")": "此模型的标签，逗号分隔\n(\"artist, style, character, 2d, 3d...\")",
"view": "查看",
"api": "api",
"built with gradio": "基于 Gradio 构建",
"Dreambooth": "Dreambooth",
"Smart Preprocess": "智能预处理",
"Embedding Editor": "Embedding 编辑器",
"Image Browser": "图库浏览器",
"Tokenizer": "词元分析器",
"Training Picker": "训练图挑选器",
"Style 1": "模版风格 1",
"Style 2": "模版风格 2",
"Check progress": "查看进度",
"Check progress (first)": "(首次)查看进度",
"Sampling Steps": "采样迭代步数",
"Highres. fix": "高清修复",
"Firstpass width": "首次宽度",
"Firstpass height": "首次高度",
"Latent Mirror mode": "镜像潜变量模式",
"Alternate Steps": "交替迭代",
"Blend Average": "平均混合",
"Latent Mirror style": "潜变量镜像方式",
"Vertical Mirroring": "垂直镜像",
"Horizontal Mirroring": "水平镜像",
"Horizontal+Vertical Mirroring": "垂直+水平镜像",
"90 Degree Rotation": "90度旋转",
"180 Degree Rotation": "180度旋转",
"Roll Channels": "色彩通道轮替",
"X panning": "沿 X 轴滚动",
"Y panning": "沿 Y 轴滚动",
"Maximum steps fraction to mirror at": "镜像干涉止步于总迭代步数的",
"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)",
"Cond.fix: Disabled (none)": "修复时调节：禁用 (无)",
"Cond.fix: Empty": "修复时调节：空掉",
"Cond.fix: Lowest": "修复时调节：最小",
"Cond.fix: Low": "修复时调节：小",
"Cond.fix: Medium": "修复时调节：中",
"Cond.fix: High (recommended)": "修复时调节：高 (推荐)",
"Cond.fix: Highest": "修复时调节：最高",
"Cond.fix: Full": "修复时调节：完全",
"Randomize": "随机化",
"Highres. percentage chance": "高清修复：随机概率",
"Highres. Denoising Strength": "高清修复：重绘幅度",
"Highres. Width": "高清修复：第一遍宽度",
"Highres. Height": "高清修复：第一遍高度",
"Stop at CLIP layers": "在 CLIP 模型的最后哪一层停下 (Clip skip)",
"Dry Run": "试运行",
"Dismiss": "屏蔽",
"Dynamic Prompts": "动态提示词",
"Ignore whitespace in prompts: All newlines, tabs, and multiple spaces are replaced by a single space": "忽略提示词中的空白符 - 所有的换行符、制表符和多个空格都将被替换为单个空格",
"Save template to metadata: Write prompt template into the PNG metadata": "保存模版至元数据 - 将提示词模版写入到 PNG 元数据",
"Write prompts to file: Create a new .txt file for every batch containing the prompt template as well as the generated prompts.": "将提示词写入文件 - 为每个批次创建一个新的 .txt 文件，其中包含提示词模版以及生成的提示词",
"String to use as left bracket for parser variants, .e.g {variant1|variant2|variant3}": "用于解析变体的左括号，例如 {variant1|variant2|variant3}",
"String to use as right bracket for parser variants, .e.g {variant1|variant2|variant3}": "用于解析变体的右括号，例如 {variant1|variant2|variant3}",
"String to use as wrap for parser wildcard, .e.g __wildcard__": "用于解析通配符的前后缀，例如 __wildcard__",
"Limit Jinja prompts: Limit the number of prompts to batch_count * batch_size. The default is to generate batch_count * batch_size * number of prompts generated by Jinja": "限制 Jinja 提示词 - 限制提示词的数量为 (batch_count * batch_size)。默认提示词的数量为 (batch_count * batch_size * Jinja 生成的提示词数量)",
"Default magic prompt model": "默认的魔法提示词模型",
"Magic Prompt batch size (higher is faster but uses more memory)": "魔法提示词批次大小 (越大越快但使用更多内存)",
"Dynamic Prompts enabled": "启用动态提示词",
"Complete documentation is available at https://github.com/adieyal/sd-dynamic-prompts. Please report any issues on GitHub.": "完整文档请访问 https://github.com/adieyal/sd-dynamic-prompts ，有任何问题请在 GitHub 上报告",
"Combinatorial generation": "组合生成",
"Generate all possible prompt combinations.": "生成所有可能的提示词组合",
"Max generations (0 = all combinations - the batch count value is ignored)": "最大生成数 (0=所有组合 批次数值将被忽略)",
"Limit the maximum number of prompts generated. 0 (default) will generate all images. Useful to prevent an unexpected combinatorial explosion.": "限制最大生成数，可用于防止意外的组合爆炸。0(默认)生成所有图片",
"Combinatorial batches": "组合批次",
"Re-run your combinatorial batch this many times with a different seed each time.": "重复运行组合批次，每次都使用不同的随机种子",
"Prompt Magic": "魔法提示词",
"Magic prompt": "魔法提示词",
"Max magic prompt length": "魔法提示词最大长度",
"Magic prompt creativity": "魔法提示词创意",
"Magic prompt model": "魔法提示词模型",
"Note: Each model will download between 300mb and 1.4gb of data on first use.": "注意：每个模型第一次使用时都会下载 300mb 到 1.4gb 的数据",
"Magic prompt blocklist regex": "魔法提示词屏蔽正则",
"Regular expression pattern for blocking terms out of the generated prompt. Applied case-insensitively. For instance, to block both \"purple\" and \"interdimensional\", you could use the pattern \"purple|interdimensional\".": "此处填写正则表达式，用于屏蔽生成的提示词中的某些项,不区分大小写。例如要屏蔽 \"purple\" 和 \"interdimensional\" ，可以使用 \"purple|interdimensional\" ",
"I'm feeling lucky": "手气不错",
"Attention grabber": "随机关键词吸引注意力",
"Minimum attention": "最小关键词",
"Maximum attention": "最大关键词",
"Don't apply to negative prompts": "不应用于负提示词",
"Don't use prompt magic on negative prompts.": "不在负提示词上使用魔法提示词",
"Write prompts to file": "将提示词写入文件",
"Don't generate images": "不生成图像",
"Disable image generation. Useful if you only want to generate text prompts. (1 image will still be generated to keep Auto1111 happy.).": "禁用图像生成。如果你只想生成文本提示词，这个选项很有用 (为了让 Auto1111 开心，仍会生成一张图像)。",
"Help": "帮助",
"Need help?": "需要帮助？",
"Syntax cheatsheet": "语法速查表",
"Tutorial": "教程",
"Discussions": "讨论区",
"Report a bug": "报告Bug",
"Choose a number of terms from a list, in this case we choose two artists:": "从列表中选几项，这里选了两个画师",
"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：",
"{2$$__artist__}": "{2$$__artist__}",
"is equivalent to": "等同于",
"{2$$__artist__|__artist__}": "{2$$__artist__|__artist_}",
"Options can be given weights:": "可以给选项加上权重：",
"{2::artist1|artist2}": "{2::artist1|artist2}",
"In this case, artist1 will be chosen twice as often as artist2.": "在这个示例中，artist1被选中的概率是artist2的两倍",
"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",
"{{1-$$and$$__adjective__}}": "{{1-3$$and$$__adjective__}}",
"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",
"Find and manage wildcards in the Wildcards Manager tab.": "在通配符管理器标签页中查找和管理通配符",
"@@/^You can add more wildcards by creating a text file with one term per line and name is mywildcards.txt. Place it in (.*)$/i": "你可以通过创建一个每行一个词的文本文件并命名为 mywildcards.txt 来添加更多通配符。将其放在 $1 中",
"Find more settings on the": "其他设置项访问",
"You are using": "你正在使用",
"@@/^version (\\d+\\.\\d+\\.[\\d+*]) of the WebUI extension$/": "扩展版本 v$1",
", and the underlying": "，底层",
"@@/^dynamicprompts library is version (\\d+\\.\\d+\\.[\\d+*])$/": "动态提示词库版本 v$1",
"If the groups wont drop down click": "如果无法下拉组，点击",
"here": "这里",
"to fix the issue.": "修复",
"Jinja2 templates": "Jinja2 模板",
"Enable Jinja2 templates": "启用 Jinja2 模板",
"Help for Jinja2 templates": "Jinja2 模板帮助",
"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",
"Literals": "字面量",
"I love red roses": "I love red roses",
"Random choices": "随机选择",
"I love {{ choice('red', 'blue', 'green') }} roses": "I love {{ choice('red', 'blue', 'green') }} roses",
"This will randomly choose one of the three colors.": "会随机从三种颜色中选一个",
"Iterations": "迭代",
"{% for colour in ['red', 'blue', 'green'] %}\n {% prompt %}I love {{ colour }} roses{% endprompt %}\n {% endfor %}": "{% for colour in ['red', 'blue', 'green'] %}\n {% prompt %}I love {{ colour }} roses{% endprompt %}\n {% endfor %}",
"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",
"{% for colour in wildcard(\"__colours__\") %}\n {% prompt %}I love {{ colour }} roses{% endprompt %}\n {% endfor %}": "{% for colour in wildcard(\"__colours__\") %}\n {% prompt %}I love {{ colour }} roses{% endprompt %}\n {% endfor %}",
"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",
"Conditionals": "条件",
"{% for colour in [\"red\", \"blue\", \"green\"] %}\n {% if colour == \"red\"}\n {% prompt %}I love {{ colour }} roses{% endprompt %}\n {% else %}\n {% prompt %}I hate {{ colour }} roses{% endprompt %}\n {% endif %}\n {% endfor %}": "{% for colour in [\"red\", \"blue\", \"green\"] %}\n {% if colour == \"red\"}\n {% prompt %}I love {{ colour }} roses{% endprompt %}\n {% else %}\n {% prompt %}I hate {{ colour }} roses{% endprompt %}\n {% endif %}\n {% endfor %}",
"This will produce the following prompts:": "会产生下列提示词",
"I hate blue roses": "I hate blue roses",
"I hate green roses": "I hate green roses",
"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 documentation.": "Jinja2 文档",
"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",
"Advanced options": "高级选项",
"Some settings have been moved to the settings tab. Find them in the Dynamic Prompts section.": "一些设置项已经移动到设置标签页中，可以在动态提示词部分找到它们",
"Unlink seed from prompt": "将随机种子与提示词解绑",
"Disable negative prompt": "禁用反向提示词",
"Fixed seed": "固定随机种子",
"Advanced Seed Blending": "高阶种子混合",
"Embedding to Shareable PNG": "将 Embedding 转换为可分享的 PNG 图片文件",
"X/Y plot": "X/Y 图表",
"Seed travel": "种子变迁",
"Shift attention": "关注转移",
"Prompt Travel": "提示词变迁",
"Seeds": "随机种子",
"Source embedding to convert": "用于转换的源 Embedding",
"Embedding token": "Embedding 的词元 / 关键词",
"Hypernet str.": "超网络 强度",
"Include Separate Images": "生成图表时，保留每一张图像",
"Primary detection model (A)": "首要检测模型 (A)",
"Detection confidence threshold % (A)": "检测置信阈值 % (A)",
"Dilation factor (A)": "扩张因子 (A)",
"X offset (A)": "X 偏移 (A)",
"Y offset (A)": "Y 偏移 (A)",
"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",
"Bitwise operation": "按位运算",
"A&B": "A&B",
"A-B": "A-B",
"Secondary detection model (B) (optional)": "次要检测模型 (B) (可选)",
"Detection confidence threshold % (B)": "检测置信阈值 % (B)",
"Dilation factor (B)": "扩张因子 (B)",
"X offset (B)": "X 偏移 (B)",
"Y offset (B)": "Y 偏移 (B)",
"Denoising strength (Inpaint)": "重绘幅度 (局部重绘)",
"Destination seed(s) (Comma separated)": "目标种子 (逗号分割)",
"Only use Random seeds (Unless comparing paths)": "只用随机种子 (除非需要对比变迁轨迹)",
"Number of random seed(s)": "随机种子数量",
"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)",
"Loop back to initial seed": "再变迁回初始种子",
"Save results as video": "保存结果为视频",
"Frames per second": "每秒多少帧",
"Number of frames for lead in/out": "渐入/渐出帧数",
"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)",
"Show generated images in ui": "在用户界面上显示生成了的图像",
"\"Hug the middle\" during interpolation": "在插值的途中 \"主动去找中间点\"",
"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)",
"Travel mode": "变迁模式",
"replace": "取代",
"grad": "梯度",
"Travel steps between stages": "每个阶段变迁的迭代步数",
"Replace order (replace mode)": "取代顺序 (取代模式)",
"Replace order": "取代顺序",
"most_similar": "最相似",
"most_different": "最大差异",
"grad_min": "最小梯度",
"grad_max": "最大梯度",
"Step size (grad mode)": "步幅 (梯度模式)",
"Step count (grad mode)": "步数 (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 count": "步数 (梯度模式)",
"Step method": "步进方法 (梯度模式)",
"clip": "clip",
"sign": "sign",
"Weight for latent match (grad/replace-grad mode)": "用于匹配潜变量(latent)的权重 (梯度/取代模式)",
"Weight for cond match (grad/replace-grad mode)": "用于匹配文字调节(cond)的权重 (梯度/取代模式)",
"Weight for latent match": "用于匹配潜变量(latent)的权重",
"Weight for cond match": "用于匹配文字调节(cond)的权重",
"Video file format": "视频格式",
"mp4": "mp4",
"gif": "gif",
"Video FPS": "视频 FPS",
"Pad begin/end frames": "预留开始/结束帧",
"Pick frames every n-th": "每 n 帧挑选 1 帧",
"Pick every n-th frame": "每 n 帧挑选 1 帧",
"Video drop last frame": "丢弃视频最后一帧",
"Show console debug": "在控制台显示调试信息",
"Show verbose debug info at console": "在控制台中输出详尽的调试信息",
"Make Zip when Save?": "保存时创建zip压缩文件?",
"Batch img2img": "批量图生图",
"Draw mask": "绘制蒙版",
"Upload mask": "上传蒙版",
"Masking mode": "蒙版模式",
"Inpaint at full resolution": "全分辨率局部重绘",
"Inpaint at full resolution padding, pixels": "预留像素",
"Will upscale the image to twice the dimensions; use width and height sliders to set tile size": "将图像放大到两倍尺寸； 使用宽度和高度滑块设置图块尺寸(tile size)",
"BSRGAN 4x": "BSRGAN 4x",
"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",
"Upscale Before Restoring Faces": "放大后再进行面部修复",
"A merger of the two checkpoints will be generated in your": "合并后的模型会生成在你的",
"checkpoint": "模型",
"directory.": "目录",
"DreamArtist Create embedding": "梦作家 创建 Embedding",
"DreamArtist Train": "梦作家 训练",
"Prompt template file": "提示词模版文件",
"Use negative embedding (DreamArtist)": "使用反向 Embedding (梦作家)",
"Number of negative vectors per token": "每个词元的反向向量数",
"DreamArtist": "梦作家",
"Train with DreamArtist": "使用梦作家训练",
"Train with reconstruction": "训练时开启重建",
"CFG scale": "提示词相关性",
"Reconstruction loss weight": "重建损失权重",
"Negative lr weight": "反向的学习率权重",
"Classifier path": "分类器的路径",
"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]）",
"EMA (positive)": "EMA (正)",
"EMA replace steps (positive)": "EMA 替换步数 (正)",
"EMA (nagetive)": "EMA (负)",
"EMA replace steps (nagative)": "EMA 替换步数 (负)",
"beta1": "beta1",
"beta2": "beta2",
"working": "运行中",
"Half Model": "半模型",
"Load Params": "加载参数",
"Cancel": "取消",
"Create Model": "创建模型",
"Train Model": "训练模型",
"Import Model from Huggingface Hub": "从 Huggingface Hub 加载模型",
"Model Path": "模型路径",
"HuggingFace Token": "HuggingFace 令牌",
"Source Checkpoint": "源模型",
"Scheduler": "调度器",
"ddim": "ddim",
"pndm": "pndm",
"lms": "lms",
"Create": "创建",
"Generate Ckpt": "创建模型",
"Training Wizard (Person)": "训练配置器 (人物)",
"Training Wizard (Object/Style)": "训练配置器 (物件/风格)",
"Concepts List (Overrides instance/class settings below)": "概念列表（将取代下面实例/类这两项设置）",
"Use Concepts List": "使用概念列表",
"Concepts List": "概念列表",
"Instance prompt": "实例提示词",
"Uses the image's filename as the image labels instead of the instance prompt": "使用图像的文件名作为图像标签而非实例提示词",
"Uses the filename.txt file's content as the image labels instead of the instance prompt": "使用 文件名.txt 文件的内容作为图像的提示词而非实例提示词",
"Dataset Directory": "数据集目录",
"Class prompt": "类提示词",
"Class Prompt": "类提示词",
"Pretrained VAE Name or Path": "预训练的 VAE 名字或者路径",
"Classification dataset directory (optional).": "分类数据集目录（可选）",
"Classification Dataset Directory": "分类数据集目录",
"Total number of classification images to use. Set to 0 to disable.": "要使用的分类图像总数。设置为 0 以禁用",
"Total Number of Class/Reg Images": "用于分类/规范化的图像总数",
"Classification Image Negative Prompt": "分类图像反向提示词",
"Classification CFG Scale": "分类提示词相关性",
"Classification Steps": "分类迭代步数",
"Training steps": "训练迭代步数",
"Training Steps": "训练迭代步数",
"Batch Size": "每批数量",
"Class Batch Size": "类每批数量",
"Learning rate": "学习率",
"Learning Rate": "学习率",
"Learning Rate Warmup Steps": "学习率的预热步数",
"Resolution": "分辨率",
"Save a checkpoint every N steps, 0 to disable": "每隔 N 步保存一次模型权重进度，设置为 0 以禁用",
"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",
"Preview image prompt": "预览图提示词",
"Preview image negative prompt": "预览图反向提示词",
"Number of samples to generate": "要生成的样本数",
"Sample guidance scale": "样本的指导尺度 - 类似基准 CFG scale 的概念",
"Sample steps": "样本迭代步数",
"Learning Rate Scheduler": "学习率调度器",
"Save Checkpoint Frequency": "保存模型权重进度的频率",
"Save Preview(s) Frequency": "保存预览的频率",
"Sample Image Prompt": "样本图像的提示词",
"Sample Image Negative Prompt": "样本图像的反向提示词",
"Number of Samples to Generate": "要生成的样本数量",
"Sample Seed": "样本种子",
"Sample CFG Scale": "样本提示词相关性",
"Sample Steps": "样本迭代步数",
"Advanced": "高阶",
"Auto-Adjust (WIP)": "自动调整 (施工中)",
"Use CPU Only (SLOW)": "只用 CPU (很慢)",
"Don't cache latents": "不要缓存潜变量",
"Don't Cache Latents": "不要缓存潜变量",
"Train Text Encoder": "训练文本编码器",
"Train EMA": "训练 EMA",
"Use 8bit Adam": "使用 8bit Adam",
"Center Crop": "中心裁切",
"Gradient Checkpointing": "梯度进度记录 - 以时间换显存",
"Scale Learning Rate": "缩放学习率",
"Mixed Precision": "混合精度",
"no": "否",
"fp16": "fp16",
"bf16": "bf16",
"cosine": "余弦",
"cosine_with_restarts": "含重启的余弦",
"polynomial": "多项式",
"constant": "常量",
"constant_with_warmup": "含预热的常量",
"# Training Epochs": "训练多少期",
"Adam Beta 1": "Adam Beta 1",
"Adam Beta 2": "Adam Beta 2",
"Adam Weight Decay": "Adam 权重衰减",
"Adam Epsilon": "Adam Epsilon (替代 0 的常量，防止直接除以 0)",
"Max Grad Norms": "最大梯度范数",
"Grad Accumulation Steps": "梯度累加步数",
"Gradient Accumulation Steps": "梯度累加步数",
"Warmup Steps": "预热步数",
"Pad Tokens": "词元垫齐",
"Max Token Length": "最大词元长度",
"Max Token Length (Requires Pad Tokens for > 75)": "最大词元长度 (词元 > 75 时会进行留空)",
"Apply horizontal Flip": "应用水平翻转",
"Apply Horizontal Flip": "应用水平翻转",
"Use EMA for finetuning": "使用 EMA 进行微调",
"Directories": "目录",
"Cropping": "剪裁",
"Captions": "描述文本",
"Post-Processing": "后处理",
"Crop Images": "剪裁图像",
"Split over-sized images": "分割过大的图像",
"Generate Captions": "生成描述文本",
"Max Caption length (0=unlimited)": "最大描述长度 (0 为无限制)",
"Existing Caption Action": "对已有的描述文本的行为",
"Append Caption to File Name": "把描述文本接在文件名后面",
"Save Caption to .txt File": "储存描述文本为 .txt 文件",
"Append DeepDanbooru to Caption": "把 DeepDanbooru 的结果接在已有的描述文本后面",
"Replace Class with Subject in Caption": "将描述文本中的类替换成主体",
"Subject Class": "主体类别",
"Subject Name": "主体名",
"Restore Faces": "面部修复",
"Face Restore Model": "面部修复模型",
"GFPGAN": "面部修复",
"Codeformer": "Codeformer",
"Upscale and Resize": "放大并调整大小",
"Upscale Ratio": "放大比例",
"Vector": "向量",
"Refresh Embeddings": "刷新 Embeddings",
"Save Embedding": "保存 Embedding",
"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",
"webui-tokenizer": "词元分析器扩展",
"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",
"Generate Preview": "生成预览",
"Favorites": "收藏夹(已保存)",
"Others": "其他",
"@@/^(\\d+) images in this directory, divided into (\\d+) pages$/": "目录中有$1张图片，共$2页",
"@@/^Favorites path from settings: (.*)$/": "设置的收藏夹目录：$1",
"@@/^Page Index (.*)$/": "页码 $1",
"Images directory": "图像目录",
"Dropdown": "下拉列表",
"First Page": "首页",
"Prev Page": "上一页",
"Page Index": "页码",
"Next Page": "下一页",
"End Page": "尾页",
"Current ranking": "当前评分",
"Set ranking to": "设置评分",
"delete next": "删除后 N 张",
"also delete off-screen images": "同时删除未列出的图片",
"Additional Generation Info": "附加生成信息",
"Delete": "删除",
"sort by": "排序方式",
"Sort by": "排序方式",
"keyword": "搜索",
"Filename keyword search": "文件名搜索",
"EXIF keyword search": "EXIF 搜索",
"Ranking filter": "评分过滤",
"Ranking Filter": "评分过滤",
"Aesthestic Score": "美学评分",
"Minimum aesthetic_score": "最低美学评分",
"Maximum aesthetic_score": "最高美学评分",
"Generation Info": "生成信息",
"File Name": "文件名",
"File Time": "文件时间",
"Open Folder": "打开目录",
"Send to buttons": "\"发送到\"按钮",
"Gallery Controls Bar": "图库控制栏",
"Ranking Bar": "评分栏",
"Delete Bar": "删除栏",
"Move to favorites": "移动到收藏夹",
"Renew Page": "刷新页面",
"Number": "数量",
"set_index": "设置索引",
"load_switch": "加载开关",
"turn_page_switch": "翻页开关",
"Checkbox": "勾选框",
"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",
"Text input": "文本输入",
"ID input": "ID 输入",
"Tokenize": "词元拆分",
"Text": "文本",
"Tokens": "词元",
"Video to extract frames from:": "要从中提取帧的视频：",
"Only extract keyframes (recommended)": "只提取关键帧（推荐）",
"Extract every nth frame": "每第 n 帧提取一次",
"Extract Frames": "提取帧",
"Extracted Frame Set": "提取好的帧",
"Resize crops to 512x512": "缩放剪裁至 512x512",
"Outfill method:": "填充方法：",
"Don't outfill": "不进行填充",
"Stretch image": "拉伸图像",
"Transparent": "透明",
"Solid color": "纯色",
"Average image color": "平均图像颜色",
"Dominant image color": "图像主色",
"Stretch pixels at border": "延伸边缘的像素",
"Reflect image around border": "从边缘镜像图像内容",
"Blurred & stretched overlay": "模糊拉伸的叠加层",
"Reuse original image": "复用原图",
"Reset Aspect Ratio": "重置纵横比",
"Bulk process frames with chosen outfill method": "使用选定的填充方法批量处理截取的帧",
"Image border outfill method:": "图像边缘的填充方法：",
"Black outfill": "填黑",
"Outfill border color:": "填充颜色：",
"Blur amount:": "模糊量：",
"Number of clusters:": "簇数：",
"Save crops to:": "储存裁剪好的成品到：",
"<": "<",
">": ">",
"Upscale latent space image when doing hires. fix": "做高清修复时，也放大潜变量",
"Shuffleing tags by ',' when create texts.": "创建文本时打乱以 ',' 分割的 tags",
"Dropout tags when create texts": "创建文本时随机丢弃一些 tags",
"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",
"auto": "自动",
"Hypernetwork strength": "超网络 强度",
"Filter NSFW content": "过滤成人内容(NSFW)（不建议开启）",
"Stop At last layers of CLIP model": "在 CLIP 模型的最后哪一层停下 (Clip skip)",
"Interrogate: use artists from artists.csv": "反推：使用 artists.csv 中的画师",
"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",
"Images Browser": "图库浏览器",
"Preload images at startup": "在启动时预加载图像",
"Number of columns on the page": "每页列数",
"Number of rows on the page": "每页行数",
"Minimum number of pages per load": "每次加载的最小页数",
"Use same seed for all images": "为所有图像使用同一个随机种子",
"Save mask previews": "保存蒙版预览",
"Output directory for mask previews": "蒙版预览的输出目录",
"Save masks": "保存蒙版",
"Output directory for masks": "蒙版输出目录",
"Fixed size to resize images to": "调整图像大小到固定大小",
"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",
"Default cropped image output directory": "裁切后的成品的默认输出目录",
"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）",
"Installing...": "安装中…",
"DreamArtist-sd-webui-extension": "梦作家",
"SD-latent-mirroring": "镜像潜变量",
"a1111-sd-webui-tagcomplete": "Tag自动补全",
"auto-sd-paint-ext": "画图工具扩展",
"ddetailer": "检测细致化",
"deforum-for-automatic1111-webui": "Deforum",
"novelai-2-local-prompt": "novelai 转 webui 括号",
"sd-dynamic-prompts": "动态提示词",
"sd_dreambooth_extension": "dreambooth 扩展",
"sd_smartprocess": "智能预处理",
"seed_travel": "种子变迁",
"shift-attention": "关注转移",
"stable-diffusion-webui-aesthetic-image-scorer": "美术风格评分",
"stable-diffusion-webui-artists-to-study": "画师图库",
"stable-diffusion-webui-auto-tls-https": "自动 tls-https",
"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-localization-zh_TW": "正體中文語言包",
"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",
"stable-diffusion-webui-wildcards": "通配符",
"training-picker": "训练图挑选器",
"unprompted": "非文本（代码化）提示词",
"Add a random artist to the prompt.": "随机添加一个画师到提示词中",
"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🎨 随机添加一个画师到提示词中\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}",
"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",
"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",
"Range of stepped values (min, max, step)": "含步幅的随机范围 (最小, 最大, 步幅)",
"Float value from 0 to 1": "从 0 到 1 的浮点数数值",
"Disable dynamic prompts by unchecking this box.": "取消勾选来禁用动态提示词",
"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.\n\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.": "与随机生成提示词不同，组合生成会从给定的字符串中生成所有可能的提示词\n提示词 “I {love|hate} {New York|Chicago} in {June|July|August}” 将总共生成 12 句提示词变体\n“种子”字段的值仅用于第一张图像。要更改此设置，请在“高级选项”部分中查找“固定种子”\n",
"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",
"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",
"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",
"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",
"Uses the lexica.art API to create random prompts.\nThe prompt in the main prompt box is used as a search string.\nLeaving the prompt box blank returns a list of completely randomly chosen prompts.\nTry it out, it can be quite fun.": "用 lexica.art API 生成随机提示词\n提示词框中的内容会作为搜索字符串\n留空提示词框会得到一组完全随机选择的提示词\n用用看，它会很有趣",
"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",
"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/",
"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",
"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",
"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",
"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",
"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",
"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",
"The name of the model to create.": "要创建的模型的名称",
"Path to classifier ckpt, can be empty": "分类器的路径，可留空",
"Path to JSON file with concepts to train.": "用于训练概念的 JSON 文件路径",
"The model to train.": "要训练的模型",
"Load model paramters from the last training session.": "从上次训练中加载模型参数",
"Generate a checkpoint at the current training lvel.": "生成当前训练级别的模型权重进度",
"Cancel training.": "取消训练",
"Start training.": "开始训练",
"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",
"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",
"Your huggingface token to use for cloning files.": "用于下载文件的 huggingface 令牌",
"The source checkpoint to extract for training.": "用于训练的要提取的源模型",
"Schedule to use for official training stuff.": "选择要用于训练官方东西的调度器",
"Create the danged model already.": "创建一个本就很牛的模型",
"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",
"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",
"Train multiple concepts from a JSON file or string.": "从 JSON 文件或字符串训练多个概念",
"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",
"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",
"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",
"The directory containing training images.": "包含训练图像的目录",
"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",
"The directory containing classification/regularization images.": "包含分类/规范化图像的目录",
"(Optional) Path to directory with classification/regularization images": "（可选）带有分类/规范化图像的目录路径",
"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)'",
"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",
"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",
"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 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 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",
"Leave blank to use base model VAE.": "留空以使用基底模型的 VAE",
"Path to directory with classification images": "分类图像的目录路径",
"how fast should the training go. Low values will take longer to train, high values may fail to converge (not generate accurate results) and/or may break the embedding (This has happened if you see Loss: nan in the training info textbox. If this happens, you need to manually restore your embedding from an older not-broken backup).\n\nYou can set a single numeric value, or multiple learning rates using the syntax:\n\n rate_1:max_steps_1, rate_2:max_steps_2, ...\n\nEG: 0.005:100, 1e-3:1000, 1e-5\n\nWill train with rate of 0.005 for first 100 steps, then 1e-3 until 1000 steps, then 1e-5 for all remaining steps.": "训练应该多快。低值将需要更长的时间来训练，高值可能无法收敛（无法产生准确的结果）以及/也许可能会破坏 Embedding（如果你在训练信息文本框中看到 Loss: nan 就会发生这种情况。如果发生这种情况，你需要从较旧的未损坏的备份手动恢复 Embedding）\n\n你可以使用以下语法设置单个数值或多个学习率：\n\n 率1:步限1, 率2:步限2, ...\n\n如： 0.005:100, 1e-3:1000, 1e-5\n\n即前 100 步将以 0.005 的速率训练，接着直到 1000 步为止以 1e-3 训练，然后剩余所有步以 1e-5 训练",
"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",
"Scale the learning rate by the number of GPUs, gradient accumulation steps, and batch size.": "通过 GPU 数量、梯度累加步数和每批数量来缩放学习率",
"Number of steps for the warmup in the lr scheduler.": "学习率调度器中的预热步数",
"The learning rate scheduler to use.": "要使用的学习率调度器",
"Save a checkpoint every N steps. ": "每 N 步保存一次模型权重进度",
"Generate preview images every N steps.": "每 N 步生成一次预览图像",
"The prompt to use when generating preview images.": "生成预览图像时使用的提示词",
"Leave blank to use instance prompt.": "留空以使用实例提示词",
"A negative prompt to use when generating preview images.": "生成预览图像时使用的反向提示词",
"How many samples to generate per subject.": "每个主体生成多少样本",
"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",
"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",
"Attempt to automatically set training parameters based on total VRAM. Still under development.": "尝试根据总显存自动设置训练参数。仍在开发中",
"How many images to process at once per training step?": "每步训练要处理多少张图像？",
"How many classifier/regularization images to generate at once.": "一次生成多少分类/规范化图像",
"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 显存的 GPU",
"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 以消耗一点显存为代价略微提高速度",
"You probably want this to be 'fp16'.": "如果你想要设置为半精度(fp16)的话",
"When this box is *checked* latents will not be cached. When latents are not cached, you will save a bit of VRAM, but train slightly slower": "当此框被*选中*时，将不会缓存潜变量(latents)。当潜变量没有被缓存时，你会节省一点显存，但训练速度会稍微慢一些",
"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",
"Enable this to save VRAM.": "启用此项以节省显存",
"Set this to 2 to increase speed?": "将此设置为 2 以提高速度？",
"If an image is too large, crop it from the center.": "如果图像太大，裁掉边缘",
"Randomly decide to flip images horizontally.": "随机决定要不要水平翻转图像",
"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",
"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",
"Weight decay for the Adam optimizer, duh.": "Adam 优化器的权重衰减（废话）",
"Max Gradient norms.": "最大梯度范数",
"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",
"Subject class to crop (leave blank to auto-detect)": "要裁剪的主体类别（留空以自动检测）",
"Subject Name to replace class with in captions": "描述文本中要替换类的主体名",
"symbol:color-hex, symbol:color-hex, ...": "文字:颜色代码, 文字:颜色代码, ...",
"e.g. A portrait photo of embedding_name": "示例： A portrait photo of embedding_name",
"Input images directory": "输入图像目录",
"Prompt for tokenization": "给词元化准备的提示词",
"Ids for tokenization (example: 9061, 631, 736)": "用于词元化的 ID (例： 9061, 631, 736)",
"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<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.": "使用以下标签定义如何选择图像的文件名： [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]。默认请留空",
"Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.": "使用以下标签定义如何选择图像和宫格图的子目录： [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]。默认请留空",
"NAIConvert": "NAI 转换",
"History": "历史记录",
"Autocomplete options": "Tag自动补全选项",
"Enable Autocomplete": "启用Tag自动补全",
"Append commas": "附加逗号",
"Action": "操作",
"Aesthetic Gradients": "美术风格梯度",
"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",
"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",
"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",
"tab": "选项卡",
"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，为低显存显卡做了优化",
"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",
"Image browser": "图库浏览器",
"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",
"Inspiration": "灵感",
"Randomly display the pictures of the artist's or artistic genres typical style, more pictures of this artist or genre is displayed after selecting. So you don't have to worry about how hard it is to choose the right style of art when you create.": "随机显示一位画师或某艺术流派的图像，选择后会显示更多该画师或艺术流派的图像。所以你不用担心在创作时难以选择出想要的艺术风格",
"Deforum": "Deforum",
"The official port of Deforum, an extensive script for 2D and 3D animations, supporting keyframable sequences, dynamic math parameters (even inside the prompts), dynamic masking, depth estimation and warping.": "Deforum 的官方移植，一个用于 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",
"Artists to study": "画师图库",
"Shows a gallery of generated pictures by artists separated into categories.": "将画师按类别划分，并显示其生成出来的图像",
"Aesthetic Image Scorer": "美术风格评分",
"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",
"Dataset Tag Editor": "数据集标签编辑器",
"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",
"Krita Plugin.": "Krita 插件",
"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",
"Unprompted": "非文本（代码化）提示词",
"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",
"Booru tag autocompletion": "Booru 标签自动补全",
"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）的标签自动补完。使用本地标签 CSV 文件，并包含可用于自定义配置的文件",
"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",
"tokenizer": "词元分析器",
"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",
"Latent Mirroring": "镜像潜变量",
"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",
"Embeddings editor": "Embeddings 编辑器",
"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",
"seed travel": "种子变迁",
"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",
"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",
"Detection Detailer": "检测细致化",
"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",
"prompt travel": "提示词变迁",
"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",
"conditioning-highres-fix": "高清修复原图调节",
"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",
"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",
"Auto TLS-HTTPS": "自动 TLS-HTTPS",
"Allows you to easily, or even completely automatically start using HTTPS.": "让你可以很简单地自动配置HTTPS",
"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",
"zh_CN Localization": "简体中文语言包",
"Simplified Chinese localization": "简体中文本地化",
"zh_TW Localization": "正體中文語言包",
"Traditional Chinese localization": "正體中文本地化",
"old localizations": "过时的语言包",
"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",
"latest": "最新",
"behind": "落后",
"Error": "错误",
"Connection errored out.": "连接出错",
"Roll three": "抽三位出来",
"Generate forever": "无限生成",
"Cancel generate forever": "停止无限生成",
"Move VAE and CLIP to RAM when training hypernetwork. Saves VRAM.": "训练超网络时将 VAE 和 CLIP 从显存移放到内存，节省显存",
"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",
"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，用图生图改进每个图块，最后将整个图像合并回来",
"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 grid(s) 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",
"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",
"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",
"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",
"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",
"Process an image, use it as an input, repeat.": "处理一张图像，将其作为输入，并重复",
"Insert selected styles into prompt fields": "在提示词中插入选定的模版风格",
"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}",
"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）作为模型名称。建议用在Y轴上以减少过程中模型的切换",
"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使用的显存峰值，不包括缓存的数据。\nTorch reserved： Torch 分配的显存的峰值量，包括所有活动和缓存数据。\nSys VRAM： 所有应用程序分配的显存的峰值量 / GPU 的总显存（峰值利用率%）",
"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",
"Start drawing": "开始绘制",
"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）",
"----not work----": "----以下内容无法被翻译，Bug----",
"Upscaler 1": "放大算法 1",
"Upscaler 2": "放大算法 2",
"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）",
"Allowed categories for random artists selection when using the Roll button": "使用抽选画师按钮时将会随机的画师类别",
"Face restoration model": "选择面部修复模型",
"----deprecated----": "----以下内容在webUI新版本已移除----",
"Show Textbox": "显示文本框",
"File with inputs": "含输入内容的文件",
"Prompts": "提示词",
"Open output directory": "打开输出目录",
"Create aesthetic images embedding": "创建美术风格图集 Embedding",
"Split oversized images into two": "将过大的图像分为两份",
"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",
"txt2img history": "文生图历史记录",
"img2img history": "图生图历史记录",
"extras history": "附加功能选项卡的历史记录",
"extras": "附加功能",
"custom fold": "自定义文件夹",
"Load": "加载",
"Prev batch": "上一批",
"Next batch": "下一批",
"number of images to delete consecutively next": "接下来要连续删除的图像数",
"Date to": "日期至",
"Refresh page": "刷新页面",
"Unload VAE and CLIP from VRAM when training": "训练时从显存中取消 VAE 和 CLIP 的加载",
"Number of pictures displayed on each page": "每页显示的图像数量",
"Number of grids in each row": "每行显示多少格",
"favorites": "收藏夹(已保存)",
"others": "其他",
"Collect": "收藏(保存)",
"Select activation function of hypernetwork": "选择超网络的激活函数",
"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",
"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",
"Provide Simplified Chinese localization for the WebUI": "提供简体中文本地化翻译",
"Prior Loss Weight": "先验损失权重",
"Steps between prompts": "每个提示词之间的迭代步伐",
"Enable Randomize extension": "启用随机化扩展",
"Randomize Sampler": "随机化 采样器",
"Randomize CFG Scale": "随机化 提示词相关性",
"Randomize Steps": "随机化 采样迭代步数",
"Randomize Width": "随机化 宽度",
"Randomize Height": "随机化 高度",
"Randomize Highres. percentage": "随机化 启用高清修复的几率",
"Randomize Highres. Denoising Strength": "随机化 高清修复的重绘幅度",
"Randomize Highres. Width": "随机化 高清修复的第一遍的宽度",
"Randomize Highres. Height": "随机化 高清修复的第一遍的高度",
"Randomize CLIP skip": "随机化 在 CLIP 模型的最后哪一层停下 (Clip skip)",
"sd-dynamic-prompting": "动态提示词",
"similar": "相似",
"different": "差异",
"Loss for latent match (grad mode)": "匹配潜变量损失 (梯度模式)",
"Loss for cond match (grad mode)": "匹配文字调节损失 (梯度模式)",
"Instance prompt(Optional)": "实例提示词 (可选)",
"--------": "---------",
"Toggle zoomed view": "切换放大视图",
"Preview tiling": "预览平铺",
"Save Image(s)": "保存图像",
"Close image viewer": "关闭图像查看器",
"(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",
"(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",
": Original extension": "：原始文件的后缀（不含 . ）",
": Original extension\nAvailable algorithms:": "：原始文件哈希，<algorithms>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 . ）",
"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",
"Add": "添加",
"Add Background image": "添加背景图片",
"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/Remove...": "编辑预设",
"Additional tags (split by comma)": "附加标签(逗号分隔)",
"Aesthetic scorer": "美学评分器",
"All": "全部",
"Allow overwrite output-model": "允许输出模型覆盖同名文件",
"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",
"Apply block weight from text": "将手动输入的权重应用于滑动条",
"Artist Tags": "画师标签",
"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）",
"Batch from directory": "批量操作",
"Both": "全部",
"CLiP model": "CLiP模型",
"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",
"Character Tags": "角色标签",
"Checkpoint Format": "模型格式",
"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",
"Close the video": "关掉视频",
"Config Presets": "预设配置",
"Config-Presets": "预设配置",
"Converted checkpoints will be saved in your": "转化换后的模型将会保存在",
"Copyright Tags": "版权标签",
"Cross-attention": "Xattn优化方案",
"Current Booru": "当前的 Booru",
"Custom settings file": "自定义设置文件",
"Detect from image": "从图片探测",
"Directory path": "目标路径",
"Embeddings: loaded": "嵌入式:已加载",
"Embeddings: skipped": "嵌入式:已跳过",
"Enable Dynamic Thresholding (CFG Scale Fix)": "启用动态阈值(提示词相关性修复 - CFG Scale Fix)",
"Enable pixelization": "启用像素化",
"Enabled": "启用",
"Escape brackets": "转义括号(防止误识别为权重信息，推荐勾选)",
"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)",
"For": "用于",
"Force Reset": "强制重置",
"Found tags": "找到的标签",
"Gelbooru Prompt": "Gelbooru标签自动摘录",
"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)",
"Hypernetwork strengths": "超网络强度",
"Hypernetworks List": "可选的超网络列表",
"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",
"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",
"Image Tags": "图像标签",
"Image with MD5 Hash": "以MD5哈希值命名的图片文件",
"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",
"Info object": "全部信息",
"Init": "初始",
"Interpolation": "插值",
"Interrogate": "开始反推",
"Interrogator": "反推算法",
"Keep empty if dont use.": "不使用请留空",
"Keep resolution": "保持分辨率不变",
"Keyframes": "关键帧",
"Leave blank to save images to the same path.": "留空则输出到输入目录下",
"Leave blank to use same filename as original.": "留空以使用与原始文件相同的文件名",
"License: MIT": "许可: MIT",
"Link to image page": "链接到图片页面",
"List-Up checkpoints": "列出模型",
"Load Settings": "加载设定",
"Load Video Settings": "加载视频设置",
"Load from JSON": "从 JSON文件 加载",
"Detect from Image": "从图像中检测",
"Add Background Image": "添加背景图像",
"Presets": "预设",
"Load Preset": "加载预设",
"Save Preset": "保存预设",
"M00": "中间层",
"MBW": "分块设置权重",
"MBW Each": "AB模型分别分块设置权重",
"M_A_00": "模型A 中间层",
"M_B_00": "模型B 中间层",
"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",
"Memory": "内存及显存用量",
"Memory Attention": "内存注意",
"Memory optimization": "显存优化选项",
"Merge Block Weighted": "模型合并(分块加权)",
"Merge Board": "合并面板",
"Meta Tags": "属性标签",
"Mimic CFG Scale": "模拟提示词相关性",
"Model A": "模型A",
"Model B": "模型B",
"Model Converter": "模型格式转换",
"Model_A": "模型A",
"Model_B": "模型B",
"Models": "模型",
"Models...": "模型列表",
"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 to directory": "将图片移动到目标路径",
"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 Merge": "多重合并",
"Multi Model Merge": "多重模型合并",
"Multi Proc Cmd": "多进程命令",
"Multiple Hypernetworks": "加载多个超网络",
"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",
"No": "否",
"Number of columns on image gallery": "图库显示图像列数",
"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",
"Only": "仅检索反向提示词",
"Open...": "打开...",
"OpenPose Editor": "OpenPose 编辑器",
"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",
"Output Model Name": "输出模型文件名",
"Output filename format": "输出文件名格式",
"Output filename formats": "输出文件名格式说明",
"Page Number": "页数",
"Parse Recipe": "剖析配方",
"Parse Result": "剖析结果",
"Pixel size": "像素块大小",
"Platform": "运行平台",
"Positive \"filewords\" only": "只限正向 \"filewords\"",
"Precision": "精度",
"Preset": "预设",
"Preset Weights": "预设权重",
"Preset_Weights": "预设权重",
"Previous Page": "前一页",
"Print debug logs to the console": "将调试日志输出到控制台",
"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",
"Pruning Methods": "压缩方案",
"Put weight sets. float number x 25": "输入权重，共25个浮点数，逗号分隔",
"Rating confidents": "分级信息置信度",
"Recipe": "配方",
"Refresh data": "刷新数据",
"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",
"Reload checkpoint": "刷新模型列表",
"Remove results with the \"animated\" tag": "删除带有\"animated\"(动图)标签的结果",
"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'_'",
"Reset": "清空画面",
"Reset recipe text area": "重置配方文本区域",
"Reset vars": "重置变量",
"Run Merge": "开始合并",
"Save & Restart": "保存并重启",
"Save JSON": "储存为 JSON文件",
"Save PNG": "保存为 PNG图片",
"Save Settings": "储存设置",
"Save Video Settings": "保存视频设置",
"Save as half": "以 float16 保存",
"Save as safetensors": "存为safetensors格式",
"Save with JSON": "保存JSON文件",
"Saved directories": "已保存的路径",
"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）",
"Search": "搜索",
"Search Booru": "搜 Booru",
"Search Results": "搜寻结果",
"Search negative prompt": "检索范围是否包含反向提示词",
"case sensitive": "区分大小写",
"regex - e.g. ^(?!.*Hires).*$": "使用正则表达式，如^(?!.*Hires).*$",
"Search string": "搜字串",
"Select": "选择",
"Select Image": "选择图像",
"Send image to tag selection": ">> 标签选择",
"Send interrupt": "发送中断指令",
"Send to Multi-Merge": ">> 多重合并",
"Send to Recipe": ">> 配方",
"Server start time": "服务器启动时间",
"Show extra options": "显示额外设置",
"Single process": "单张图片",
"Skip/Reset CLIP position_ids": "跳过或重置CLIP position_ids键值",
"Sort by alphabetical order": "按首字母排序 (不推荐勾选)",
"State": "运行状态",
"StylePile": "风格加码",
"System Info": "系统信息",
"System data": "系统信息",
"Tag confidents": "标签置信度",
"Tagger": "Tag反推",
"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 your models list.": "这是您的模型列表",
"Threshold": "阈值",
"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)",
"Upscale": "图像放大",
"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 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",
"Username": "用户名",
"Video Input": "视频输入",
"Visualize Cross-Attention": "Cross-Attention 可视化",
"WD 1.4 Tagger": "WD 1.4 标签器",
"Weight values": "权重值",
"Weight_values": "权重值(手动输入)",
"Write all generated prompts to a file": "将所有生成的提示词写入文件",
"Yes": "是",
"You can try it by own, to dig more deeper into Abyss ...": "可自行探索，以窥深渊",
"[hash:<algorithms>]": "[hash:<算法>]",
"aesthetic_score": "美学评分",
"all": "全部",
"base_alpha": "文本编码器比例",
"booru2prompt": "booru转提示词",
"border": "边框",
"by AUTOMATIC1111": "来自 AUTOMATIC1111",
"cfg scale": "提示词相关性",
"config": "配置",
"convert": "转换",
"default": "默认",
"delete": "删除",
"depthmap2mask": "深度图转蒙版",
"display_samples": "显示样本",
"ema-only": "仅保留ema权重",
"exif keyword": "搜索生成信息关键字（按回车开始检索）",
"extension by": "扩展来自",
"filename": "文件名",
"filename keyword": "搜索文件名关键字（按回车开始检索）",
"fixed": "固定",
"frappe": "冰沙（深色-亮）",
"hash": "哈希",
"height": "高度",
"img2img-grids": "宫格图(i2i)",
"iter": "迭代器",
"latte": "拿铁（浅色）",
"macchiato": "玛奇朵（深色）",
"max_frames": "最大帧数",
"minimum aesthetic_score": "美学评分下限",
"maximum aesthetic_score": "美学评分上限",
"mocha": "mocha/摩卡（深色-暗）",
"model": "模型",
"model hash": "模型哈希值",
"model_name": "模型名",
"multi-subject-render": "多主体渲染器",
"no-ema": "舍弃ema权重",
"openpose-editor": "OpenPose 编辑器插件",
"or to CTRL+SHIFT": "将 CTRL 绑定更改为 CTRL+SHIFT",
"ranking": "评分",
"ranking filter": "按图片评分筛选",
"sampler": "采样方法",
"save_samples": "储存样本",
"save_settings": "储存设定",
"schedule": "调度",
"sd-extension-aesthetic-scorer": "美学评分插件",
"sd-extension-system-info": "系统信息面板",
"sd-webui-additional-networks": "可选附加网络",
"sd-webui-controlnet": "扩散控制网络",
"sd-webui-gelbooru-prompt": "Gelbooru标签自动摘录插件",
"sd-webui-model-converter": "模型格式转换插件",
"sd-webui-multiple-hypernetworks": "复数超网络加载",
"sdweb-merge-block-weighted-gui": "分块加权模型合并插件",
"sdweb-merge-board": "合并面板",
"seed": "随机种子",
"seed_schedule": "种子调度",
"size": "大小",
"stable-diffusion-webui-pixelization": "像素化插件",
"stable-diffusion-webui-wd14-tagger": "Waifu Diffusion 1.4 标签器",
"steps": "采样迭代步数",
"strength": "强度",
"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",
"txt2img-grids": "宫格图(t2i)",
"verbose console output": "将详细信息输出到控制台",
"width": "宽度",
"* change 'type' to clear/reload dropdowns.": "改变坐标轴类型可清空、刷新选项",
"/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",
"API Keys": "API 密钥",
"Action on exiting caption": "对退出符的响应方式",
"Animation settings": "动画设定",
"Batch settings": "批次设定",
"Canny high threshold": "强边缘判断阈值",
"Canny low threshold": "弱边缘判断阈值",
"Checkpoint Dropdown": "模型列表",
"Class Token + Description": "类的词元 + 描述",
"Class token(s) to swap, can be comma-separated": "要互换的类的词元，可以是以英文逗号分割的",
"Coherence:": "相干性:",
"ControlNet - 0": "扩散控制网络 - 0",
"ControlNet - 1": "扩散控制网络 - 1",
"ControlNet - 2": "扩散控制网络 - 2",
"ControlNet - 3": "扩散控制网络 - 3",
"ControlNet - 4": "扩散控制网络 - 4",
"ControlNet - 5": "扩散控制网络 - 5",
"ControlNet - 6": "扩散控制网络 - 6",
"ControlNet - 7": "扩散控制网络 - 7",
"ControlNet - 8": "扩散控制网络 - 8",
"ControlNet - 9": "扩散控制网络 - 9",
"Copy Metdata": "开始复制元数据",
"Copy image to: ": "将图片发送到:",
"Send to txt2img ControlNet": ">> 文生图的扩散控制网络",
"Send to img2img ControlNet": ">> 图生图的扩散控制网络",
"Copy to directory": "将图片复制到目标路径",
"Copy to favorites": "复制到收藏夹",
"Deforum-webui (use tab extension instead!)": "Deforum-webui (请使用选项卡上的扩展版本)",
"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",
"Draw Legends": "输出坐标轴名字",
"Enable extras": "打开 ▼",
"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",
"Flatfile": "纯文字文件",
"Generate a checkpoint at the current training level.": "生成当前训练级别的模型权重进度",
"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",
"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)",
"H": "高",
"HED Resolution": "HED 分辨率",
"Half": "一半",
"Hough Resolution": "霍夫分辨率",
"Hough distance threshold (MLSD)": "霍夫距离阈值（MLSD）",
"Hough value threshold (MLSD)": "霍夫值阈值（MLSD）",
"Import settings from file": "从文件导入设置",
"Info and links": "资讯和链接",
"Instance Token + Class Token + Description": "实例的词元 + 类的词元 + 描述",
"Instance Token + Description": "实例的词元 + 描述",
"Instance token to swap": "要互换的实例的词元",
"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",
"LeReS Resolution": "LeReS 分辨率",
"Low VRAM (8GB or below)": "低显存（8GB以下）模式（需配合启动参数\"--lowvram\"）",
"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",
"Mask source": "蒙版来源",
"Math keyframing explanation docs.google.com/document/d/1pfW1PwbDIuW0cv-dnuyYj1UzPqe23BlSLTJsqazffXM/edit?usp=sharing": "数学关键帧 解释 docs.google.com/document/d/1pfW1PwbDIuW0cv-dnuyYj1UzPqe23BlSLTJsqazffXM/edit?usp=sharing",
"Midas Resolution": "MiDaS 分辨率",
"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：",
"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",
"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 background threshold": "背景识别阈值",
"Open drawing canvas!": "创建绘图画布（使用手绘草稿而非上传的图片）",
"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",
"Path relative to the webui folder": "webui文件夹的相对路径",
"Prespective flip — Low VRAM pseudo-3D mode:": "透视翻转 — 低显存伪3D模式:",
"Record accessable images directories": "在 \"其他\" 标签下记录访问过的目录",
"Reloading...": "正在重新加载...",
"Remove Background %": "背景排除（%）",
"Remove Near %": "近景排除（%）",
"Restore Checkpoint after process": "完成后恢复开始前选择的模型",
"Run settings": "运行设置",
"Sampling settings": "采样设置",
"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）",
"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）",
"Send to ControlNet": "发送到 ControlNet",
"Show Ad": "显示广告",
"Show only favorite Axis Option": "仅显示常用坐标轴类型",
"Sort models by": "排序方式",
"Start from Axis": "优先遍历的坐标轴",
"Subject Name to replace class with in cations": "描述文本中要替换类的主体名",
"Swap axes": "交换XY轴",
"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",
"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 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",
"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”",
"Training Epochs": "训练多少期",
"Update instructions:": "更新指引：",
"Useful for I'm feeling lucky and Magic Prompt. If this is set, then negative prompts are not generated.": "对手气不错和魔法提示词很有用。如果设置了此项，则不会生成否定提示",
"User guide for v0.5 docs.google.com/document/d/1pEobUknMFMkn8F5TMsv8qRzamXX_75BShMMXV8IFslI/edit": "v0.5 用户指南 docs.google.com/document/d/1pEobUknMFMkn8F5TMsv8qRzamXX_75BShMMXV8IFslI/edit",
"Uses a trained model file, produces WD 1.4 Tags. Model link - https://mega.nz/file/ptA2jSSB#G4INKHQG2x2pGAVQBn-yd_U5dMgevGF8YYM9CR_R1SY": "使用经过训练的模型文件，生成 Waifu Diffusion 1.4 标签。模型链接 - https://mega.nz/file/ptA2jSSB#G4INKHQG2x2pGAVQBn-yd_U5dMgevGF8YYM9CR_R1SY",
"Video output": "视频输出",
"View the wiki for usage tips.": "点击查看wiki，获取使用说明",
"W": "宽",
"X/Y Plus-1.4.2": "X/Y图表 Plus",
"`animation_mode: None` batches on list of *prompts*. (Batch mode disabled atm, only animation_prompts are working)": "`animation_mode: None` *提示词*列表中的批次。 （批处理模式暂时禁用，只有 animation_prompts 有效）",
"animation_mode": "动画模式",
"batch_name": "批次名称",
"explicit": "色情/露骨内容",
"extension by bbc_mc": "由bbc_mc编写",
"file not found: None": "未检索到模型",
"filename_format": "文件名格式",
"general": "大众级/普通内容",
"grid_rows": "宫格行数",
"is experimental functions and NO PROOF of effectiveness.": " 为实验性功能，不保证有效性",
"make_grid": "制作宫格",
"midas": "MiDaS 深度信息估算",
"n_batch": "批次",
"override_these_with_webui": "用 webui 覆写这些",
"questionable": "强烈性暗示/可疑内容",
"resize: from": "从 ",
"save_sample_per_step": "每步都储存样本",
"sdweb-xyplus": "X/Y图表 Plus 插件",
"seed_behavior": "随机种子行为",
"sensitive": "轻微性暗示/敏感内容",
"show_sample_per_step": "每步都显示样本",
"subseed": "差异随机种子",
"subseed_strength": "差异随机种子强度",
"-------------": "-------------",
"Bilingual Localization": "双语对照翻译",
"Enable Bilingual Localization": "启用双语对照翻译插件",
"Localization file (Please leave `User interface` - `Localization` as None)": "本地化文件（请将 `User interface` -`Localization` 保留为 None）",
"Translation display order": "翻译显示顺序",
"Translation First": "译文在前",
"Original First": "原文在前",
"Enable Devtools Log": "打印控制台日志",
"Bilingual translation, no need to worry about how to find the original button. Compatible with language pack extensions, no need to re-import.": "双语对照翻译插件，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",
"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。",
"Apply": "应用",
"Composable LoRA": "可自组 LoRA",
"Composable Lora": "可自组 LoRA",
"Divisions": "分割",
"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。",
"Extra generation params": "从生成参数的文本提取潜空间分区参数",
"Latent Couple": "潜变量成对",
"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.": "启用的选项卡列表，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）",
"Select components to hide": "选择要隐藏的组件",
"Scan Exif-/.txt-data (initially slower, but required for many features to work)": "扫描 Exif-/.txt-数据（初次会较慢，但许多功能需要此项开启才可以正常工作）",
"Use optimized images in the thumbnail interface (significantly reduces the amount of data transferred)": "在缩略图界面中使用优化的图片尺寸（显著减少传输的数据量）",
"Size of the thumbnails (px)": "缩略图大小（像素）",
"Localization dirs": "本地化文件目录",
"Positions": "位置",
"Regions": "分区",
"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。",
"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）",
"Visualize": "预览",
"Weights": "权重",
"end at this step": "迭代止步于",
"sd-webui-bilingual-localization": "双语对照翻译插件",
"stable-diffusion-webui-composable-lora": "可自组 LoRA",
"stable-diffusion-webui-two-shot": "潜变量成对(双人特写)",
"Control Model - 0": "控制模型-0",
"Control Model - 1": "控制模型-1",
"Control Model - 2": "控制模型-2",
"Control Model - 3": "控制模型-3",
"Control Model - 4": "控制模型-4",
"Control Model - 5": "控制模型-5",
"Control Model - 6": "控制模型-6",
"Control Model - 7": "控制模型-7",
"Control Model - 8": "控制模型-8",
"Control Model - 9": "控制模型-9",
"Activate Selected Script": "激活所选的脚本",
"Allow NSFW": "允许成人内容",
"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 Logo": "应用 Logo",
"Apply Style": "应用风格",
"Apply changes (Reload UI)": "应用设置（重启 WebUI）",
"Apply to": "应用于",
"Background": "背景图片",
"Cardssize": "卡片尺寸（附加网络面板）",
"ControlNet-M2M": "ControlNet-视频转绘",
"Custom Theme.": "自定义主题",
"Deactivate Selected Script": "停用所选脚本",
"Decoder Tile Size": "解码器图块尺寸(Decoder Tile Size)",
"Depth Maps": "深度图",
"Downscaling": "缩小",
"Drop Video Here": "拖拽视频到此处",
"Duration": "持续时间",
"Effects (on until refresh)": "效果（重启后开启）",
"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 Maintenance tab": "启用 维护 选项卡",
"Enable MultiDiffusion": "启用 MultiDiffusion",
"Encoder Tile Size": "编码器图块尺寸",
"Fast Mode": "快速模式",
"Favicon": "网页图标",
"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）",
"Guidance End (T)": "引导退出时机(T)",
"Guidance Start (T)": "引导介入时机(T)",
"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。",
"Image height": "图像高度",
"Image width": "图像宽度",
"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）",
"Keep input image size": "保持输入图像尺寸",
"Kitchen Theme": "Kitchen 主题",
"LLuL": "潜变量局部放大器",
"Latent tile batch size": "潜变量分块批处理规模",
"Latent tile height": "潜变量分块高度",
"Latent tile overlap": "潜变量分块重叠",
"Latent tile width": "潜变量分块宽度",
"Lerp": "线性插值",
"Load results": "加载结果",
"Maintenance": "维护",
"Max Batch Count": "最大批次数量",
"Max Image Size": "最大图像尺寸",
"Move VAE to GPU": "将 VAE 移放到 GPU",
"Move completion popup together with text cursor": "补全弹窗随文本光标一起移动（建议开启）",
"MultiDiffusion with Tiled VAE": "MultiDiffusion 与 分块 VAE",
"Multiplication (2^N)": "放大指数 (2^N)",
"NSFW": "成人内容",
"NSFW checker": "成人内容检测器",
"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",
"Opacity": "透明度",
"Overwrite image size": "覆写图像尺寸设置",
"Please use smaller tile size when see CUDA error: out of memory.": "当显存溢出时，请调小图块尺寸",
"Plot": "绘表",
"Posex": "3D OpenPose 编辑器",
"Refresh List": "刷新列表",
"Remove": "移除",
"Remove Stylesheet": "移除 风格样式表",
"Replaces NSFW images with black.": "将含有成人内容的图像以纯黑图替换",
"Reset Tile Size": "重设图块尺寸",
"Run benchmark": "跑分",
"SLerp": "球面线性插值",
"Seamless Image Fusion, along with vram efficient tiled vae script.": "无缝图像融合，配合显存优化过的 分块 VAE 脚本",
"Selected": "已选择的",
"Send this image to ControlNet.": "将此图像发送到 ControlNet",
"Send to": "发送到",
"Some instructions": "一些操作说明",
"Start steps": "起始迭代步数",
"Target ControlNet number": "接收此图像的 ControlNet 编号",
"Theme": "主题",
"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 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'~~",
"Tiled VAE": "分块 VAE",
"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\"'",
"VRAM Estimator": "显存评估",
"Estimated VRAM usage:": "显存估计用量：",
"@@/^\\((\\d+\\.?\\d*) MB system \\+ (\\d+\\.?\\d*) MB used\\)$/": "$1MB 系统 + $2MB 占用",
"Video": "视频",
"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",
"a1111-sd-webui-locon": "LoCon 插件",
"a1111-stable-diffusion-webui-vram-estimator": "显存评估插件",
"controlnet m2m": "ControlNet-视频转绘",
"dropdown": "下拉菜单",
"interpolation method": "插值算法",
"multidiffusion-upscaler-for-automatic1111": "MultiDiffusion 放大器",
"posex": "3D OpenPose 编辑器插件",
"sd-web-ui-kitchen-theme": "Kitchen 主题",
"sd-webui-llul": "潜变量局部放大器",
"🔄 All Reset": "全部重置",
"🎥 Reset Camera": "重置镜头",
"🧍 Reset Pose": "重置姿势",
"- Background": "背景参考图",
"🖼 Set": "设置",
"❌ Del": "移除",
"- Body": "人体模型",
"➕ Add": "新增",
"➖ Remove": "移除",
"- Camera": "镜头",
"- Canvas Size": "画布大小",
"- Joints and Limbs": "关节和肢体",
"- Others": "其他设置",
"📋 Copy to clipboard": "复制到剪贴板",
"💾 Download image": "下载图片",
"💾🧍 Save Pose": "保存姿势",
"Add background image": "添加背景图片",
"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Civitai网页确认Civitai是否崩溃，Civitai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",
"Civitai Helper": "Civitai助手",
"Civitai Helper's extension tab": "Civitai助手插件选项卡",
"replace preview image with currently selected in gallery": "将预览图替换为当前在图库中选择的图像",
"Open this model's civitai url": "打开这个模型的Civitai发布页面",
"Add trigger words to prompt": "向prompt中添加此模型的触发词",
"Use prompt from preview image": "使用预览图像中的提示词",
"Copy to clipboard": "复制到剪贴板",
"Del": "删除",
"Depth Library": "深度图编辑器",
"Download image": "下载图片",
"Elliptic Limbs": "椭圆形肢体",
"Fixed Roll": "滚转修复",
"Hands": "手部",
"Laters": "层",
"Limb Width": "肢体粗细",
"Low fps": "低帧率模式",
"Memory Optimised SHA256": "SHA256哈希值 计算时优化内存用量",
"Pages: ": "页码：",
"Refresh Civitai Helper": "刷新Civitai助手",
"Remove background image": "移除背景图片",
"Remove selected": "移除已选中的",
"Reset Camera": "重置镜头",
"Reset Pose": "重置动作",
"SKip NSFW Preview images": "跳过成人内容预览图",
"Save Pose": "保存动作",
"Save ranking in image's pnginfo": "将分级保存到 PNG 文件信息",
"Scan model": "扫描模型",
"Set": "设为",
"Shapes": "图形",
"Stable-Diffusion-Webui-Civitai-Helper": "Civitai助手",
"binary": "二值",
"clip_vision": "风格转移",
"color": "色彩",
"sd-webui-depth-lib": "深度图编辑器插件",
"Snapshot to Resume": "从快照中恢复",
"Lora Model": "LoRA 模型",
"Loaded Model:": "当前模型:",
"Model Revision:": "模型修正:",
"Model Epoch:": "模型训练期数:",
"V2 Model:": "V2 模型:",
"Has EMA:": "包含 EMA:",
"Source Checkpoint:": "原始ckpt模型:",
"Scheduler:": "调度器:",
"Input": "输入",
"Concepts": "概念",
"Saving": "保存",
"Testing": "测试",
"Create From Hub": "从huggingface创建",
"512x Model": "512x 模型",
"Extract EMA Weights": "提取EMA权重",
"Unfreeze Model": "解冻模型",
"Performance Wizard (WIP)": "性能向导 (WIP)",
"Basic": "基本配置",
"General": "一般",
"Use LORA": "使用 LoRA",
"Use Lora Extended": "使用 LoRA 扩展(需要安装Locon扩展)",
"Train Imagic Only": "仅意象训练",
"Train Inpainting Model": "训练局部重绘模型",
"Generate Classification Images Using txt2img": "使用 txt2img 生成分类图",
"Intervals": "训练周期/间隔",
"Training Steps Per Image (Epochs)": "每张图片的训练步数（训练期数）",
"Pause After N Epochs": "N阶段后暂停",
"Amount of time to pause between Epochs (s)": "每训练期数之间暂停的时间（秒）",
"Save Model Frequency (Epochs)": "保存模型频率（训练期数）",
"Save Preview(s) Frequency (Epochs)": "保存预览频率（训练期数）",
"Batching": "批次",
"Set Gradients to None When Zeroing": "当梯度设置为0的时候设置为无",
"Min Learning Rate": "最小学习率",
"Number of Hard Resets": "硬重置數量",
"Constant/Linear Starting Factor": "常数/线性起始因子",
"Polynomial Power": "多项式功率",
"Scale Position": "比例位置",
"Lora UNET Learning Rate": "Lora UNET学习率",
"Lora Text Encoder Learning Rate": "Lora Text Encoder学习率",
"Image Processing": "图像处理",
"Max Resolution": "最高分辨率",
"Optimizer": "优化器",
"Sanity Sample Prompt": "样本提示词",
"Sanity Sample Negative Prompt": "样本反向提示词",
"Sanity Sample Seed": "样本种子",
"Miscellaneous": "杂项",
"Discord Webhook": "Discord Webhook",
"Save and Test Webhook": "保存和测试Webhook",
"Tuning": "调整",
"Use EMA": "使用EMA",
"Cache Latents": "缓存潜变量",
"Train UNET": "训练 UNET",
"Step Ratio of Text Encoder Training": "文本编码器训练步骤比率",
"Freeze CLIP Normalization Layers": "冻结 CLIP 归一化层",
"Clip Skip": "Clip 跳過",
"AdamW Weight Decay": "AdamW 权重衰減",
"Shuffle Tags": "打乱标签",
"Prior Loss": "先验损失",
"Scale Prior Loss": "缩放先验损失",
"Prior Loss Target": "先验损失目標",
"Minimum Prior Loss Weight": "最小先验损失权重",
"Concept 1": "概念1",
"Concept 2": "概念2",
"Concept 3": "概念3",
"Concept 4": "概念4",
"Filewords": "风格/物品名称",
"Instance Token": "实例名称",
"Class Token": "分类名称",
"Instance Prompt": "实例提词",
"Strict Tokens": "严格的提示词",
"Sample Prompt Template File": "样本提示词文件",
"Sample Negative Prompt": "样本反向提示词",
"Image Generation": "图像生成",
"Class Images Per Instance Image": "每个实例图片的分类图片数量",
"Custom Model Name": "自定义模型名称",
"Save in .safetensors format": "以 .safetensors 格式保存",
"Save Checkpoint to Subdirectory": "保存ckpt模型到子目录",
"Generate a .ckpt file when saving during training.": "在训练期间保存时生成 .ckpt 文件。",
"Generate a .ckpt file when training completes.": "在训练完成时生成 .ckpt 文件。",
"Generate a .ckpt file when training is canceled.": "在训练取消时生成 .ckpt 文件。",
"Lora UNET Rank": "Lora UNET等级",
"Lora Text Encoder Rank": "Lora Text Encoder等级",
"Lora Weight": "Lora 权重",
"Lora Text Weight": "Lora 文本权重",
"Generate lora weights when saving during training.": "在训练期间保存时生成 lora。",
"Generate lora weights when training completes.": "在训练完成时生成 lora。",
"Generate lora weights when training is canceled.": "在训练取消时生成 lora。",
"Diffusion Weights": "扩散权重",
"Save separate diffusers snapshots when saving during training.": "在训练期间保存独立的模型。",
"Save separate diffusers snapshots when training completes.": "训练完成后保存独立的模型。",
"Save separate diffusers snapshots when training is canceled.": "當训练被取消时保存独立的模型。",
"Generate Class Images": "生成分类图片",
"Preview Prompts": "预览提示词",
"Generate Graph": "生成图形",
"Graph Smoothing Steps": "图形平滑步骤",
"Debug Buckets": "调试",
"Epochs to Simulate": "要模拟的训练期数",
"Batch Size to Simulate": "模拟的批量大小",
"Generate Sample Images": "生成样本图像",
"Sample Prompt": "样本提示词",
"Sample Prompt File": "样本提示文件",
"Sample Width": "样本宽度",
"Sample Height": "样本高度",
"Sample Batch Size": "样本批次大小",
"Output": "输出",
"A generic prompt used to generate a sample image to verify model fidelity.": "生成样本图像用于验证模型保真度的通用提示。",
"When using [filewords], this is the subject to use when building prompts.": "使用 [filewords] 时，构建提示词时使用的主题。",
"When using [filewords], this is the class to use when building prompts.": "使用 [filewords] 时，构建提示词时使用的分类。",
"Leave blank to use instance prompt. Optionally use [filewords] to base sample captions on instance images.": "留空以使用实例提示词。可以选择使用 [filewords] 以实例图像为基础生成样本标题。",
"Enter the path to a txt file containing sample prompts.": "输入包含样本提示词的 txt 文件的路径。",
"Enter a model name for saving checkpoints and lora models.": "输入模型名称以保存 ckpt 和 lora 模型。",
"/path/to/images or /path/to/images//*": "/path/to/images 或 /path/to/images//*",
"Offset Noise": "噪声偏移",
"Save EMA Weights to Generated Models": "将EMA权重保存到生成的模型中",
"Use EMA Weights for Inference": "使用EMA权重进行推论",
"Deterministic": "Deterministic",
"Use EMA for prediction.": "使用 EMA 进行预测。",
"Calculate Split Loss": "计算分割损失",
"Use TensorFloat 32": "使用TensorFloat 32",
"Use DEIS for noise scheduler": "使用DEIS进行噪音调度",
"Update Extension and Restart": "更新扩充并重新启动",
"Bucket Cropping": "批量裁剪",
"Source Path": "来源路径",
"Dest Path": "目标路径",
"Max Res": "最大分辨率",
"Bucket Steps": "批量步骤",
"Select or create a model to begin.": "选择或创建一个模型",
"Start Cropping": "开始裁剪",
"Generate lora weights for extra networks.": "生成附加网络的LoRA",
"A negative prompt for the generic sample image.": "通用图像的反向提示词",
"Converting text encoder...": "正在转换文本编码器...",
"@@/^Checkpoint successfully extracted to (.*)$/": "ckpt模型已被成功提取到 $1",
"@@/^Calculated training params based on (.*) of VRAM:$/": "当前显存大小为 $1，根据显存大小计算训练参数：",
"Codec": "编码器",
"Create animation": "创建视频动画 (调用ffmpeg，需提前安装)",
"Creates animation sequence from denoised intermediate steps with video frame interpolation to achieve desired animation duration": "根据去噪的过程生成动画序列，通过视频帧插值方法使动画持续预定的时间",
"Debug info": "在控制台打印详细信息",
"Delete intermediate": "运行结束后删除产生的中间步骤文件",
"Extra text to add before <...> when adding extra network to prompt": "添加额外的网络进行提示时，<...> 前的额外文本",
"Hidden UI tabs (requires restart)": "需要隐藏的选项卡 (需要重启)",
"Intermediate files path": "中间步骤文件路径",
"Foreground": "前景",
"Feather": "羽化",
"Region 1": "区域 1",
"Region 2": "区域 2",
"Region 3": "区域 3",
"Region 4": "区域 4",
"Region 5": "区域 5",
"Region 6": "区域 6",
"Region 7": "区域 7",
"Region 8": "区域 8",
"Move ControlNet images to CPU (if applicable)": "如果可以的话将ControlNet图像用CPU处理",
"Region Prompt Control": "分区控制",
"Fast Encoder": "快速编码",
"Fast Decoder": "快速解码",
"Fast Encoder may change colors; Can fix it with more RAM and lower speed.": "快速编码可能会改变颜色，关闭后虽然计算更精确但是消耗巨量的显存和内存",
"Encoder Color Fix": "编码器颜色修复",
"Output animation path": "输出动画路径",
"Passing ControlNet parameters with \"Send to img2img\"": "使用“发送到图生图”传递ControlNet参数",
"Run on incomplete": "不等到结束时才生成 (中途停止也会基于已有的结果生成动画)",
"Script Enabled": "启用脚本",
"Skip steps": "跳过刚开始噪声过多的n步",
"UniPC lower order final": "在 UniPC 采样最后步骤中使用低阶解算器 (推荐小于15个推理步骤时开启，可以稳定解算器的采样)",
"UniPC order (must be < sampling steps)": "UniPC 阶数 (推荐有提示词时使用2阶，无提示词使用3阶)",
"UniPC skip type": "UniPC 采样跳过类型 (t_uniform适合512及更高分辨率；logSNR适合低分辨率，否则会出现不合理的细节；t_quadratic略好于logSNR)",
"UniPC variant": "UniPC 变体 (bh1适合在无提示词且步数小于10情况下使用；vary_coeff同样在10步内效果最好；其余情况全部使用bh2)",
"Use lossless compression for webp images": "对 webp 图像使用无损压缩",
"blend": "颜色混合",
"mci": "运动补偿",
"sd-extension-steps-animation": "生成去噪过程动画插件",
"All Reste": "全部重置",
"Scan Models for Civitai": "扫描模型",
"Download Max Size Preview": "下载最大尺寸的预览图",
"Model Types": "模型种类",
"ti": "ti",
"hyper": "hyper",
"ckp": "ckp",
"lora": "lora",
"Scan": "扫描",
"Scanning takes time, just wait. Check console log for detail": "请稍等，扫描会持续一段时间，请在控制台查看详细信息。",
"Get Model Info from Civitai by URL": "使用URL从Civitai获取模型信息",
"Use this when scanning can not find a local model on civitai": "扫描不到本地模型时可以使用这个功能。",
"Only Show Models have no Info": "只显示没有信息的模型",
"Civitai URL": "Civitai 网址",
"Get Model Info from Civitai": "从Civitai获取模型信息",
"Download Model": "模型下载",
"1. Get Model Info by Civitai Url": "1. 从网址获取模型信息",
"Pick Subfolder and Model Version": "选择子文件夹和模型版本",
"Model Name": "模型名称",
"Model Type": "模型类型",
"Sub-folder": "子文件夹",
"Model Version": "模型版本",
"3. Download Model": "3. 下载模型",
"Check Console log for Downloading Status": "下载状态显示在控制台中。",
"Check models' new version": "检查模型更新",
"Check models’ new version": "检查模型更新",
"Check New Version from Civitai": "从Civitai检查模型更新",
"It takes time, just wait. Check console log for detail": "这将会花费一些时间，请在控制台中查看详细信息",
"Other Setting": "其他设置",
"Open Url At Client Side": "在客户端打开网址",
"Always Display Buttons": "总是显示按钮",
"Show Button On Thumb Mode": "在缩略图模式下显示按钮",
"Proxy": "代理",
"@@/^format:(.*)$/": "格式: $1",
"Save Setting": "保存设置",
"@@/^version:(.*)$/": "版本: $1",
"sd-webui-3d-open-pose-editor": "3D Openpose 编辑器插件",
"3D Openpose Editor": "3D 姿势编辑器",
"Use online version": "使用在线版本",
"3D Openpose": "3D 姿势编辑器",
"Edit Openpose": "编辑 Openpose",
"Original:": "原项目: ",
"Online 3D Openpose Editor": "在线3D Openpose编辑器",
"##tab_threedopenpose##Pose": "姿势图",
"##tab_threedopenpose##Depth": "深度图",
"##tab_threedopenpose##Normal": "法线图",
"##tab_threedopenpose##Canny": "Canny边缘图",
"Control Model number": "控制网模型编号",
"Download": "下载",
"stable-diffusion-webui-rembg": "移除图像背景插件",
"Remove background": "移除背景",
"Return mask": "生成遮罩",
"Alpha matting": "Alpha matting",
"tag-autocomplete": "标签自动补全插件",
"stable-diffusion-webui-state": "web UI 状态保存插件",
"Saved main elements": "需要保存的主要元素",
"Saved elements from txt2img": "文生图界面需要保存的元素",
"Saved elements from img2img": "图生图界面需要保存的元素",
"Saved elements from extensions": "扩展界面需要保存的元素",
"tabs": "标签页",
"prompt": "提示词",
"negative_prompt": "负面提示词",
"styles": "风格模板",
"sampling": "采样器",
"sampling_steps": "采样步数",
"batch_count": "生成批次",
"batch_size": "每批数量",
"cfg_scale": "提示词相关性",
"restore_faces": "面部修复",
"tiling": "可平铺",
"hires_fix": "高清修复",
"hires_upscaler": "高清修复放大算法",
"hires_steps": "高清修复采样次数",
"hires_scale": "高清修复放大倍率",
"hires_resize_x": "高清修复宽度",
"hires_resize_y": "高清修复高度",
"hires_denoising_strength": "高清修复重绘幅度",
"resize_mode": "缩放模式",
"denoising_strength": "重绘幅度",
"control-net": "控制网络",
"Select All": "全选",
"Select All Except Seeds": "全选 (不包括种子)",
"Unselect All": "取消全选"
}
@lijuncao
Copy link

6

@w774431242
Copy link

有没有将新增插件汉化的，

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment