Sign In
homemodelsimagesvideos3D Modelshubsarticlescomicschallengesupdatesshop

[Style] Artist: unQjless | 上官林萤

0

Updated: Sep 19, 2026

styleartist

Download

1 variant available

bf16 SafeTensor

unqjless-step00000600.safetensors

BF16, good balance • 104.04 MB

Verified:

Type
LoRA
Stats

52

0

Reviews

(1)

Published

Sep 19, 2026

Base Model

Anima

Hash
AutoV2
3AB9F97630
Trigger Words
@unQjless
default creator card background decoration
New Creators position #51

#51

Followers - 23

23

Likes - 85

85

License:

Anima

The 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

ComfyUI_temp_tszoi_00033__cleaned.png

Introduction

This LoRA is trained on the illustration style of the artist unQjless.

Usage

Recommended LoRA strength: 1.0
Trigger word: @unQjless

Training Details

  • Trainer: sorryhyun/anima_lora v1.17.1

  • Dataset: 25 captioned images

  • LoRA rank / alpha: 32 / 128

  • Learning rate: 2e-5

  • Optimizer: AdamW

  • Scheduler: Cosine, with 5% warmup

  • Batch size: 1

  • Released checkpoint: Step 600

  • Precision: 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 @unQjless 画风 LoRA。

使用

推荐 LoRA 权重： 1.0

激活词： @unQjless

训练参数

  • 训练工具： sorryhyun/anima_lora v1.17.1

  • 数据集： 25 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

  • Batch size： 1

  • 发布权重： 第 600 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