此lora可以提升对提示词的准确度、增加细节、色彩更鮮豔、提升美感。
This lora can improve the accuracy of prompt words, increase details, make colors more vivid, and enhance beauty.
--
lora权重请从0.1开始，依序增加0.01，请勿超过0.2，超过0.2将会过拟合。权重每增加0.01就会对图片产生影响。
(某些检查站权重可以超过0.2，请基于你使用的检查站来调整权重。)
Please start the lora weight from 0.1 and increase it by 0.01 in sequence. Do not exceed 0.2. Exceeding 0.2 will cause over-fitting. Every 0.01 increase in weight will have an impact on the image.
(Some checkpoint weights can be higher than 0.2, adjust the weights based on the checkpoints you use.)
--
这是"LoRA"不是检查站。
This is "LoRA" not a checkpoint.
--
我使用的档案尺寸较大的lora提取方式，介意档案尺寸较大的人请勿下载。
I use the lora extraction method with a larger file size. People who mind the larger file size should not download it.
--
My other checkpoints and Lora.
--
--
--
Negative prompt for NoobAI-XL。
--
我只有在” civitai”发布我的模型和lora，其余的地方皆是盗用。
I only publish my models and lora on ” civitai” , the rest are all stolen.
--
面部局部重绘可使用adetailer或sd-face-editor.
高解析度放大可使用"ultimate SD upscale".
--
For partial facial redrawing,adetailer orsd-face-editor can be used.
High resolution upscaling can be done using "ultimate SD upscale".
--
客製化lora:我的Telegram ID:@iamddtla0620
我的微信ID:iamddtla
我的line ID:iamddtla
时间宝贵，请直接说明来意，例如:订制LORA.
Customized lora: My Telegram ID: @iamddtla0620
My WeChat ID: iamddtla
My Line ID: iamddtla
Time is precious, please state your intention directly, for example: customized LORA.
V1-Slow版本生成图片速度较慢，美感较佳。
V1-Fast版本生成图片速度较快，美感比V1-Slow版本低。
The V1-Slow version generates images more slowly, but has better aesthetics.
The V1-Fast version generates images more quickly, but has lower aesthetics than the V1-Slow version.
--
--
--
Negative prompt for NoobAI-XL。
--
Files
pornmaster-Aesthetics-fast-v1-lora.safetensors