Get early access to build and test build, be able to try all epochs and test them by yourself on Pat

If you want flexible one > Use V.2 If you just want Cool one > Use V.1 It's fun using this V.2 with

我的社交平台，抖音和B站同名都叫娜乌斯嘉！也可以加入我的qq群一起交流! 一群:321159940 二群:554810562 V1版本：权重推荐0.6-0.7 V1.1版本：权重推荐0.8 V2.0版

weight 0.7 is best. outfit1 sama1, tiara, sailor senshi uniform, white gloves, red sailor collar, re

Realistic Yae Miko from Genshin Impact. All samples generate with Ulzzang-6500 " embeddings, "vae-ft

AI净土交流群电报：https://t.me/+soU-Ws67aBlkY2I1 凯登AI私模定制咨询电报：https://t.me/+Ql4sngcJlbhmOTU1 个人吐司主页：https://

Mix from koreanDollLikeness_v10 and something I trained, work with Chilloutmix. Making models takes

Studio Ghibli style LoRA Making models can be expensive. Do you like what I do? Consider supporting

It is merged based on the flat illustration model that I failed to train before. Now this model is m

I am going to add various emotion sliders here so they will all be in one place. In general, the wei

? Which will you choose? Try all 5 quintuplets in this single small Lora. Prompt them by name, and c

Weights can swing very far on this one -8.0 to +8.0. It can do extremely large crowds the higher you

曾经沧海难为水，除却巫山不是云。 If there are no clouds in the mountains, then the mountains are not mountains. If t

XSArchi_127新科幻Neo Sci-Fi 使用建议: 模型包含了所有科幻场景和细分风格，通过输入prompt就可以调用想要表现的风格数据。 新的模型功能：能够完美使用自然语言描述进行出图！大家

Creating this lora is just to meet your own needs, and you can download and use it if you have the s

Now, something completely different. With all the konyconi-style LoRAs, I started to feel as a one-t

(Still WIP, Do not recommend using this now unless you want to test it) Trained with animefull. ※ 0.

这是一个LoRA，用于控制勾线线条，同时尽量保持原图； 增加权重增加勾线粗细，减少权重减少勾线，最高/最低可达2/-2！更多的上限可以探索下。 使用较大权重的时候画面有可能会产生比较大的变化 注意：使

The other day I found a embedding of DAGASI's art style but it was too bad to create some satisfacto

当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 SDK下载 #安装ModelS