我们需要真正理解女性年龄的模型而不是只能生成萝莉！
We need a model that truly understands female age, not one that only generates "loli"!
所以这是一个旨在生成成熟女性并且试图理解多样的女性年龄，而不是只能生成小孩、女孩、萝莉的模型。
Therefore, this is a model designed to generate mature female and attempts to understand the diverse ages of women, rather than only generating "children, girls, or loli."
我的推特:@ekll01
My Twitter: @ekll01
版本说明请查看About this version
Please see "About this version" for the version description.
Please refer to the workflow that I have disclosed.
目前支持的年龄tag
女性：lxlx、mesugaki、bishoujo、lady、mature lady
男性：shxtx、bishounen、gentleman
请您用以上tag代替1girl、1boy。
Currently Supported Age Tags
For females: lxlx, mesugaki, bishoujo, lady, mature lady
For males: shxtx, bishounen, gentleman
Please use these tags instead of 1girl or 1boy.
Recommended Settings（general）
CFG: 5
Steps: 40
Sampling: Euler a
Scheduler: simple
Resolution: 832*1216 above
希望喜欢这个模型的朋友能够量力为模型进行一下Bid投资。这不是请求，但是如果有人能够帮助模型进行Bid，我会十分感谢！
I hope that friends who like this model can consider making a "Bid" investment in the model according to their ability. This is not a request, but I would be very grateful if someone could help the model with a "Bid."
Description
Base it on my new model, "GrownRuler," adjust the age and add some "Sexy element".
Differences from the TWO versions: stronger prompt word understanding, more variety, more restore artist tag. (As literally, this is an experiment version, there are still problems, and the resulting picture is not necessarily better than the TWO version.)
以我的新模型“GrownRuler”为基底，调整年龄，加入一些“油腻感”。
与TWO版本的区别：更强的提示词理解力、更多的多样性、更还原的画师tag。修正一些问题，比如TWO版本无法生成cyan_skin等等。（如字面意思，这是一个experiment版本，仍然存在问题，生成的图片并不一定比TWO版本好。）
FAQ
Comments (27)
实验版本已发布！
祝大家新年快乐！
Happy New Year. Whether it's Chinese New Year or New Year, happy things are always happy.
新年快樂 身體健康!!
@kurodahuga843 thank you
@Kisaku_KK77 谢谢
Dear Author
When a round window (round window) is specified, a lattice that should not have been specified is depicted. Is this a quirk of the training data?
Do you mean when "round window" is added to the prompt word
@EKLL Translation and typo. Sorry.
Why is it that when you add a round window to a prompt, a lattice is formed? This was the content.
@kurodahuga843 Sorry, there are errors in the exp version, and the question you asked should be one of them
We need adult Grown female, not minors (not girls/lolis)!
We need adult Grown female, not minors (not girls/lolis)!
x2
从初版到two，我都有测试，结果最理想的0.3，后面的男性都会变成中老年，而且无法跑出mmf或者n+ boys（我不是跑男同，而是跑gangbang），结果只有自己加上 controlnet，虽然我喜欢成熟女性，但多男性很尴尬跑NSFW很蛋疼，期待未来有所改善。
不好意思，数据集中女性年龄对比男性年龄实在偏小了，举个不恰当的例子：女性外表年龄平均10岁，男性平均20岁，在这个基础上，把年龄加大，结果就是女性加到20岁，男性就30了。我自己也是知道这个问题，加上one版本之后的目标是更具多样性和更多的知识，所以目前正在通过建立另一个模型Grown Ruler作为基底重新构筑配方来试图解决Mature ritual存在的问题。
hey man m gonna be honest. M.R. 0.3 version is still the best imo. its crazy how epic that version is. if you could just make another version of 0.3, which would focus on generating mature girls (age between 20 to 28) and not fully milf, then that model would be epic as hell. that version is easy to use, it follows the artist tags well and its pretty good with hands as well. so yeah, just wanted to lay out my thoughts. cheers.
I do think about it, maybe I do too much addition, it's time to do a little subtraction.
@EKLL I like v0.2, there are very juicy women there, I haven't met better ones yet.
@Gerasim thank you
@Gerasim Totally agree, I only generate with 0.2. The juicy has no competition with any other checkpoint.
@InMyDarkMind But 0.2 knowledge base and tag comprehension... I will consider making a version of 0.2EXP
@EKLL I love your checkpoint! It's true the newer models follow the prompt closer and have a better anatomy understanding. That said 0.2 is like a car with too much horse power, hard to drive but sure is fast af :D I have to make more generations as sometimes the anatomy is weird and the faces are a weak point but the results sure have character!
The newer ones don't make the poses as dynamic, colors as vibrant. juicy as juicy as 0.2 imo and look closer to the other illustrious checkpoints. This could be good for adding your own style/poses, Loras but I'm no expert. It could be cool if you can capture the vibrant/color, oily/shiny, juicy look of 0.2 into a Lora as an addon to the newer models.
@InMyDarkMind Thank you for your use! I've decided to do another version of 0.3EXP, but I need to take a few days off before I start working on it.
I can't stop using this model. I love the mature sexy milf style since we have enough young anime girls. TWO is amazing and I've been using it for the past few days with amazing results. Thank you so much for this!
Thank you for your use, and I hope you can help promote it more. I need more downloads and like
EXP version has a strong predefined style, it influences other styles - even those that were strong in previous versions (and in other Illustrious models). It's not bad per se, it just feels like a LoRa was built into it.
Style dependent lora is not used
@EKLL I know, it just looks like some particular style was dominant in the new dataset. I'll upload my own examples, but you can notice it even on existing examples by other users.
@dobomex761604 Perhaps influenced by "masterpiece"? I'm not sure at the moment, or maybe there are too few pictures of adult women, so it's more concentrated. It is recommended to match the style lora and artist tags for a while.