"Checkpoints to cache in RAM":"缓存在内存(RAM)中的模型(ckpt)",
"Hypernetwork strength":"Hypernetwork 强度",
"Apply color correction to img2img results to match original colors.":"对图转图结果应用颜色校正以匹配原始颜色",
"Save a copy of image before applying color correction to img2img results":"在对图转图结果应用颜色校正之前保存图像副本",
"With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising).":"在进行图转图的时候,确切地执行滑块指定的迭代步数(通常更少的降噪会做更少的迭代步数)",
"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",
"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",
"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(通常更少的降噪会做更少的迭代步数)",
"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、更清晰的结果。这可能会改变现有的随机种子。需要重新启动才能应用",
"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] 使其减少关注",
"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",
...
...
@@ -365,16 +365,16 @@
"Increase coherency by padding from the last comma within n tokens when using more than 75 tokens":"当使用超过 75 个 token 时,通过从 n 个 token 中的最后一个逗号填空来提高一致性",
"Filter NSFW content":"过滤成人内容",
"Stop At last layers of CLIP model":"在 CLIP 模型的最后哪一层停下",
"Interrogate Options":"逆向生成提示词选项",
"Interrogate: keep models in VRAM":"逆向生成: 将模型保存在显存(VRAM)中",
"Interrogate: use artists from artists.csv":"逆向生成: 使用 artists.csv 中的艺术家",
"Interrogate: include ranks of model tags matches in results (Has no effect on caption-based interrogators).":"逆向生成: 在生成结果中包含与模型标签(tags)相匹配的等级(对基于生成自然语言描述的逆向生成没有影响)",
"Interrogate: num_beams for BLIP":"逆向生成: BLIP 的 num_beams",
"Interrogate: maximum description length":"逆向生成: 最大描述长度",
"Interrogate Options":"反推提示词选项",
"Interrogate: keep models in VRAM":"反推: 将模型保存在显存(VRAM)中",
"Interrogate: use artists from artists.csv":"反推: 使用 artists.csv 中的艺术家",
"Interrogate: include ranks of model tags matches in results (Has no effect on caption-based interrogators).":"反推: 在生成结果中包含与模型标签(tags)相匹配的等级(对基于生成自然语言描述的反推没有影响)",
"Interrogate: num_beams for BLIP":"反推: BLIP 的 num_beams",
"use spaces for tags in deepbooru":"在 deepbooru 中为标签使用空格",
"escape (\\) brackets in deepbooru (so they are used as literal brackets and not for emphasis)":"在 deepbooru 中使用转义 (\\) 括号(因此它们用作文字括号而不是强调符号)",
"User interface":"用户界面",
...
...
@@ -396,7 +396,7 @@
"Hide samplers in user interface (requires restart)":"在用户界面中隐藏采样器(需要重新启动)",
"eta (noise multiplier) for DDIM":"DDIM 的 eta (噪声倍增器) ",
"eta (noise multiplier) for ancestral samplers":"ancestral 采样器的 eta (噪声倍增器)",
"img2img DDIM discretize":"图转图 DDIM 离散化",
"img2img DDIM discretize":"图生图 DDIM 离散化",
"uniform":"均勻",
"quad":"二阶",
"sigma churn":"sigma churn",
...
...
@@ -456,7 +456,7 @@
"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":"重复处理图像多少次并将其用作下一次迭代的输入",
"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,降噪强度都会乘以该值。<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。图块之间(Tiles)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",
"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",
"A directory on the same machine where the server is running.":"与服务器主机上的目录",
"Leave blank to save images to the default path.":"留空以将图像保存到默认路径",