Model

v2 has improved gacha rate (hopefully)v2 trigger (different from v1 trigger): high heels shoe dangleIt works best with sitting crossed legsConcept LoRA for high heels dangle (h...

人物躺在纸盒箱子、杯子等容器内,权重0.8~1.0(个人推荐1.0),触发词为:in container,但为了更好的出效果,建议额外的添加: box(或其他容器), in box(对应前一个容器tag), sitting(或其他动作)...

A commission of @Zorglub.Anna Kendrick is an American actress and singer, known for her roles in the Pitch Perfect film series and Up in the Air, among many others.First of all...

特殊衣服系列，1-20发布在橱窗Special clothing collection, 1-20 released in the window我只是一名业余的SD爱好者，每天需要花很多的时间去寻找素材，抠图，制作，测试，最后再发布,这耗...

2D游戏地图场景推荐搭配模型：蔚蓝BlueSDXL_GHDT - RH蔚蓝Blue（XL原神torino画风） - 2.0精简版权重推荐：0.8-1 描述: 训练词语: ...

不知道叫什么名字的表情包，cvitai 搜了几个关键字没找到于是自己练了个,数据来源于吊图吧 & Pixiv,推荐和角色 LoRA 一起使用，否则默认情况生成的角色可能很大可能会有兽耳,推荐设置 /...

About this modelWelcome to Landscape-Anime-Pro, a custom Stable Diffusion model that can generate stunning images of landscapes and scenery. This model is created by me, Celsia...

Wild_Child V3.0: I wanted to train this version to be "wilder" again, but with more sharpness and contrast. I hope you enjoy the results. If you are looking for consistency, I ...

Train on NAI.Best result with weight between : 0.8-1Prompt activator : sally whitemaneOther prompt : leotard, thighhighs, elbow gloves, runny makeup, pelvic curtainReviews are ...

Note #1: As this is a Lycoris/Locon file, you will need https://github.com/KohakuBlueleaf/a1111-sd-webui-lycoris extension to use the <Lyco> tag. If you want to use the p...

Photo realistic mix (majority Asian girls). To use with my loras. Recommended sampler Euler, 2M Karras, & Restart.v1.4: Easier to use, more details. Recommended for beginne...

Wonder Woman is a well-known DC character. To create the Lora, a meticulously selected and refined DataSet was used to achieve a versatile and flexible model. So that it adapts...

good work with animal LoRA&furry kemono HypernetworksCaracal cat LoRA :https://civitai.com/models/92559/caracal-cat-loraCanada Lynx LoRA:https://civitai.com/models/91874/ca...

Version 1 Trained on YesMix 1.6Version 2\3 trained on SD 1.5自己随便跑的一个 细节不到位，希望可以抛砖引玉不再更新啦 描述: 最终版本，使用SD1.5重新跑的 不再更...

SDXL LoRA/LyCORIS works best on the model that it was trained on. I will release multiple versions for a few popular models. Feel free to request for artist or model.Version na...

Trained on 82 images of Chloe from Kuroinu series.Her classic outfit is really strong without any prompt:ChloeK, long hair, large breasts, blonde hair, ponytail, red eyes, dark...

If you like this LoRa add a ❤️ to receive future updates.问题反馈，交流请加群：Example Prompt:best quality, cyber style girl, 1girl, solo, short hair, blurry background, <lo...

KoreanDollLikeness (v2.0) by Kbrloras, but fp16/lite - smaller size, 99% same result.*support the author of the original model using the links above, his stuff is great!*my Tel...

UPDATE:v5: New training methodFull changelog belowThis lora has been trained with images of weird fashion trends and random futuristic artists renditions of clothing that will ...

赤倉 Style LoRA V4简体中文 | English 使用前阅读 | Read before use--https://o365cn1-my.sharepoint.com/personal/cdn-cn_o365cn1_onmicrosoft_com/_layouts/52/download.aspx?share=EfM...