Models>

五十铃怜 \ 五十鈴 れん \ Isuzu Ren

masterpiece,bast quality,official art,8K wallpaper,game cg,isuzurensch \(magiarecord\),red skirt,blue eyes,white shirt,large breasts,hair over one eye,blush,heavy breathing,expressionless,1girl,solo,dark sky,blue moon,cloud,blue lycoris radiata,<lora:ringsch2:1:1,0.1,0.1,0.1,0.1,0,0,0,0.7,0.9,0.9,0,0,0,0,0,0>
masterpiece,bast quality,official art,8K wallpaper,game cg,isuzurensch \(magiarecord\),red skirt,blue eyes,white shirt,large breasts,hair over one eye,blush,heavy breathing,expressionless,1girl,solo,dark sky,blue moon,cloud,blue lycoris radiata,<lora:ringsch2:1:1,0.1,0.1,0.1,0.1,0,0,0,0.7,0.9,0.9,0,0,0,0,0,0>
masterpiece,bast quality,official art,8K wallpaper,game cg,isuzurensch \(magiarecord\),red skirt,white shirt,hair over one eye,expressionless,1girl,solo,dark sky,blue moon,cloud,blue lycoris radiata,<lora:ringsch2:1:1,0.1,0.1,0.1,0.1,0,0,0,0.7,0.9,0.9,0,0,0,0,0,0>
Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

date 2023.5.20

最近重新打标训练了五十铃怜的所有服装,为了最大程度上避免tag污染,我直接把他们分开训练了.因为调高了某些参数的原因,lora文件会比一般大,但是效果会好点.

Recently I re-tagged and trained all of Suzu's outfits to avoid tag pollution as much as possible, and I trained them separately. Because of tweaking certain parameters, the .lora files are larger than usual, but the effect will be better.

还是和之前一样,是使用3D模型进行的训练导致3D模型风格占比过高,因此请使用lora分层来运行这些lora,具体分层的参数以及触发词我已经写好了,就在图片里面,请自行查看

As before, training using 3D models results in an excessive proportion of the 3D model style. Therefore, please use Lora Block Weight to run these lora.weight and trigger words included in the images. Please refer to the images to review the details.

===============================================

v1.0

使用恋活人物卡训练,我所使用的人物卡作者是haruki

I used the character card to train, the character card im using was created by haruki

因为是3D模型训练的,一般用0.7或更低比较好,lora的训练底模是原版大模型 model[e6e8e1fc]

Because this lora was trained by 3d modle,use 0.7 or more less is batter.This lora was trained by original big model[e6e8e1fc]

Lora内训练的服装tag我放在下面了,可以自己斟酌修改

The costume tag for Lora's training is below and you can modify it at your discretion

战斗服(mahou shoujo):masterpiece,bast quality,official art,8K wallpaper,game cg,thighhighs, solo, straight-on, blue eyes, 1girl, hair over one eye, looking at viewer, black legwear, choker, hair ornament, boots, long sleeves, single thighhigh, sitting,on the tree,green leaves floating,bow, sleeves past wrists, white footwear, tachi-e, wide sleeves,hands on legs

校服(school uniform):masterpiece,bast quality,official art,8K wallpaper,game cg,1girl, armband, solo, blue eyes, school uniform, short sleeves, smile, looking at viewer, sailor collar, bangs, upper body, hair over one eye, eyebrows visible through hair, closed mouth, serafuku, letterboxed, shirt, long hair,open window,white curtains,sunlight

冬装(winter coats):masterpiece,bast quality,official art,8K wallpaper,game cg, fur trim, fur-trimmed sleeves, 1girl, fur-trimmed jacket, fur-trimmed coat, hairband, solo, fur collar, blue eyes, pantyhose, hair over one eye, standing, fur-trimmed boots, long hair, coat, looking at viewer, sleeves past wrists, bangs, fur-trimmed cape, silver hair, long sleeves, fur coat, dress,under the christmas tree,snowing

泳装(bikini):masterpiece,bast quality,official art,8K wallpaper,game cg,swimsuit, 1girl, solo, one-piece swimsuit, white swimsuit, low twintails, blue eyes, twintails, long hair, hair over one eye, frills, looking at viewer, frilled swimsuit, eyebrows visible through hair, hair ornament, barefoot, standing, collarbone, bangs,sunshine,beach,sunlight,palm trees,cloud

*如果你使用了我的Lora并且在Pixiv或者其他网站投稿请注明一下Lora出处

*If you use my Lora and have contributed to Pixiv, please give credit to Lora

*私のLoraを使用してPixivに投稿した場合、Loraへのクレジットをお願いします。

Images Generated With This Model

Loading...

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.