Type | |
Stats | 1,267 0 |
Reviews | (268) |
Published | Jan 7, 2024 |
Base Model | |
Trigger Words | tutututu, (nun),(cross necklace), latex bodysuit, shiny clothes, skin tight, habit, latex gloves,black bodysuit,thigh boots, |
Hash | AutoV2 BE3D01B828 |
Tutu’s sexy uniform (Dimension Radio x Latex Clothing PU Nun Uniform)
Communication Q group: 950351015, welcome to play and exchange information.
Telegram: https://t.me/+nbU3j7rLEYZkNzVl
A friend sent me this and asked me if I should try it because it looked pretty good (a friend out of nowhere), so I tried it. I originally planned to buy it to shoot a video, but I got lazy and didn’t make it, so I made a LORA.
Insisting on high-quality LORA production, this LORA is also produced using difference extraction method + real shooting, and the effect is very good when used together with other LORA.
Recently, a lot of optimizations have been done to the entire algorithm and production methods.
However, for this model, the weight can be set smaller. Generally, 0.6 can have a better effect, and there is no need to make it too large.
For ease of use, all the LORA trigger words I create in the future will be tutututu, four tu.
For this LORA, in order to ensure a high degree of restoration, it is recommended to write in the prompt word:
tutututu, (nun), (cross necklace), latex bodysuit, shiny clothes, skin tight, habit, latex gloves, black bodysuit,thigh boots,
All kinds of large models are very friendly, especially good at 2.5D and two-dimensional.
Instructions:
1. Make sure you use LORA correctly.
2. It is recommended that the number of CLIP termination layers be set to 2.
3. The weight depends on the needs. It can range from 0.4 to 0.9. It is recommended to start with 0.6.
4. The trigger words are: tutututu, (nun), (cross necklace), latex bodysuit, shiny clothes, skin tight, habit, latexgloves, blackbodysuit,thighboots,
5. Don’t add too many negatives, otherwise it will affect the effect of LORA.
6. The prompt word guidance coefficient (CFGScale) can be tried starting from 7.
If you encounter problems during use, you can leave me a message.
Looking forward to your work!
Looking forward to your work!
Looking forward to your work!
Hope you have a good time.
Thank you for your long-term trust and support.
statement:
1. You shall bear full responsibility for any creative works using this model.
2. You may not use this model to intentionally create or share illegal or harmful output or content, and avoid using this model for malicious, harmful, defamatory, fraudulent or political purposes.
3. If you use this model for commercial purposes, please inform me, thank you.
common problem:
1. What is differential extraction method?
As the name suggests, simply speaking, it is to extract the differences to make LORA. In the past, our general LORA was trained directly with pictures. In this way, the trained LORA would inevitably be contaminated by the base film and other environmental factors of the picture, so when producing the picture Sometimes it will have unexpected effects on the picture. The LORA produced by the differential extraction method will remove these contaminations. The LORA produced in this way will have almost no influence from factors other than the base film and the target elements. Therefore, even if the weight is set relatively high, the pollution to the picture will be very small. , the model quality will be much higher. The differential extraction method is more complex to make and requires more steps.
2. Why do you want to do this LORA?
Although there are many similar LORAs, I found that on the one hand, most of these LORAs are not very close to reality. Many of the more popular clothing at the moment are not available, and they are not realistic enough.
In addition, the quality is uneven. Many LORAs have a greater impact on the characters themselves and the graphics, making them inconvenient to use. So I plan to make a series of clothing LORA.
3. Why can’t I take photos like yours?
Everyone's computer configuration and operating environment are different, and the LORA and plug-in versions used, plug-in configurations, etc. will also be different, so please don't pursue the same photos and create your own perfect works!
4. How to get in touch?
If you have any need to customize LORA, or have other cooperation intentions, you can leave a message here directly, or contact Q331506796 (indicate your intention)
5. What optimizations have you made to the difference extraction method? Or are you just talking casually?
A: I have done a lot of optimization on the code involved. There are:
1. Automated model exploration: Automatically generate multiple fusion models from a set of models, similar to the automated process of parameter tuning or model selection, but focused on model fusion.
2. Difference analysis based on Euclidean distance: used to compare the weight differences of two LoRA (Low-RankAdaptation) models.
In dissimilarity analysis, Euclidean distance is used to quantify the difference between the weights of two models. Specifically:
Weight representation: The weight of each LoRA model can be regarded as a point in high-dimensional space. Each element of the weight corresponds to a dimension in the space.
Calculate the difference: By calculating the Euclidean distance between the corresponding weights of the two models, we can get a numerical value that represents the relative position difference of the two weights in the high-dimensional space.
Explain the difference: A larger Euclidean distance means the two models are more different in that weight; a smaller distance means they are more similar.
This difference analysis is used to guide model fusion decisions. For example, if two models differ greatly in a certain weight, this weight may need to be specially processed to ensure that the fused model can effectively combine the characteristics of the two original models.
These optimizations are completely based on my own materials. Because my materials have some special characteristics, they are not difference extraction in the traditional sense. There are some trade-offs.
图图的情趣制服(次元电台X乳胶衣PU修女服)
交流Q群:950351015,欢迎来玩,互通有无。
电报:https://t.me/+nbU3j7rLEYZkNzVl
朋友发来说这个挺好看的要不要试一下(无中生友),就试了,本来是打算买来拍视频的,结果临时犯懒没拍成,就做了个LORA
坚持高质量LORA制作,这个LORA也是用差异提取法+实拍制作,和其他LORA一起用效果也非常好。
最近对整个算法以及制作方式进行了大量的优化。
不过对于这个模型,权重可以开小点,一般0.6就能有比较好的效果了,不需要搞的太大。
为了方便使用,以后我制作的LORA触发词全部都是tutututu,四个tu。
对于这个LORA,为了确保高还原度,建议在提示词中写入:
tutututu, (nun),(cross necklace), latex bodysuit, shiny clothes, skin tight, habit, latex gloves,black bodysuit,thigh boots,
各种大模型都很友好,尤其擅长2.5D和二次元。
使用方法:
1、确保你正确的使用LORA.
2、CLIP终止层数建议设置为2.
3、权重看需要,从0.4到0.9都可以,建议0.6开始。
4、触发词为:tutututu, (nun),(cross necklace), latex bodysuit, shiny clothes, skin tight, habit, latexgloves,blackbodysuit,thighboots,
5、负面不要加的太多,否则会对LORA的效果产生影响。
6、提示词引导系数(CFGScale)可以从7开始尝试。
如果您在使用中遇到问题,可以给我留言。
期待您的作品!
期待您的作品!
期待您的作品!
祝你玩的开心。
感谢您长期以来的信任和支持。
声明:
1、您应对使用此模型的任何创意作品承担全部责任。
2、您不能使用该模型故意制作或分享非法或有害的输出或内容,避免将此模型用于恶意、伤害、诽谤、诈骗或政治用途。
3、如果将本模型用于商业用途,请通知我,谢谢。
常见问题:
1、什么是差异提取法?
顾名思义,简单来说就是将差异提取出来制作LORA.以往我们一般的LORA都是拿图直接训练,这样训练出的LORA不可不免的会受到底膜以及画面其他环境因素的污染,所以在出图的时候会对画面产生预料之外的影响。而差异提取法制作的LORA会将这些污染去除掉,这样制作出的LORA几乎不会有来自底膜以及目标元素之外其他因素的影响,所以权重即使开的比较高对画面的污染也很小,模型质量会高很多。差异提取法制作起来更复杂,需要的步骤更多。
2、为什么要做这个LORA?
虽然类似的LORA有很多,但是我发现一方面这种LORA大多数不是很贴近现实,很多当下比较流行的服装并没有,而且不够写实。
另外就是质量方面残次不齐,很多LORA对人物本身以及画面的影响比较大,使用起来不够方便。所以打算做一系列的服装LORA。
3、为什么我出不了和你一样的照片?
每个人的电脑配置以及操作环境都不一样,使用的LORA以及插件版本、插件配置等也会有所区别,所以请不要追求一模一样的照片,创作您自己的完美作品吧!
4、如何取得联系?
如果有定制LORA的需求,或者有其他合作意向,可以直接在这里留言,或者联系Q331506796(注明来意)
5、你对差异提取法做了哪些优化?还是只是随便说说?
答:我对涉及代码进行了大量的优化。主要有:
1、自动化模型探索:自动从一组模型中生成多种融合模型,类似于参数调优或模型选择的自动化过程,但专注于模型融合。
2、基于欧氏距离的差异性分析:用于比较两个LoRA(Low-RankAdaptation)模型的权重差异。
在差异性分析中,欧氏距离用于量化两个模型权重之间的差异。具体来说:
权重表示:每个LoRA模型的权重可以看作是高维空间中的一个点。权重的每个元素对应空间中的一个维度。
计算差异:通过计算两个模型相应权重之间的欧氏距离,我们可以得到一个数值,表示这两个权重在高维空间中的相对位置差异。
解释差异:较大的欧氏距离意味着两个模型在该权重上的差异较大;较小的距离则意味着它们较为相似。
这种差异性分析用于指导模型融合的决策。例如,如果两个模型在某个权重上的差异很大,可能就需要特别处理这个权重,以确保融合后的模型能够有效地结合两个原始模型的特性。
这些优化完全是针对我自己的素材进行的,因为我的素材有一些特殊性,所以不是传统意义上的差异提取,要有一些取舍。