{ "----deprecated----": "----以下内容在webUI新版本已移除----", "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", "Disable negative prompt": "禁用反向提示词", "Hypernetwork strength": "超网络(Hypernetwork) 强度", "X/Y plot": "X/Y 图表", "Hypernet str.": "超网络(Hypernetwork) 强度", "Include Separate Images": "生成图表时，保留每一张图像", "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)", "\"Hug the middle\" during interpolation": "在插值的途中 \"主动去找中间点\"", "grad": "梯度", "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": "步幅 (梯度模式)", "Step count": "步数 (梯度模式)", "Step method": "步进方法 (梯度模式)", "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", "Show console debug": "在控制台显示调试信息", "Batch img2img": "批量图生图", "Mask source": "蒙版来源", "Draw mask": "绘制蒙版", "Upload mask": "上传蒙版", "Deforum-webui (use tab extension instead!)": "Deforum-webui (请使用选项卡上的扩展版本)", "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", "Update instructions:": "更新指引（英文）：", "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(ckpt)会生成在你的", "Info and links": "资讯和链接", "Video output": "视频输出", "Run settings": "运行设置", "Import settings from file": "从文件导入设置", "Sampling settings": "采样设置", "override_these_with_webui": "用 webui 覆写这些", "W": "宽", "H": "高", "Highres. fix": "高清修复", "Firstpass width": "首次宽度", "Firstpass height": "首次高度", "Enable extras": "打开 ▼", "subseed": "差异随机种子", "subseed_strength": "差异随机种子强度", "n_batch": "批次", "make_grid": "制作宫格", "grid_rows": "宫格行数", "save_sample_per_step": "每步都储存样本", "show_sample_per_step": "每步都显示样本", "Batch settings": "批次设定", "batch_name": "批次名称", "filename_format": "文件名格式", "seed_behavior": "随机种子行为", "Animation settings": "动画设定", "animation_mode": "动画模式", "Motion parameters:": "运动参数：", "2D and 3D settings": "2D 及 3D 设定", "3D settings": "3D 设定", "Prespective flip — Low VRAM pseudo-3D mode:": "透视翻转 — 低显存(VRAM)伪3D模式:", "Generation settings:": "一般设置:", "3D Fov settings:": "3D 视野设置:", "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”", "Coherence:": "相干性:", "`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）", "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...”。", "Path relative to the webui folder": "webui文件夹的相对路径", "working": "运行中", "Import Model from Huggingface Hub": "自 Huggingface Hub 载入模型", "keyword": "搜索", "Collect": "收藏(保存)", "Bulk process frames with chosen outfill method": "使用选定的填充方法批量处理截取的帧", "Images Browser": "图库浏览器", "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", "Interrogate: use artists from artists.csv": "反推：使用 artists.csv 中的艺术家", "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", "stable-diffusion-webui-localization-zh_TW": "正體中文語言包", "Read generation parameters from prompt or last generation if prompt is empty into user interface.": "从提示词(prompt)中自动提取生成参数，若当前提示词为空则从上次的生成信息中读取（允许将包含正面、负面、采样器、步数、模型等信息的整段生成信息全部粘贴到提示词区域，点击后可自动将对应信息填入并删除多余内容）", "Save style": "将当前的提示词(prompt)保存为模板风格", "Apply selected styles to current prompt": "将已选择的模板风格写入当前的提示词(prompt)", "Add a random artist to the prompt.": "随机添加一个艺术家到提示词中", "Stop processing current image and continue processing.": "停止处理当前图像，并继续处理下一个", "Stop processing images and return any results accumulated so far.": "停止处理图像，并返回迄今为止累积的任何结果", "Style to apply; styles have components for both positive and negative prompts and apply to both": "要使用的模版风格； 模版风格包含正向和反向提示词，并应用于两者\n🎨 随机添加一个艺术家到提示词中\n ↙️ 从提示词中读取生成参数，如果提示词为空，则读取上一次的生成参数到用户界面\n💾 将当前的提示词保存为模版风格(保存在styles.csv)\n📋 将所选模板风格，应用于当前提示词\n如果你在文本中添加{prompt}标记，并保存为模版风格\n那么将来你使用该模版风格时，你现有的提示词会替换模版风格中的{prompt}", "Do not do anything special": "什么都不做", "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 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", "How many times to improve the generated image iteratively; higher values take longer; very low values can produce bad results": "迭代改进生成的图像多少次；更高的值需要更长的时间；非常低的值会产生不好的结果", "How many 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(Classifier Free Guidance Scale) - 图像应在多大程度上服从提示词 - 较低的值会产生更有创意的结果", "A value that determines the output of random number generator - if you create an image with same parameters and seed as another image, you'll get the same result": "一个固定随机数生成器输出的值 - 以相同参数和随机种子生成的图像会得到相同的结果\n🎲 将随机种子设置为-1，则每次都会使用一个新的随机数\n♻️ 重用上一次使用的随机种子，如果想要固定输出结果就会很有用", "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", "Produce an image that can be tiled.": "生成可用于平铺(tiled)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", "Determines how little respect the algorithm should have for image's content. At 0, nothing will change, and at 1 you'll get an unrelated image. With values below 1.0, processing will take less steps than the Sampling Steps slider specifies.": "决定算法对图像内容的影响程度。设置 0 时，什么都不会改变，而在 1 时，你将获得不相关的图像。\n值低于 1.0 时，处理的迭代步数将少于“采样迭代步数”滑块指定的步数", "Disable dynamic prompts by unchecking this box.": "取消勾选来禁用动态提示词", "Instead of generating random prompts from a template, combinatorial generation produces every possible prompt from the given string.\nThe prompt 'I {love|hate} {New York|Chicago} in {June|July|August}' will produce 12 variants in total.\nDon't forget to increase the 'Batch count'/'Batch size' value accordingly.\n\t\nThe value of the 'Seed' field is only used for the first image. To change this, look for 'Fixed seed' in the 'Advanced options' section.": "组合生成从给定的字符串中生成所有可能的提示词，而非随机其中一个\n'I {love|hate} {New York|Chicago} in {June|July|August}' 总共会生成 12 句提示词变体\n别忘记相应地增加 “批次（Batch count）” 和 “批量（Batch size）” 值\n\t\n“随机种子” 的值只用于第一图像，可在 “高级选项” 中的 “固定随机种子” 修改此行为", "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", "Open images output directory": "打开图像输出目录", "Loads weights from checkpoint before making images. You can either use hash or a part of filename (as seen in settings) for checkpoint name. Recommended to use with Y axis for less switching.": "在生成图像之前从模型(ckpt)中加载权重。你可以使用哈希值或文件名的一部分（如设置中所示）作为模型(ckpt)名称。建议用在Y轴上以减少过程中模型的切换", "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", "Separate values for X axis using commas.": "使用逗号分隔 X 轴的值", "Separate values for Y axis using commas.": "使用逗号分隔 Y 轴的值", "Denoising Diffusion Implicit Models - best at inpainting": "Denoising Diffusion Implicit models - 最擅长局部重绘", "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", "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", "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 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(SD upscale)时，图块(Tiles)之间应该有多少像素重叠。图块(Tiles)之间需要重叠才可以让它们在合并回一张图像时，没有清晰可见的接缝", "Result = A * (1 - M) + B * M": "结果 = A * (1 - M) + B * M", "Result = A + (B - C) * M": "结果 = A + (B - C) * M", "Restore low quality faces using GFPGAN neural network": "使用 GFPGAN 神经网络修复低质量面部", "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", "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", "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", "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", "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", "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", "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", "latest": "最新", "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", "Show Textbox": "显示文本框", "File with inputs": "含输入内容的文件", "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", "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(VRAM)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)", "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", "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(CFG Scale)", "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(Denoising)", "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", "Loss for latent match (grad mode)": "匹配潜变量(latent)损失 (梯度模式)", "Loss for cond match (grad mode)": "匹配文字调节(cond)损失 (梯度模式)", "Instance prompt(Optional)": "实例(Instance)提示词 (可选)", "Replace order (replace mode)": "取代顺序 (取代模式)", "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)", "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)", "Pick frames every n-th": "每 n 帧挑选 1 帧", "Show verbose debug info at console": "在控制台中输出详尽的调试信息", "Concepts List (Overrides instance/class settings below)": "概念列表（将取代下面实例/类这两项设置）", "Training steps": "训练迭代步数", "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", "Class prompt": "类(Class)提示词", "Classification dataset directory (optional).": "分类(Classification)数据集目录（可选）", "Total number of classification images to use. Set to 0 to disable.": "要使用的分类(classification)图像总数。设置为 0 以禁用", "Learning rate": "学习率", "Save a checkpoint every N steps, 0 to disable": "每隔 N 步保存一次模型权重进度(ckpt)，设置为 0 以禁用", "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(guidance scale) - 类似基准 CFG scale 的概念", "Sample steps": "样本迭代步数", "Don't cache latents": "不要缓存潜变量", "Grad Accumulation Steps": "梯度累加步数(Grad Accumulation Steps)", "Warmup Steps": "预热步数", "Apply horizontal Flip": "应用水平翻转", "Use EMA for finetuning": "使用 EMA 进行微调", "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", "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", "view": "查看", "•": "・", "built with gradio": "基于 Gradio 构建", "If the groups wont drop down click": "如果无法下拉组，点击", "to fix the issue.": "修复", "Dry Run": "试运行", "Dismiss": "屏蔽", "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", "Seeds": "随机种子", "Source embedding to convert": "用于转换的源 Embedding", "Embedding token": "Embedding 的词元(Token) / 关键词", "Pick every n-th frame": "每 n 帧挑选 1 帧", "Video drop last frame": "丢弃视频最后一帧", "Make Zip when Save?": "保存时创建zip压缩文件?", "Masking mode": "蒙版模式", "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)", "SwinIR_4x": "SwinIR 4x", "Use negative embedding (DreamArtist)": "使用反向 Embedding (梦作家)", "CFG scale": "提示词相关性(CFG Scale)", "API Keys": "API 密钥", "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", "Original Deforum Github repo github.com/deforum/stable-diffusion": "原始 Deforum Github 仓库 github.com/deforum/stable-diffusion", "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", "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", "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", "Math keyframing explanation docs.google.com/document/d/1pfW1PwbDIuW0cv-dnuyYj1UzPqe23BlSLTJsqazffXM/edit?usp=sharing": "数学关键帧(Math keyframing)解释 docs.google.com/document/d/1pfW1PwbDIuW0cv-dnuyYj1UzPqe23BlSLTJsqazffXM/edit?usp=sharing", "Half": "一半", "Load Params": "载入参数", "Train Model": "训练模型", "Training Steps": "训练迭代步数", "Instance prompt": "实例(Instance)提示词", "Existing Prompt Contents": "现存的提示词内容", "Instance Token + Description": "实例的词元(Token) + 描述", "Class Token + Description": "类的词元(Token) + 描述", "Instance Token + Class Token + Description": "实例的词元 + 类的词元 + 描述", "Instance token to swap": "要互换的实例的词元(Token)", "Class token(s) to swap, can be comma-separated": "要互换的类的词元(Token)，可以是以英文逗号分割的", "Scale Learning Rate": "缩放学习率", "Save Checkpoint Frequency": "保存模型权重进度(ckpt)的频率", "Save Preview(s) Frequency": "保存预览的频率", "Sample Image Negative Prompt": "样本图像的反向提示词", "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", "Train Text Encoder": "训练文本编码器", "Train EMA": "训练 EMA", "# Training Epochs": "训练多少期(Epochs)", "Training Epochs": "训练多少期(Epochs)", "Adam Weight Decay": "Adam 权重衰减(Weight Decay)", "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(Max Grad Norms)", "Max Token Length (Requires Pad Tokens for > 75)": "最大词元(Token)长度 (词元(Token) > 75 时会进行留空)", "Split over-sized images": "分割过大的图像", "Max Caption length (0=unlimited)": "最大描述长度 (0 为无限制)", "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", "Output type": "输出类型", "Flatfile": "纯文字文件", "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。", "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)", "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…", "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", "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", "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(ckpt)", "Generate a checkpoint at the current training level.": "生成当前训练级别的模型权重进度(ckpt)", "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(ckpt)", "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(token)", "The source checkpoint to extract for training.": "用于训练的要提取的源模型(ckpt)", "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(prior preservation)", "Calculate training parameters for a non-human subject. Disables prior preservation.": "计算训练非人物主体需要的参数。并禁用先验存留(prior preservation)", "Total number of training steps to perform. If provided, overrides num_train_epochs.": "要执行的训练迭代步数总数。如果填了，则覆盖 '训练多少期(num_train_epochs)'", "Train 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", "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", "Total number of classification/regularization images to use. If no images exist, they will be generated. Set to 0 to disable prior preservation.": "要使用的分类/规范化图像总数。如果没有图像，就生成一些。设置为 0 以禁用先验存留(prior preservation)", "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", "Scale the learning rate by the number of GPUs, gradient accumulation steps, and batch size.": "通过 GPU 数量、梯度累加步数(gradient accumulation steps)和每批数量(batch size)来缩放学习率", "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", "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(ckpt)", "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(VRAM)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(VRAM)的 GPU", "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(latents)没有被缓存时，你会节省一点显存(VRAM)，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(VRAM)", "Enable this to save VRAM.": "启用此项以节省显存(VRAM)", "Don't checkpoint the gradients, Duh. Set to False to slightly increase speed at the cost of a bit of VRAM.": "保存权重进度时不要保存梯度，啊不废话。设置为 False 以消耗一点显存(VRAM)为代价略微提高速度", "Set this to 2 to increase speed?": "将此设置为 2 以提高速度？", "You probably want this to be 'fp16'.": "如果你想要设置为半精度(fp16)的话", "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(Max Gradient norms)", "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 Name to replace class with in cations": "描述文本中要替换类(class)的主体名(subject)", "/path/to/images/* or /path/to/images/**/*": "/图像/的/路径/* 或 /图像/的/路径/**/*", "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime], [datetime