Download
1 variant available

140 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
670 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
License:
AnimaThe Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
Built on NVIDIA Cosmos
Introduction
This LoRA is trained on Kaguya (輝夜, かぐや), a VRChat avatar created by IKUSIA.
Usage
Recommended LoRA strength: 1.0
Trigger word: kaguya (vrchat)
In ComfyUI, escape the parentheses:
kaguya \(vrchat\)Default outfit:
black serafuku, black sailor collar, red bow, bell, black cardigan, long sleeves, black pleated skirt, black pantyhose, black footwear, black beret, multiple tailsThe trigger alone is enough to bring out the character's identity. Add the outfit block above if you want the full original look.
Training Details
Trainer:
sorryhyun/anima_lora v1.17.1Dataset: 15 captioned images
LoRA rank / alpha:
32 / 128Learning rate:
2e-5Optimizer: AdamW
Scheduler: Cosine, with 5% warmup
Released checkpoint: Step
2,000Precision: 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 Kaguya(輝夜,かぐや)角色 LoRA。Kaguya 是由 IKUSIA 制作的 VRChat 虚拟形象。
使用
推荐 LoRA 权重: 1.0
激活词: kaguya (vrchat)
在 ComfyUI 中需要转义括号:
kaguya \(vrchat\)常服:
black serafuku, black sailor collar, red bow, bell, black cardigan, long sleeves, black pleated skirt, black pantyhose, black footwear, black beret, multiple tails激活词单独使用即可带出角色人设。如需完整的原设造型,请附带上述常服 prompt。
训练参数
训练工具:
sorryhyun/anima_lora v1.17.1数据集: 15 张带 caption 的图片
LoRA rank / alpha:
32 / 128学习率:
2e-5优化器: AdamW
学习率调度: Cosine,5% warmup
发布权重: 第
2,000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


