交流Q群：950351015，欢迎来玩，互通有无。
图图的情趣制服（蕾丝半透旗袍）
这算是情趣制服系列的第一个LORA.
后面我还会做一系列的服装系LORA.
这个衣服的原型其实就是个情趣制服，全部采用实拍然后修图，1024*1024尺寸+bf16，细节拉满，我也想试试用差异提取法做衣服效果怎么样。
实践证明，效果很不错。比丝袜的效果更好，主要提现在还原度比较高，污染少，丝袜有时候还会对画面其他内容产生污染，但是衣服的话污染就非常少了。
这件衣服因为是第一次制作，主要还是因为蕾丝本身细节太多，SD1.5的分辨率还是不够高，细节还是不太行，我可能会多做点其他类型的制服。
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。
为了方便使用，以后我制作的LORA触发词全部都是tutututu,四个tu。
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、如果对其他服装以及环境没有任何描述，LORA可能会对环境有一些影响。但是如果加了描述词后，影响就会降低。
4、触发词为：tutututu, see-through, cheongsam,起手可以设置为：
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 (CFG Scale)可以从7开始尝试。
7、LoRA Block Weight (LoRA 区块权重配置)我没有用。也可以打开试试？
8、目前尝试的大模型比较好的有，墨幽系列，麦橘系列，似乎对真人模型更加友好。对于不同的大模型，需要对参数进行调试。
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！
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、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！
2、权重调高以后图片出现大面积马赛克怎么办？
尝试调低权重，或者降低其他LORA的权重，或者打开LoRA Block Weight插件。
3、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）
Tutu’s sexy uniform (lace semi-transparent cheongsam)
This is the first LORA in the sexy uniform series.
I will also make a series of clothing-based LORA later.
The prototype of this dress is actually a sexy uniform, all taken from real photos and then retouched, 1024*1024 size + bf16, full of details. I also want to try using the difference extraction method to make clothes.
Practice has proved that the effect is very good. The effect is better than that of stockings, mainly due to the relatively high degree of restoration and less pollution. Stockings sometimes pollute other content in the picture, but clothes have very little pollution.
This is the first time I have made this dress, mainly because the lace itself has too many details. The resolution of SD1.5 is still not high enough, and the details are still not good enough. I may make more other types of uniforms.
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.
For ease of use, all the LORA trigger words I create in the future will be tutututu, four tu.
Instructions:
1. Make sure you use LORA correctly.
2. It is recommended that the number of CLIP termination layers be set to 2.
3. If there is no description of other clothing and the environment, LORA may have some impact on the environment. But if descriptors are added, the impact will be reduced.
4. The trigger words are: tutututu, see-through, cheongsam. The starting move can be set to:
5. Don’t add too many negatives, otherwise it will affect the effect of LORA.
6. The prompt word guidance coefficient (CFG Scale) can be tried starting from 7.
7. I have no use for LoRA Block Weight (LoRA block weight configuration). Can you also try opening it?
8. The better large models currently being tried include the Moyou series and the Maiju series, which seem to be more friendly to real-life models. For different large models, parameters need to be debugged.
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!
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. 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!
2. What should I do if a large mosaic appears in the image after the weight is increased?
Try to lower the weight, or reduce the weight of other LORA, or open the LoRA Block Weight plug-in.
3. 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)