1580158
/
stable-diffusion-webui-localization-zh_Hans
mirror of https://github.com/hanamizuki-ai/stable-diffusion-webui-localization-zh_Hans.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

ci(update): synchronize from translation platform

master
wfjsw 2024-09-16 04:00:04 +00:00
parent e44dd6157a
commit 51051b4371
4 changed files with 28 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
localizations/zh-Hans (Stable) [vladmandic].json
View File

@ -4,6 +4,7 @@
"# 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)", "# 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)",
"'add_soundtrack' and 'soundtrack_path' aren't being honoured in \"Interpolate an existing video\" mode. Original vid audio will be used instead with the same slow-mo rules above.": "‘添加音频’和‘音频路径’将不会在‘插入现有视频’模式中执行，原有视频的音频将会使用相同的慢动作规则设置", "'add_soundtrack' and 'soundtrack_path' aren't being honoured in \"Interpolate an existing video\" mode. Original vid audio will be used instead with the same slow-mo rules above.": "‘添加音频’和‘音频路径’将不会在‘插入现有视频’模式中执行，原有视频的音频将会使用相同的慢动作规则设置",
"'seed_behavior' will be forcibly set to 'schedule'.": "“种子行为” 会被强制设为 “调度计划” 来进行调度", "'seed_behavior' will be forcibly set to 'schedule'.": "“种子行为” 会被强制设为 “调度计划” 来进行调度",
"(\"Add Textual Inversion hashes to infotext\" needs to be enabled)": "(需启用 \"添加 Lora 的哈希值文本到图片信息中\" 选项)",
"(\"When searched\" option will only show the item when the search string has 4 characters or more)": "(\"检索时\" 选项只有当搜索字符串有4个或更多字符时, 才会显示隐藏栏目)", "(\"When searched\" option will only show the item when the search string has 4 characters or more)": "(\"检索时\" 选项只有当搜索字符串有4个或更多字符时, 才会显示隐藏栏目)",
"(0 = No limit)": "(0 = 无限制)", "(0 = No limit)": "(0 = 无限制)",
"(0 = default (7 for karras, 1 for polyexponential); higher values result in a more steep noise schedule (decreases faster))": "(0 = 默认 (karras 选择 7, polyexponential 选择 1); 值越高噪声调度曲线越陡峭 (递减更快速))", "(0 = default (7 for karras, 1 for polyexponential); higher values result in a more steep noise schedule (decreases faster))": "(0 = 默认 (karras 选择 7, polyexponential 选择 1); 值越高噪声调度曲线越陡峭 (递减更快速))",
@ -69,6 +70,7 @@
"(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)": "(ENSD: 对图像质量无任何提升, 只为 Ancestral 采样方法产生不同的结果 - 仅对复现图像有用)", "(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)": "(ENSD: 对图像质量无任何提升, 只为 Ancestral 采样方法产生不同的结果 - 仅对复现图像有用)",
"(Early access models are only downloadable for supporter tier members)": "(抢鲜体验模型仅供支持者级的成员下载)", "(Early access models are only downloadable for supporter tier members)": "(抢鲜体验模型仅供支持者级的成员下载)",
"(Early access models are only downloadable for supporter tier members, Requires API key)": "(抢鲜体验模型仅供支持者级别的成员下载, 需要 API 密钥)", "(Early access models are only downloadable for supporter tier members, Requires API key)": "(抢鲜体验模型仅供支持者级别的成员下载, 需要 API 密钥)",
"(Enable Clip skip for the secondary clip model in sdxl. Has no effect on SD 1.5 or SD 2.0/2.1.)": "(为 SDXL 中的第二模型启用 Clip 终止层数调整选项. 对 SD 1.5 或 SD 2.0/2.1 模型无效)",
"(Experimental, keep cond caches across jobs, reduce overhead.)": "(实验性功能；在不同任务中保留缓存以减少开销)", "(Experimental, keep cond caches across jobs, reduce overhead.)": "(实验性功能；在不同任务中保留缓存以减少开销)",
"(For [red:green:N]; old: If N < 1, it's a fraction of steps (and hires fix uses range from 0 to 1), if N >= 1, it's an absolute number of steps; new: If N has a decimal point in it, it's a fraction of steps (and hires fix uses range from 1 to 2), othewrwise it's an absolute number of steps)": "(对于如 [red:green:N] 的表达式; 旧: 若 N < 1, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 0 - 1), 若 N >= 1, 则其表示一个确定的迭代步数数值; 新: 若 N 值含小数点, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 1 - 2), 其他情况则表示一个确定的迭代步数数值)", "(For [red:green:N]; old: If N < 1, it's a fraction of steps (and hires fix uses range from 0 to 1), if N >= 1, it's an absolute number of steps; new: If N has a decimal point in it, it's a fraction of steps (and hires fix uses range from 1 to 2), othewrwise it's an absolute number of steps)": "(对于如 [red:green:N] 的表达式; 旧: 若 N < 1, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 0 - 1), 若 N >= 1, 则其表示一个确定的迭代步数数值; 新: 若 N 值含小数点, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 1 - 2), 其他情况则表示一个确定的迭代步数数值)",
"(Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise)": "(完整 = 慢但显示效果好; Approx NN 和 TAESD = 快速但低质量; Approx cheap = 超级快但最糟糕)", "(Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise)": "(完整 = 慢但显示效果好; Approx NN 和 TAESD = 快速但低质量; Approx cheap = 超级快但最糟糕)",
@ -178,6 +180,7 @@
"(larger = more neural network layers affected; minor effect on performance)": "(数值越大意味着受影响的神经网络层越多; 对性能影响不大)", "(larger = more neural network layers affected; minor effect on performance)": "(数值越大意味着受影响的神经网络层越多; 对性能影响不大)",
"(larger = worse performance)": "(数值越大意味着性能越差)", "(larger = worse performance)": "(数值越大意味着性能越差)",
"(lets you override the noise schedule for k-diffusion samplers; choosing Automatic disables the three parameters below)": "(覆盖 k-diffusion 采样方法的噪声调度器; 选择自动会禁用以下的三个参数)", "(lets you override the noise schedule for k-diffusion samplers; choosing Automatic disables the three parameters below)": "(覆盖 k-diffusion 采样方法的噪声调度器; 选择自动会禁用以下的三个参数)",
"(load T5 text encoder; increases VRAM use by a lot, potentially improving quality of generation; requires model reload to apply)": "(加载 T5 文本编码器; 大幅提高显存用量, 可能会提高生成质量; 需重载模型以生效)",
"(makes interrupts faster)": "(使中断处理更快速)", "(makes interrupts faster)": "(使中断处理更快速)",
"(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the orginal emphasis implementation, No norm: same as orginal, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))", "(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the orginal emphasis implementation, No norm: same as orginal, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))",
"(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the original emphasis implementation, No norm: same as original, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))", "(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the original emphasis implementation, No norm: same as original, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))",
@ -1080,6 +1083,7 @@
"Clip and renormalize": "衰减与规格化", "Clip and renormalize": "衰减与规格化",
"Clip skip": "CLIP 终止层数", "Clip skip": "CLIP 终止层数",
"Clip skip (2 if training anime model)": "CLIP 终止层数 (训练二次元模型时调至 2)", "Clip skip (2 if training anime model)": "CLIP 终止层数 (训练二次元模型时调至 2)",
"Clip skip SDXL": "SDXL Clip 终止层数",
"Clip skip:": "CLIP 终止层数:", "Clip skip:": "CLIP 终止层数:",
"Close": "关闭", "Close": "关闭",
"Close Preview": "关闭预览", "Close Preview": "关闭预览",
@ -1748,6 +1752,7 @@
"Enable Region 8": "启用区域 8", "Enable Region 8": "启用区域 8",
"Enable Style Selector": "启用样式选择器", "Enable Style Selector": "启用样式选择器",
"Enable Subseed scheduling": "启用第二种子调度计划", "Enable Subseed scheduling": "启用第二种子调度计划",
"Enable T5": "启用 T5 ",
"Enable Tag Autocompletion": "启用标签自动补全", "Enable Tag Autocompletion": "启用标签自动补全",
"Enable Tiled Diffusion": "启用 Tiled Diffusion", "Enable Tiled Diffusion": "启用 Tiled Diffusion",
"Enable Tiled VAE": "启用 Tiled VAE", "Enable Tiled VAE": "启用 Tiled VAE",
@ -3769,6 +3774,7 @@
"Prev page": "上一页", "Prev page": "上一页",
"Prevent Stability-AI's ldm/sgm modules from printing noise to console.": "阻止 Stability-AI 的 ldm/sgm 模块向控制台打印垃圾信息", "Prevent Stability-AI's ldm/sgm modules from printing noise to console.": "阻止 Stability-AI 的 ldm/sgm 模块向控制台打印垃圾信息",
"Prevent empty spots in grid (when set to autodetect)": "自动检测并消除网格图中的空位", "Prevent empty spots in grid (when set to autodetect)": "自动检测并消除网格图中的空位",
"Prevent screen sleep during generation": "防止在生成过程中屏幕进入睡眠状态",
"Prevents overfit by clipping gradient norms. Default value is 0.0. Recommended value for Lora is 1.0": "通过裁剪梯度归一层防止过拟合。默认 0.0。推荐 Lora 使用 1.0 。", "Prevents overfit by clipping gradient norms. Default value is 0.0. Recommended value for Lora is 1.0": "通过裁剪梯度归一层防止过拟合。默认 0.0。推荐 Lora 使用 1.0 。",
"Preview": "预览", "Preview": "预览",
"Preview Image": "预览图像", "Preview Image": "预览图像",
@ -5545,6 +5551,7 @@
"Write all generated prompts to a file": "将所有生成的提示词写入文件", "Write all generated prompts to a file": "将所有生成的提示词写入文件",
"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", "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",
"Write infotext to metadata of the generated image": "写入生成信息到生成图像的元数据中", "Write infotext to metadata of the generated image": "写入生成信息到生成图像的元数据中",
"Write log.csv when saving images using 'Save' button": "当使用 “保存” 按钮保存图像时写入 log.csv 文件",
"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：为每个包含提示词模板和生成提示词的批次创建一个新的 .txt 文件", "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：为每个包含提示词模板和生成提示词的批次创建一个新的 .txt 文件",
"Write weights to tags files": "写入权重到标签文件中", "Write weights to tags files": "写入权重到标签文件中",
"X Types": "X 轴类型", "X Types": "X 轴类型",

7
localizations/zh-Hans (Stable).json
View File

@ -4,6 +4,7 @@
"# 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)", "# 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)",
"'add_soundtrack' and 'soundtrack_path' aren't being honoured in \"Interpolate an existing video\" mode. Original vid audio will be used instead with the same slow-mo rules above.": "‘添加音频’和‘音频路径’将不会在‘插入现有视频’模式中执行，原有视频的音频将会使用相同的慢动作规则设置", "'add_soundtrack' and 'soundtrack_path' aren't being honoured in \"Interpolate an existing video\" mode. Original vid audio will be used instead with the same slow-mo rules above.": "‘添加音频’和‘音频路径’将不会在‘插入现有视频’模式中执行，原有视频的音频将会使用相同的慢动作规则设置",
"'seed_behavior' will be forcibly set to 'schedule'.": "“种子行为” 会被强制设为 “调度计划” 来进行调度", "'seed_behavior' will be forcibly set to 'schedule'.": "“种子行为” 会被强制设为 “调度计划” 来进行调度",
"(\"Add Textual Inversion hashes to infotext\" needs to be enabled)": "(需启用 \"添加 Lora 的哈希值文本到图片信息中\" 选项)",
"(\"When searched\" option will only show the item when the search string has 4 characters or more)": "(\"检索时\" 选项只有当搜索字符串有4个或更多字符时, 才会显示隐藏栏目)", "(\"When searched\" option will only show the item when the search string has 4 characters or more)": "(\"检索时\" 选项只有当搜索字符串有4个或更多字符时, 才会显示隐藏栏目)",
"(0 = No limit)": "(0 = 无限制)", "(0 = No limit)": "(0 = 无限制)",
"(0 = default (7 for karras, 1 for polyexponential); higher values result in a more steep noise schedule (decreases faster))": "(0 = 默认 (karras 选择 7, polyexponential 选择 1); 值越高噪声调度曲线越陡峭 (递减更快速))", "(0 = default (7 for karras, 1 for polyexponential); higher values result in a more steep noise schedule (decreases faster))": "(0 = 默认 (karras 选择 7, polyexponential 选择 1); 值越高噪声调度曲线越陡峭 (递减更快速))",
@ -69,6 +70,7 @@
"(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)": "(ENSD: 对图像质量无任何提升, 只为 Ancestral 采样方法产生不同的结果 - 仅对复现图像有用)", "(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)": "(ENSD: 对图像质量无任何提升, 只为 Ancestral 采样方法产生不同的结果 - 仅对复现图像有用)",
"(Early access models are only downloadable for supporter tier members)": "(抢鲜体验模型仅供支持者级的成员下载)", "(Early access models are only downloadable for supporter tier members)": "(抢鲜体验模型仅供支持者级的成员下载)",
"(Early access models are only downloadable for supporter tier members, Requires API key)": "(抢鲜体验模型仅供支持者级别的成员下载, 需要 API 密钥)", "(Early access models are only downloadable for supporter tier members, Requires API key)": "(抢鲜体验模型仅供支持者级别的成员下载, 需要 API 密钥)",
"(Enable Clip skip for the secondary clip model in sdxl. Has no effect on SD 1.5 or SD 2.0/2.1.)": "(为 SDXL 中的第二模型启用 Clip 终止层数调整选项. 对 SD 1.5 或 SD 2.0/2.1 模型无效)",
"(Experimental, keep cond caches across jobs, reduce overhead.)": "(实验性功能；在不同任务中保留缓存以减少开销)", "(Experimental, keep cond caches across jobs, reduce overhead.)": "(实验性功能；在不同任务中保留缓存以减少开销)",
"(For [red:green:N]; old: If N < 1, it's a fraction of steps (and hires fix uses range from 0 to 1), if N >= 1, it's an absolute number of steps; new: If N has a decimal point in it, it's a fraction of steps (and hires fix uses range from 1 to 2), othewrwise it's an absolute number of steps)": "(对于如 [red:green:N] 的表达式; 旧: 若 N < 1, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 0 - 1), 若 N >= 1, 则其表示一个确定的迭代步数数值; 新: 若 N 值含小数点, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 1 - 2), 其他情况则表示一个确定的迭代步数数值)", "(For [red:green:N]; old: If N < 1, it's a fraction of steps (and hires fix uses range from 0 to 1), if N >= 1, it's an absolute number of steps; new: If N has a decimal point in it, it's a fraction of steps (and hires fix uses range from 1 to 2), othewrwise it's an absolute number of steps)": "(对于如 [red:green:N] 的表达式; 旧: 若 N < 1, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 0 - 1), 若 N >= 1, 则其表示一个确定的迭代步数数值; 新: 若 N 值含小数点, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 1 - 2), 其他情况则表示一个确定的迭代步数数值)",
"(Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise)": "(完整 = 慢但显示效果好; Approx NN 和 TAESD = 快速但低质量; Approx cheap = 超级快但最糟糕)", "(Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise)": "(完整 = 慢但显示效果好; Approx NN 和 TAESD = 快速但低质量; Approx cheap = 超级快但最糟糕)",
@ -178,6 +180,7 @@
"(larger = more neural network layers affected; minor effect on performance)": "(数值越大意味着受影响的神经网络层越多; 对性能影响不大)", "(larger = more neural network layers affected; minor effect on performance)": "(数值越大意味着受影响的神经网络层越多; 对性能影响不大)",
"(larger = worse performance)": "(数值越大意味着性能越差)", "(larger = worse performance)": "(数值越大意味着性能越差)",
"(lets you override the noise schedule for k-diffusion samplers; choosing Automatic disables the three parameters below)": "(覆盖 k-diffusion 采样方法的噪声调度器; 选择自动会禁用以下的三个参数)", "(lets you override the noise schedule for k-diffusion samplers; choosing Automatic disables the three parameters below)": "(覆盖 k-diffusion 采样方法的噪声调度器; 选择自动会禁用以下的三个参数)",
"(load T5 text encoder; increases VRAM use by a lot, potentially improving quality of generation; requires model reload to apply)": "(加载 T5 文本编码器; 大幅提高显存用量, 可能会提高生成质量; 需重载模型以生效)",
"(makes interrupts faster)": "(使中断处理更快速)", "(makes interrupts faster)": "(使中断处理更快速)",
"(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the orginal emphasis implementation, No norm: same as orginal, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))", "(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the orginal emphasis implementation, No norm: same as orginal, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))",
"(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the original emphasis implementation, No norm: same as original, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))", "(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the original emphasis implementation, No norm: same as original, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))",
@ -1080,6 +1083,7 @@
"Clip and renormalize": "衰减与规格化", "Clip and renormalize": "衰减与规格化",
"Clip skip": "CLIP 终止层数", "Clip skip": "CLIP 终止层数",
"Clip skip (2 if training anime model)": "CLIP 终止层数 (训练二次元模型时调至 2)", "Clip skip (2 if training anime model)": "CLIP 终止层数 (训练二次元模型时调至 2)",
"Clip skip SDXL": "SDXL Clip 终止层数",
"Clip skip:": "CLIP 终止层数:", "Clip skip:": "CLIP 终止层数:",
"Close": "关闭", "Close": "关闭",
"Close Preview": "关闭预览", "Close Preview": "关闭预览",
@ -1748,6 +1752,7 @@
"Enable Region 8": "启用区域 8", "Enable Region 8": "启用区域 8",
"Enable Style Selector": "启用样式选择器", "Enable Style Selector": "启用样式选择器",
"Enable Subseed scheduling": "启用第二种子调度计划", "Enable Subseed scheduling": "启用第二种子调度计划",
"Enable T5": "启用 T5 ",
"Enable Tag Autocompletion": "启用标签自动补全", "Enable Tag Autocompletion": "启用标签自动补全",
"Enable Tiled Diffusion": "启用 Tiled Diffusion", "Enable Tiled Diffusion": "启用 Tiled Diffusion",
"Enable Tiled VAE": "启用 Tiled VAE", "Enable Tiled VAE": "启用 Tiled VAE",
@ -3769,6 +3774,7 @@
"Prev page": "上一页", "Prev page": "上一页",
"Prevent Stability-AI's ldm/sgm modules from printing noise to console.": "阻止 Stability-AI 的 ldm/sgm 模块向控制台打印垃圾信息", "Prevent Stability-AI's ldm/sgm modules from printing noise to console.": "阻止 Stability-AI 的 ldm/sgm 模块向控制台打印垃圾信息",
"Prevent empty spots in grid (when set to autodetect)": "自动检测并消除网格图中的空位", "Prevent empty spots in grid (when set to autodetect)": "自动检测并消除网格图中的空位",
"Prevent screen sleep during generation": "防止在生成过程中屏幕进入睡眠状态",
"Prevents overfit by clipping gradient norms. Default value is 0.0. Recommended value for Lora is 1.0": "通过裁剪梯度归一层防止过拟合。默认 0.0。推荐 Lora 使用 1.0 。", "Prevents overfit by clipping gradient norms. Default value is 0.0. Recommended value for Lora is 1.0": "通过裁剪梯度归一层防止过拟合。默认 0.0。推荐 Lora 使用 1.0 。",
"Preview": "预览", "Preview": "预览",
"Preview Image": "预览图像", "Preview Image": "预览图像",
@ -5545,6 +5551,7 @@
"Write all generated prompts to a file": "将所有生成的提示词写入文件", "Write all generated prompts to a file": "将所有生成的提示词写入文件",
"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", "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",
"Write infotext to metadata of the generated image": "写入生成信息到生成图像的元数据中", "Write infotext to metadata of the generated image": "写入生成信息到生成图像的元数据中",
"Write log.csv when saving images using 'Save' button": "当使用 “保存” 按钮保存图像时写入 log.csv 文件",
"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：为每个包含提示词模板和生成提示词的批次创建一个新的 .txt 文件", "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：为每个包含提示词模板和生成提示词的批次创建一个新的 .txt 文件",
"Write weights to tags files": "写入权重到标签文件中", "Write weights to tags files": "写入权重到标签文件中",
"X Types": "X 轴类型", "X Types": "X 轴类型",

7
localizations/zh-Hans (Testing) [vladmandic].json
View File

@ -7,6 +7,7 @@
"# 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)", "# 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)",
"'add_soundtrack' and 'soundtrack_path' aren't being honoured in \"Interpolate an existing video\" mode. Original vid audio will be used instead with the same slow-mo rules above.": "‘添加音频’和‘音频路径’将不会在‘插入现有视频’模式中执行，原有视频的音频将会使用相同的慢动作规则设置", "'add_soundtrack' and 'soundtrack_path' aren't being honoured in \"Interpolate an existing video\" mode. Original vid audio will be used instead with the same slow-mo rules above.": "‘添加音频’和‘音频路径’将不会在‘插入现有视频’模式中执行，原有视频的音频将会使用相同的慢动作规则设置",
"'seed_behavior' will be forcibly set to 'schedule'.": "“种子行为” 会被强制设为 “调度计划” 来进行调度", "'seed_behavior' will be forcibly set to 'schedule'.": "“种子行为” 会被强制设为 “调度计划” 来进行调度",
"(\"Add Textual Inversion hashes to infotext\" needs to be enabled)": "(需启用 \"添加 Lora 的哈希值文本到图片信息中\" 选项)",
"(\"When searched\" option will only show the item when the search string has 4 characters or more)": "(\"检索时\" 选项只有当搜索字符串有4个或更多字符时, 才会显示隐藏栏目)", "(\"When searched\" option will only show the item when the search string has 4 characters or more)": "(\"检索时\" 选项只有当搜索字符串有4个或更多字符时, 才会显示隐藏栏目)",
"(0 = No limit)": "(0 = 无限制)", "(0 = No limit)": "(0 = 无限制)",
"(0 = default (7 for karras, 1 for polyexponential); higher values result in a more steep noise schedule (decreases faster))": "(0 = 默认 (karras 选择 7, polyexponential 选择 1); 值越高噪声调度曲线越陡峭 (递减更快速))", "(0 = default (7 for karras, 1 for polyexponential); higher values result in a more steep noise schedule (decreases faster))": "(0 = 默认 (karras 选择 7, polyexponential 选择 1); 值越高噪声调度曲线越陡峭 (递减更快速))",
@ -82,6 +83,7 @@
"(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)": "(ENSD: 对图像质量无任何提升, 只为 Ancestral 采样方法产生不同的结果 - 仅对复现图像有用)", "(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)": "(ENSD: 对图像质量无任何提升, 只为 Ancestral 采样方法产生不同的结果 - 仅对复现图像有用)",
"(Early access models are only downloadable for supporter tier members)": "(抢鲜体验模型仅供支持者级的成员下载)", "(Early access models are only downloadable for supporter tier members)": "(抢鲜体验模型仅供支持者级的成员下载)",
"(Early access models are only downloadable for supporter tier members, Requires API key)": "(抢鲜体验模型仅供支持者级别的成员下载, 需要 API 密钥)", "(Early access models are only downloadable for supporter tier members, Requires API key)": "(抢鲜体验模型仅供支持者级别的成员下载, 需要 API 密钥)",
"(Enable Clip skip for the secondary clip model in sdxl. Has no effect on SD 1.5 or SD 2.0/2.1.)": "(为 SDXL 中的第二模型启用 Clip 终止层数调整选项. 对 SD 1.5 或 SD 2.0/2.1 模型无效)",
"(Experimental, keep cond caches across jobs, reduce overhead.)": "(实验性功能；在不同任务中保留缓存以减少开销)", "(Experimental, keep cond caches across jobs, reduce overhead.)": "(实验性功能；在不同任务中保留缓存以减少开销)",
"(For [red:green:N]; old: If N < 1, it's a fraction of steps (and hires fix uses range from 0 to 1), if N >= 1, it's an absolute number of steps; new: If N has a decimal point in it, it's a fraction of steps (and hires fix uses range from 1 to 2), othewrwise it's an absolute number of steps)": "(对于如 [red:green:N] 的表达式; 旧: 若 N < 1, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 0 - 1), 若 N >= 1, 则其表示一个确定的迭代步数数值; 新: 若 N 值含小数点, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 1 - 2), 其他情况则表示一个确定的迭代步数数值)", "(For [red:green:N]; old: If N < 1, it's a fraction of steps (and hires fix uses range from 0 to 1), if N >= 1, it's an absolute number of steps; new: If N has a decimal point in it, it's a fraction of steps (and hires fix uses range from 1 to 2), othewrwise it's an absolute number of steps)": "(对于如 [red:green:N] 的表达式; 旧: 若 N < 1, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 0 - 1), 若 N >= 1, 则其表示一个确定的迭代步数数值; 新: 若 N 值含小数点, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 1 - 2), 其他情况则表示一个确定的迭代步数数值)",
"(Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise)": "(完整 = 慢但显示效果好; Approx NN 和 TAESD = 快速但低质量; Approx cheap = 超级快但最糟糕)", "(Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise)": "(完整 = 慢但显示效果好; Approx NN 和 TAESD = 快速但低质量; Approx cheap = 超级快但最糟糕)",
@ -211,6 +213,7 @@
"(larger = more neural network layers affected; minor effect on performance)": "(数值越大意味着受影响的神经网络层越多; 对性能影响不大)", "(larger = more neural network layers affected; minor effect on performance)": "(数值越大意味着受影响的神经网络层越多; 对性能影响不大)",
"(larger = worse performance)": "(数值越大意味着性能越差)", "(larger = worse performance)": "(数值越大意味着性能越差)",
"(lets you override the noise schedule for k-diffusion samplers; choosing Automatic disables the three parameters below)": "(覆盖 k-diffusion 采样方法的噪声调度器; 选择自动会禁用以下的三个参数)", "(lets you override the noise schedule for k-diffusion samplers; choosing Automatic disables the three parameters below)": "(覆盖 k-diffusion 采样方法的噪声调度器; 选择自动会禁用以下的三个参数)",
"(load T5 text encoder; increases VRAM use by a lot, potentially improving quality of generation; requires model reload to apply)": "(加载 T5 文本编码器; 大幅提高显存用量, 可能会提高生成质量; 需重载模型以生效)",
"(makes interrupts faster)": "(使中断处理更快速)", "(makes interrupts faster)": "(使中断处理更快速)",
"(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the orginal emphasis implementation, No norm: same as orginal, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))", "(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the orginal emphasis implementation, No norm: same as orginal, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))",
"(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the original emphasis implementation, No norm: same as original, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))", "(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the original emphasis implementation, No norm: same as original, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))",
@ -1242,6 +1245,7 @@
"Clip and renormalize DepthMap": "剪切重构深度图", "Clip and renormalize DepthMap": "剪切重构深度图",
"Clip skip": "CLIP 终止层数", "Clip skip": "CLIP 终止层数",
"Clip skip (2 if training anime model)": "CLIP 终止层数 (训练二次元模型时调至 2)", "Clip skip (2 if training anime model)": "CLIP 终止层数 (训练二次元模型时调至 2)",
"Clip skip SDXL": "SDXL Clip 终止层数",
"Clip skip:": "CLIP 终止层数:", "Clip skip:": "CLIP 终止层数:",
"Close": "关闭", "Close": "关闭",
"Close Preview": "关闭预览", "Close Preview": "关闭预览",
@ -1996,6 +2000,7 @@
"Enable Region 8": "启用区域 8", "Enable Region 8": "启用区域 8",
"Enable Style Selector": "启用样式选择器", "Enable Style Selector": "启用样式选择器",
"Enable Subseed scheduling": "启用第二种子调度计划", "Enable Subseed scheduling": "启用第二种子调度计划",
"Enable T5": "启用 T5 ",
"Enable Tag Autocompletion": "启用标签自动补全", "Enable Tag Autocompletion": "启用标签自动补全",
"Enable Tiled Diffusion": "启用 Tiled Diffusion", "Enable Tiled Diffusion": "启用 Tiled Diffusion",
"Enable Tiled VAE": "启用 Tiled VAE", "Enable Tiled VAE": "启用 Tiled VAE",
@ -4229,6 +4234,7 @@
"Prev page": "上一页", "Prev page": "上一页",
"Prevent Stability-AI's ldm/sgm modules from printing noise to console.": "阻止 Stability-AI 的 ldm/sgm 模块向控制台打印垃圾信息", "Prevent Stability-AI's ldm/sgm modules from printing noise to console.": "阻止 Stability-AI 的 ldm/sgm 模块向控制台打印垃圾信息",
"Prevent empty spots in grid (when set to autodetect)": "自动检测并消除网格图中的空位", "Prevent empty spots in grid (when set to autodetect)": "自动检测并消除网格图中的空位",
"Prevent screen sleep during generation": "防止在生成过程中屏幕进入睡眠状态",
"Prevents overfit by clipping gradient norms. Default value is 0.0. Recommended value for Lora is 1.0": "通过裁剪梯度归一层防止过拟合。默认 0.0。推荐 Lora 使用 1.0 。", "Prevents overfit by clipping gradient norms. Default value is 0.0. Recommended value for Lora is 1.0": "通过裁剪梯度归一层防止过拟合。默认 0.0。推荐 Lora 使用 1.0 。",
"Preview": "预览", "Preview": "预览",
"Preview Image": "预览图像", "Preview Image": "预览图像",
@ -6262,6 +6268,7 @@
"Write all generated prompts to a file": "将所有生成的提示词写入文件", "Write all generated prompts to a file": "将所有生成的提示词写入文件",
"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", "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",
"Write infotext to metadata of the generated image": "写入生成信息到生成图像的元数据中", "Write infotext to metadata of the generated image": "写入生成信息到生成图像的元数据中",
"Write log.csv when saving images using 'Save' button": "当使用 “保存” 按钮保存图像时写入 log.csv 文件",
"Write prompts to file": "将提示词写入文件", "Write prompts to file": "将提示词写入文件",
"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：为每个包含提示词模板和生成提示词的批次创建一个新的 .txt 文件", "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：为每个包含提示词模板和生成提示词的批次创建一个新的 .txt 文件",
"Write weights to tags files": "写入权重到标签文件中", "Write weights to tags files": "写入权重到标签文件中",

7
localizations/zh-Hans (Testing).json
View File

@ -7,6 +7,7 @@
"# 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)", "# 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)",
"'add_soundtrack' and 'soundtrack_path' aren't being honoured in \"Interpolate an existing video\" mode. Original vid audio will be used instead with the same slow-mo rules above.": "‘添加音频’和‘音频路径’将不会在‘插入现有视频’模式中执行，原有视频的音频将会使用相同的慢动作规则设置", "'add_soundtrack' and 'soundtrack_path' aren't being honoured in \"Interpolate an existing video\" mode. Original vid audio will be used instead with the same slow-mo rules above.": "‘添加音频’和‘音频路径’将不会在‘插入现有视频’模式中执行，原有视频的音频将会使用相同的慢动作规则设置",
"'seed_behavior' will be forcibly set to 'schedule'.": "“种子行为” 会被强制设为 “调度计划” 来进行调度", "'seed_behavior' will be forcibly set to 'schedule'.": "“种子行为” 会被强制设为 “调度计划” 来进行调度",
"(\"Add Textual Inversion hashes to infotext\" needs to be enabled)": "(需启用 \"添加 Lora 的哈希值文本到图片信息中\" 选项)",
"(\"When searched\" option will only show the item when the search string has 4 characters or more)": "(\"检索时\" 选项只有当搜索字符串有4个或更多字符时, 才会显示隐藏栏目)", "(\"When searched\" option will only show the item when the search string has 4 characters or more)": "(\"检索时\" 选项只有当搜索字符串有4个或更多字符时, 才会显示隐藏栏目)",
"(0 = No limit)": "(0 = 无限制)", "(0 = No limit)": "(0 = 无限制)",
"(0 = default (7 for karras, 1 for polyexponential); higher values result in a more steep noise schedule (decreases faster))": "(0 = 默认 (karras 选择 7, polyexponential 选择 1); 值越高噪声调度曲线越陡峭 (递减更快速))", "(0 = default (7 for karras, 1 for polyexponential); higher values result in a more steep noise schedule (decreases faster))": "(0 = 默认 (karras 选择 7, polyexponential 选择 1); 值越高噪声调度曲线越陡峭 (递减更快速))",
@ -82,6 +83,7 @@
"(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)": "(ENSD: 对图像质量无任何提升, 只为 Ancestral 采样方法产生不同的结果 - 仅对复现图像有用)", "(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)": "(ENSD: 对图像质量无任何提升, 只为 Ancestral 采样方法产生不同的结果 - 仅对复现图像有用)",
"(Early access models are only downloadable for supporter tier members)": "(抢鲜体验模型仅供支持者级的成员下载)", "(Early access models are only downloadable for supporter tier members)": "(抢鲜体验模型仅供支持者级的成员下载)",
"(Early access models are only downloadable for supporter tier members, Requires API key)": "(抢鲜体验模型仅供支持者级别的成员下载, 需要 API 密钥)", "(Early access models are only downloadable for supporter tier members, Requires API key)": "(抢鲜体验模型仅供支持者级别的成员下载, 需要 API 密钥)",
"(Enable Clip skip for the secondary clip model in sdxl. Has no effect on SD 1.5 or SD 2.0/2.1.)": "(为 SDXL 中的第二模型启用 Clip 终止层数调整选项. 对 SD 1.5 或 SD 2.0/2.1 模型无效)",
"(Experimental, keep cond caches across jobs, reduce overhead.)": "(实验性功能；在不同任务中保留缓存以减少开销)", "(Experimental, keep cond caches across jobs, reduce overhead.)": "(实验性功能；在不同任务中保留缓存以减少开销)",
"(For [red:green:N]; old: If N < 1, it's a fraction of steps (and hires fix uses range from 0 to 1), if N >= 1, it's an absolute number of steps; new: If N has a decimal point in it, it's a fraction of steps (and hires fix uses range from 1 to 2), othewrwise it's an absolute number of steps)": "(对于如 [red:green:N] 的表达式; 旧: 若 N < 1, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 0 - 1), 若 N >= 1, 则其表示一个确定的迭代步数数值; 新: 若 N 值含小数点, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 1 - 2), 其他情况则表示一个确定的迭代步数数值)", "(For [red:green:N]; old: If N < 1, it's a fraction of steps (and hires fix uses range from 0 to 1), if N >= 1, it's an absolute number of steps; new: If N has a decimal point in it, it's a fraction of steps (and hires fix uses range from 1 to 2), othewrwise it's an absolute number of steps)": "(对于如 [red:green:N] 的表达式; 旧: 若 N < 1, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 0 - 1), 若 N >= 1, 则其表示一个确定的迭代步数数值; 新: 若 N 值含小数点, 则其表示占总迭代步数的比例 (且高分辨率修复使用的范围是 1 - 2), 其他情况则表示一个确定的迭代步数数值)",
"(Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise)": "(完整 = 慢但显示效果好; Approx NN 和 TAESD = 快速但低质量; Approx cheap = 超级快但最糟糕)", "(Full = slow but pretty; Approx NN and TAESD = fast but low quality; Approx cheap = super fast but terrible otherwise)": "(完整 = 慢但显示效果好; Approx NN 和 TAESD = 快速但低质量; Approx cheap = 超级快但最糟糕)",
@ -211,6 +213,7 @@
"(larger = more neural network layers affected; minor effect on performance)": "(数值越大意味着受影响的神经网络层越多; 对性能影响不大)", "(larger = more neural network layers affected; minor effect on performance)": "(数值越大意味着受影响的神经网络层越多; 对性能影响不大)",
"(larger = worse performance)": "(数值越大意味着性能越差)", "(larger = worse performance)": "(数值越大意味着性能越差)",
"(lets you override the noise schedule for k-diffusion samplers; choosing Automatic disables the three parameters below)": "(覆盖 k-diffusion 采样方法的噪声调度器; 选择自动会禁用以下的三个参数)", "(lets you override the noise schedule for k-diffusion samplers; choosing Automatic disables the three parameters below)": "(覆盖 k-diffusion 采样方法的噪声调度器; 选择自动会禁用以下的三个参数)",
"(load T5 text encoder; increases VRAM use by a lot, potentially improving quality of generation; requires model reload to apply)": "(加载 T5 文本编码器; 大幅提高显存用量, 可能会提高生成质量; 需重载模型以生效)",
"(makes interrupts faster)": "(使中断处理更快速)", "(makes interrupts faster)": "(使中断处理更快速)",
"(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the orginal emphasis implementation, No norm: same as orginal, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))", "(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the orginal emphasis implementation, No norm: same as orginal, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))",
"(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the original emphasis implementation, No norm: same as original, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))", "(makes it possible to make model to pay (more:1.1) or (less:0.9) attention to text when you use the syntax in prompt; None: disable the mechanism entirely and treat (:.1.1) as literal characters, Ignore: treat all empasised words as if they have no emphasis, Original: the original emphasis implementation, No norm: same as original, but without normalization (seems to work better for SDXL))": "(使模型在提示词中使用语法时可以对文本进行 (更多:1.1) 或 (更少:0.9) 强调; 无：完全禁用该机制并将 (:.1.1) 视作文字字符, 忽略: 将所有强调的提示词视为没有强调, Original: 原始强调实现, No norm: 与原始相同, 但没有规范化 (似乎更适合 SDXL))",
@ -1242,6 +1245,7 @@
"Clip and renormalize DepthMap": "剪切重构深度图", "Clip and renormalize DepthMap": "剪切重构深度图",
"Clip skip": "CLIP 终止层数", "Clip skip": "CLIP 终止层数",
"Clip skip (2 if training anime model)": "CLIP 终止层数 (训练二次元模型时调至 2)", "Clip skip (2 if training anime model)": "CLIP 终止层数 (训练二次元模型时调至 2)",
"Clip skip SDXL": "SDXL Clip 终止层数",
"Clip skip:": "CLIP 终止层数:", "Clip skip:": "CLIP 终止层数:",
"Close": "关闭", "Close": "关闭",
"Close Preview": "关闭预览", "Close Preview": "关闭预览",
@ -1996,6 +2000,7 @@
"Enable Region 8": "启用区域 8", "Enable Region 8": "启用区域 8",
"Enable Style Selector": "启用样式选择器", "Enable Style Selector": "启用样式选择器",
"Enable Subseed scheduling": "启用第二种子调度计划", "Enable Subseed scheduling": "启用第二种子调度计划",
"Enable T5": "启用 T5 ",
"Enable Tag Autocompletion": "启用标签自动补全", "Enable Tag Autocompletion": "启用标签自动补全",
"Enable Tiled Diffusion": "启用 Tiled Diffusion", "Enable Tiled Diffusion": "启用 Tiled Diffusion",
"Enable Tiled VAE": "启用 Tiled VAE", "Enable Tiled VAE": "启用 Tiled VAE",
@ -4229,6 +4234,7 @@
"Prev page": "上一页", "Prev page": "上一页",
"Prevent Stability-AI's ldm/sgm modules from printing noise to console.": "阻止 Stability-AI 的 ldm/sgm 模块向控制台打印垃圾信息", "Prevent Stability-AI's ldm/sgm modules from printing noise to console.": "阻止 Stability-AI 的 ldm/sgm 模块向控制台打印垃圾信息",
"Prevent empty spots in grid (when set to autodetect)": "自动检测并消除网格图中的空位", "Prevent empty spots in grid (when set to autodetect)": "自动检测并消除网格图中的空位",
"Prevent screen sleep during generation": "防止在生成过程中屏幕进入睡眠状态",
"Prevents overfit by clipping gradient norms. Default value is 0.0. Recommended value for Lora is 1.0": "通过裁剪梯度归一层防止过拟合。默认 0.0。推荐 Lora 使用 1.0 。", "Prevents overfit by clipping gradient norms. Default value is 0.0. Recommended value for Lora is 1.0": "通过裁剪梯度归一层防止过拟合。默认 0.0。推荐 Lora 使用 1.0 。",
"Preview": "预览", "Preview": "预览",
"Preview Image": "预览图像", "Preview Image": "预览图像",
@ -6262,6 +6268,7 @@
"Write all generated prompts to a file": "将所有生成的提示词写入文件", "Write all generated prompts to a file": "将所有生成的提示词写入文件",
"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", "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",
"Write infotext to metadata of the generated image": "写入生成信息到生成图像的元数据中", "Write infotext to metadata of the generated image": "写入生成信息到生成图像的元数据中",
"Write log.csv when saving images using 'Save' button": "当使用 “保存” 按钮保存图像时写入 log.csv 文件",
"Write prompts to file": "将提示词写入文件", "Write prompts to file": "将提示词写入文件",
"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：为每个包含提示词模板和生成提示词的批次创建一个新的 .txt 文件", "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：为每个包含提示词模板和生成提示词的批次创建一个新的 .txt 文件",
"Write weights to tags files": "写入权重到标签文件中", "Write weights to tags files": "写入权重到标签文件中",