禁止使用此模型进行一切商务及违法行为，禁止随意转载，仅作为成果分享，违者后果自负！
（我的QQ群：235392155，Lora代练、ckpt融合调整加我qq：2402799912）
我在国内站tusi.art和liblibai.com里也都有模型，按平台的创作激励会有所不同，还请多多关注支持！（我会再此模型的示例图中公示一部分的图出来）
【闲鱼】https://m.tb.cn/h.5V7ITvv?tk=eY01dB4UcnH
这是我的爱发电，补贴一下电费QAQ，感谢您的支持~
一、模型特征概述
V3：
一、更新操作：
1、利用MBW插件，通过穷举法融合了部分basil mix的输入层和中间层
2、利用MBW插件，通过穷举法以非常低的权重融合了部分模型的输出层
二、更新效果：
1、提高了tag的准确度
2、提高了饱和度，增强了画面的真实质感
3、提高了光影效果
4、提高了肢体的准确率
5、提高了角色lora的还原度
三、注意事项
1、建议使用vae：animevae，防止过度饱和（画廊示例图分别为此vae和84000）
2、对tag把握更准确也意味着对tag的书写要求会更高，若V3难上手可以尝试V2或V1版本
V2：
（若只喜欢成熟的肌肉男性或希望使用更简单可以尝试V1版本）
一、更新操作：
1、将NovelAI原版VAE替换了模型内VAE
2、穷举法更换了ckpt内的clip模型
3、与V1未融合lora版本进行融合
二、更新效果：
1、提升了tag的准确度
2、提升了构图质量
3、减轻了融合lora导致的形象固定
4、减轻了对于部分tag的过高权重
V1:
1、泛化型融合模型，能对应tag跑出多种画风，具有很高的跑图下限、tag准确性，并且从返图区还能看到他一大能力^v^
2、对人体塑造能力很强，肢体至今未遇到崩坏情况，手部、脚部崩坏几率很小
3、融合时特意避开对脸部的影响，所以脸部没有固化，很适合搭配角色lora
4、无clip偏移问题
5、因为unet有些过拟合导致某些tag不听使唤
二、跑图建议
（具体可以看封面图片的各类参数，不同VAE有不同的效果，我还喜欢开Face Editor插件）
1、因为融了相当一部分真人模，使用跑图时可以尝试和跑真人底膜一样的参数，但依然非常不建议使用面部修复
2、可以在跑图时加点质量词，它们是有用的。如果你希望他看起来更逼真立体，用一些与写实、光影相关的tag
3、可以多多尝试在同一tag下，clip跳过层为1和2的实际出图情况
4、方图、长图、宽图表现都不差，可以随意调整画布大小
5、尝试使用高分辨率修复，不建议使用面部修复
6、请多多点赞、返图、评论、5星哦~
三、融合采用模型
（我无法确定是否是这些，仅当参考）
LORA：（总共权重为0.3）
Animale LoRa - Animale LoRa v1 | Stable Diffusion LoRA | Civitai
AIroticArt's Penis Model (LoRA) - v1.0 LoRA | Stable Diffusion LoRA | Civitai
CKPT：
AbyssOrangeMix2 - NSFW - AbyssOrangeMix2_nsfw | Stable Diffusion Checkpoint | Civitai
maturemalemix - v1.2 | Stable Diffusion Checkpoint | Civitai
YaoiGen - YaoiGen v0.4.4 | Stable Diffusion Checkpoint | Civitai
Plazm Men - Plazm v1.0 | Stable Diffusion Checkpoint | Civitai
HomoDiffusion (gay) - Homo Diffusion v1.0 FP32 | Stable Diffusion Checkpoint | Civitai
四、给予访客使用模型的一些建议与回答
（English translation below）
（作为一个外行人，虽然没有经历过美术和ai的专业课学习，但我仍然在不断努力学习探索，并与各位大佬交流心得。我对自己在意的事情有着很高的精神洁癖，因此我希望能在自己的一亩三分地里传达正确的ai知识。这些在下方文档里都有，仅作为遇到的问题单独回答。）
1、LORA
对于动漫角色lora而言，最好的权重便是1。虽然我们能通过改变权重的方式来改善拟合，但改变权重会额外产生一些不好影响。比如：c站动漫角色lora大多数都过拟合，而为了改善这一现象往往会推荐降低权重到0.6/0.8，而这一举动会导致角色失去部分原本的外貌特征
过拟合通俗解释：过分训练导致的lora表现僵化，如人物不听tag话甚至出原本素材的图
2、CKP
clip偏移和unet过拟合都会导致模型不听tag话
clip偏移会导致tag识别问题，c站有相当一部分模型存在此问题而不自知，如果你感兴趣，在下面的“其他”里我会给予检查及简单修复的途径
unet过拟合也会让模型僵化，不听tag使唤，甚至在无tag的情况下跑出好看的图片，这也是过拟合吐原图的情况
融合类ckpt能够很好的提高模型出图的下限，但融合模型对于tag的权重是很乱的，因此会各具“特色”，同样，基于此类模型训练的lora很难在其他模型上适用
如果你希望大模型对于lora及其他模型的接纳程度更好就尽量不要再融合ckp模型时融合lora，或者和我一样在权衡之下融入以较低权重修正不尽人意的部分
3、VAE
CKP自身就有一个VAE，外挂VAE不是用于额外的增加，而是用于替换
VAE只是最直观的是饱和度变化，这并非VAE功能的全部，就对于跑图而言还会改变构图、细节等等
4、其他
模型占内存大的不一定好，很多模型内有一堆无用数据，下载完全浪费流量内存
示例图的好坏不能确定模型质量，除了基于作者本身审美外，你无法确定他用了多少模型、插件的辅助，你也无法确定他文生图跑了几次、图生图跑了几次
下载量与点赞也不能确定模型质量，点赞量基于下载量，而下载量会和作者名气、封面图片受众、模型角色人气、模型画风受众、模型类型受众等等相关
模型并非版本最新为最好，很多时候是基于某一版本的不同方向的调整。甚至有部分作者为了通过更新的推送而蹭到更多的下载量而恶意刷更新，实际使用下来模型的质量不过是在原地迂回踏步
其他更为专业详细的知识请看万象熔炉 | Anything V5/Ink的简介部分，关于clip偏移的检验修复的扩展链接在此文档前段部分中
模型链接：万象熔炉 | Anything V5/Ink - V3.2++[ink] | Stable Diffusion Checkpoint | Civitai
4. Suggestions and Answers for Model Usage by Visitors:
(As a layperson without formal education in art and AI, though I have been continuously learning and exploring, and exchanging experiences with various experts. I hold a strong commitment to accuracy in matters that concern me, and thus I aim to convey correct AI knowledge in my space. The details are found in the document below and are provided only for separately addressing encountered issues.)
1. LORA:
For anime character LORA, the ideal weight is 1. While we can improve fitting by adjusting weights, this can have additional undesirable effects. For instance: On certain image-sharing sites, many anime character LORAs are overfitted. To mitigate this, weight reduction to 0.6/0.8 is often recommended. However, this may result in characters losing some of their original features.
Simplified explanation of overfitting: Excessive training leads to stiff LORA performance, causing characters to not adhere to tags, or even generating images unrelated to the input material.
2. CKP:
Both clip offset and unet overfitting can cause models to not adhere to tags.
Clip offset leads to tag recognition issues. Many models on certain platforms have this problem unknowingly. If interested, I will provide ways to check and repair this in the "Other" section below.
Unet overfitting can also result in stiffness, not following tags, or even generating appealing images without any tags. This situation is when the overfitting produces images that are nearly identical to the original material.
Fusion-style ckpt models can enhance the lower limit of image generation quality. However, the tag weights in fusion models tend to be disorganized, resulting in diverse "characteristics." Similarly, LORAs trained based on such models are less compatible with other models.
If you want larger models to integrate LORA and other models better, avoid fusing LORA when merging ckp models. Alternatively, consider, as I have, incorporating underwhelming parts with lower weights in your fusion process.
3. VAE:
CKP itself has a VAE. External VAEs are meant to replace, not supplement, it.
The most immediate effect of a VAE is saturation alteration. However, this is not the entirety of its function; it can also impact composition, details, and more when generating images.
4. Other:
Models with large memory consumption aren't necessarily superior; many contain extraneous data, wasting bandwidth and memory.
The quality of sample images doesn't definitively determine model quality. Besides the author's aesthetic preferences, you cannot ascertain how many models, plugins, and iterations were involved. Download counts and likes are not definitive measures either; likes are often linked to downloads, which are influenced by the author's reputation, cover image appeal, character popularity, art style compatibility, and audience type.
Newer versions of models are not always superior. Often, adjustments are made based on different directions within a specific version. In fact, some authors maliciously exploit updates for increased downloads. In practice, the quality of the model only treads in place.
For more specialized and detailed knowledge, please refer to the introduction section of "万象熔炉 | Anything V5/Ink." Expanded links for examining and repairing clip offset issues are located in the earlier part of this document.
Description
FAQ
Comments (28)
sadly, i feel pity when you said it the final version
哈哈哈，没事的~
此模型在融合后就有很高的下限了，我后来也是尽己所能完善其中的各种不足之处，尽可能让它成为一个真正高质量的模型，而非无止境的更迭……
作为画图大模型，我已经完成了绝大部分，剩下的最后一步，作为使用者的彼此，我们可以利用其他的小模型来创造出我们心仪的图画。毕竟无论是角色、构图、画风，我无法让所有人都喜欢，但我可以让这个大模型乖乖听话~
作为作者，我和anythingV5等作者一样，并不想浪费访客的时间和流量，用一堆低质量的模型或者原地踏步式的更新来谋取下载量、点赞量等。
在未来，我会带来更多我能力范围内并且足够质量的模型，还希望您能多多支持！^v^
（悄悄说一句，您的模型很好看，很有艺术气息，我真的很喜欢！^v^）
我能改进的我已经尽力改的差不多啦，上版本不是完全上位替代可自行尝试！
大佬你是我的神！！！非常感谢！！！
I don't have any images I can post at the moment, but I really like this model. It gives me some nice boys. It may not become my favorite model for boys, but I'll be using it quite a bit anyway. I'll post a review+images when I can.
谢谢·！期待您的艺术创作~
So... This did become my favorite model for boys! I'll post some images soon, but almost everything I create now is down with this checkpoint. It's so easy to work with, and the results are always pleasing!
@dita
没事没事，您随意，开心就好~
No problem, it's okay. Feel free, as long as you're happy
kinda hard to find male model so i rly love this one
有没有两个男孩的模型
木有哎，稳定多人的话其实可以试试女模，出正太还是可以的
the male banana on top of cute cute boy faces this model generates is just sooo perfect! i love it so much. thank you for your hardwork!
请问之前上传的anythingqingmix realistic版本的还会重新上传吗？昨天被效果惊艳了但今天再找却找不到了
怎么说呢，作为模型作者其实很担心搞真人向或者画师画风的相关东西，尤其是和R18相关的，虽然我只是因为感兴趣而广涉猎，但是很有可能会因为使用者而出事……我再考虑考虑吧……
@_Qing_ 感谢作者的再次上传，希望你的心意能被使用者尊重
Was this recently updated and then the update was taken down?
不是，下架的是一个亚洲男性真人向的模型，考虑到危险性而下架了
@_Qing_ Well, it looked great. I wish I'd downloaded it when I had the chance. Are you considering doing a remake without the real life male model?
@DarkZephyr 哎……主要是真人类的模型很容易被个别别有用心的人拿去干坏事，也容易被那些反对ai的人抨击……我想着多一事不如少一事就很快下架了，如果以后有缘我会再上架的。^v^
我的模型还是以动漫为主（画师画风除外），也会尝试各种不同方式训练lora。我最近就在尝试直接训练tag来制作一个lora，就如同这个Neg4All！Both Positive High quality、Details and Negative worse quality、bad hand in one LoRA！ - v3.5 | Stable Diffusion LyCORIS | Civitai
但这个训练起来时间非常久，而且我所有的炼丹都是在云端租借电脑训练的，不断试错就会有点烧钱……总之我再多试试，还是那样，我会分享一些有趣且质量好的模型，还请多多期待哦~
@_Qing_ Thanks!
_Qing_:
我认为将第四部分（"给予访客使用模型的一些建议与回答"）单独发布为一篇新的文章在 CivitAI 上是一个好主意。您在那里分享了如此多有价值的信息，我认为更多的人需要阅读。很不幸，由于这种模型的类型，只有少数人会看到这个页面，所以您应该将这些信息放到一个新的页面上。
我从您在那里写的内容中学到了很多。我确信其他人也可以。我认为您可能在所有方面都是对的，特别是过拟合和融合模型的问题。
如果您愿意，我在下面包含了英文版本，这是我让 ChatGPT 翻译的。请随意将其包含在这个页面上，以及您希望的任何其他页面上。我不能保证它完全正确，但 ChatGPT 在翻译其他语言（比如日语）时做得很好，所以意思应该是正确的。
最后，非常感谢您提供这个模型。我比任何其他大型模型/CKP都要经常使用它。您创造了一个非常出色的模型。它易于操作并且效果非常好。我不胜感激。我会尽快尝试发布更多的图片和评论。
4. Suggestions and Answers for Model Usage by Visitors:
(As a layperson without formal education in art and AI, though I have been continuously learning and exploring, and exchanging experiences with various experts. I hold a strong commitment to accuracy in matters that concern me, and thus I aim to convey correct AI knowledge in my space. The details are found in the document below and are provided only for separately addressing encountered issues.)
1. LORA:
For anime character LORA, the ideal weight is 1. While we can improve fitting by adjusting weights, this can have additional undesirable effects. For instance: On certain image-sharing sites, many anime character LORAs are overfitted. To mitigate this, weight reduction to 0.6/0.8 is often recommended. However, this may result in characters losing some of their original features.
Simplified explanation of overfitting: Excessive training leads to stiff LORA performance, causing characters to not adhere to tags, or even generating images unrelated to the input material.
2. CKP:
Both clip offset and unet overfitting can cause models to not adhere to tags.
Clip offset leads to tag recognition issues. Many models on certain platforms have this problem unknowingly. If interested, I will provide ways to check and repair this in the "Other" section below.
Unet overfitting can also result in stiffness, not following tags, or even generating appealing images without any tags. This situation is when the overfitting produces images that are nearly identical to the original material.
Fusion-style ckpt models can enhance the lower limit of image generation quality. However, the tag weights in fusion models tend to be disorganized, resulting in diverse "characteristics." Similarly, LORAs trained based on such models are less compatible with other models.
If you want larger models to integrate LORA and other models better, avoid fusing LORA when merging ckp models. Alternatively, consider, as I have, incorporating underwhelming parts with lower weights in your fusion process.
3. VAE:
CKP itself has a VAE. External VAEs are meant to replace, not supplement, it.
The most immediate effect of a VAE is saturation alteration. However, this is not the entirety of its function; it can also impact composition, details, and more when generating images.
4. Other:
Models with large memory consumption aren't necessarily superior; many contain extraneous data, wasting bandwidth and memory.
The quality of sample images doesn't definitively determine model quality. Besides the author's aesthetic preferences, you cannot ascertain how many models, plugins, and iterations were involved. Download counts and likes are not definitive measures either; likes are often linked to downloads, which are influenced by the author's reputation, cover image appeal, character popularity, art style compatibility, and audience type.
Newer versions of models are not always superior. Often, adjustments are made based on different directions within a specific version. In fact, some authors maliciously exploit updates for increased downloads. In practice, the quality of the model only treads in place.
For more specialized and detailed knowledge, please refer to the introduction section of "万象熔炉 | Anything V5/Ink." Expanded links for examining and repairing clip offset issues are located in the earlier part of this document.
哇！谢谢您的帮助！太感谢了！我其实有发布过这篇文章，只是看得人很少……但有您的翻译，我相信会有更多人看见！希望大家都能从中得到帮助，从而制造出自己理想的图片和模型
@_Qing_ 我很高兴能帮忙。我觉得这是非常有价值的信息，应该分享出去，希望更多人能在英文版中阅读。不是吗，AnythingQing 是基于这些信息制作的吗？我可以感觉到它比我从 CivitAI 下载的大多数模型都更高质量。它对我的提示反应良好，没有抵抗我。:-D 还要感谢您分享它。我每天都在使用。
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.