我的其他检查站和Lora。
My other checkpoints and Lora.
--
--
反推提示词工具(Reverse prompt word tool):"JoyCaption Alpha One"
SDXL 1.0 藝術研究。(SDXL 1.0 Artistic Studies)
--
使用自然语言并且混合"danbooru"标签时，能获得更好的效果。
Better results are achieved when using natural language and mixing in "danbooru" tags.
--
模型介绍为中英双语，中文用户可以关闭翻译。
--
如果你想在我的模型上發布你的作品，可以一次在同一個post發布20張圖片，如果是優秀的作品我就能將其頂至在展示圖片的最上方。
"If you want to post your work on my model, you can upload up to 20 images in a single post. If the work is outstanding, I can feature it at the top of the displayed images."
--
如果你喜欢我的模型，可以用"buzz"鼓励我。
If you like my model, you can encourage me with "buzz".
---
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.
--
由於許多人在問我如何脫衣的問題，我開放一對一收費的脫衣教學，透过视讯教学，30分钟学会，台币3000元，想學習的請加入我的Telegram ID:@iamddtla0620
--
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.
--
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".
Description
此版本为SD1.5模型(This version is the SD1.5 model):
1.此版本主要用于生成亚洲女性-例如:中国、日本、韩国等美女、成人偶像、角色扮演、汉服、中国传统服装。适合训练亚洲女性lora。如果你只打算生成亚洲女性图片请使用此版本。
2.你可以尝试生成1024解析度的图片。在1024解析度时，将更容易生成良好手指。要生成站立的全身图片，也建议生成高度为1024解析度的图片。
3.完全的重新合并，合并的模型皆为”培训(Checkpoint Trained)”的模型，并免合并混和”(CHECKPOINT MERGE)”的模型。没有任何lora的合并。
4.模型挑选高品质模型、高解析度的模型、或是具有大量培训数据的模型。
5.合并中的模型包含使用GPT4V、Cogvqa、Cogvlm、WD1.4进行标记提示词。
6.可使用自然语言与danbooru标签。
7.为了生成良好图片，请学习使用”ADetailer”、 inpainting、ControlNet 等基本技巧。
--
1.This version is mainly used to generate Asian women - for example: Chinese, Japanese, Korean and other beauties, adult idols, role-playing, Hanfu, traditional Chinese clothing.Suitable for training Asian women lora.Please use this version if you only plan to generate images of Asian women.
2.You can try to generate 1024 resolution images. At 1024 resolution, it will be easier to generate good fingers. To generate standing full-body images, it is also recommended to generate images with a high resolution of 1024.
3.Complete re-merge, all merged models are "Checkpoint Trained" models, and no "CHECKPOINT MERGE" models are merged. There is no merging of any lora.
4.Model selection: high-quality models, high-resolution models, or models with a large amount of training data.
5.The model being merged includes using GPT4V, Cogvqa, Cogvlm, and WD1.4 to mark prompt words.
6.Natural language and danbooru tags can be used.
7. To generate good pictures, please learn basic techniques such as using "ADetailer", inpainting, ControlNet, etc.