Introduction
This LoRA is trained on Karin (カリン), a VRChat avatar created by Amatousagi (あまとうさぎ).
Usage
Recommended LoRA strength: 1.0
Trigger word: karin (vrchat)
In ComfyUI, escape the parentheses:
karin \(vrchat\)Default outfit:
white sweatshirt, long sleeves, pink sleeve bows, black suspenders, black pleated skirt, white sneakers, fox tailTraining Details
Trainer:
sorryhyun/anima_lora v1.17.1Dataset: 51 captioned images, with 23 higher-quality images sampled twice and 28 images sampled once
LoRA rank / alpha:
32 / 128Learning rate:
2e-5Optimizer: AdamW
Scheduler: Cosine, with 5% warmup
Batch size:
1Released checkpoint: Step
1,392Precision: BF16
Resolution: Aspect-ratio buckets at approximately 1 megapixel
GPU: NVIDIA RTX 3090
简介
这是基于 Anima Base 1.0 训练的 Karin(カリン)角色 LoRA。Karin 是由 あまとうさぎ 制作的 VRChat 虚拟形象。
使用
推荐 LoRA 权重: 1.0
激活词: karin (vrchat)
在 ComfyUI 中需要转义括号:
karin \(vrchat\)常服:
white sweatshirt, long sleeves, pink sleeve bows, black suspenders, black pleated skirt, white sneakers, fox tail训练参数
训练工具:
sorryhyun/anima_lora v1.17.1数据集: 51 张带 caption 的图片,其中 23 张高质量图片重复采样 2 次,其余 28 张采样 1 次
LoRA rank / alpha:
32 / 128学习率:
2e-5优化器: AdamW
学习率调度: Cosine,5% warmup
Batch size:
1发布权重: 第
1,392步训练精度: BF16
训练分辨率: 约 1 M 像素的宽高比分桶
显卡: NVIDIA RTX 3090
Description
Comments (1)
Somehow the "fox tail" tag was missed from my prompt when I generated the demo images. 😅
This LoRA does include her tail, so just add that word to your prompt!




