Downloads · 30 days
0
anima-Cunnyfunky_Style-Lora
E-stick/anima-Cunnyfunky_Style-Lora
anima-Cunnyfunky_Style-Lora is a machine learning model from E-stick. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Access
Public
Updated Aug 25, 2026
Repo size
735 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors505 MB · 100%
At a glance
- License
- other
- Access
- Public
- Created
- Aug 23, 2026
- Updated
- Aug 25, 2026
- SHA
- aebe384c
Model card
From the Hugging Face model README
-CunnyFunky Style LoRA — Anima
简介
基于 CunnyFunky 在 Pixiv 上发布的原画作品（挑选535 张,v2约1000张）训练的画风 LoRA，底模为 CircleStone-Labs Anima-Base v1.0。
触发词：cunny，建议正面提示词：shiny skin, detailed skin texture, detailed fabric 湿润/水光：wet, water droplets, sweat，织物细节：lace, knit, fabric detail，皮肤高光：glossy skin, rim lighting
建议的负面提示词：flat skin, smooth skin, flat color
v1版推荐2400步和2800步版本
Lora强度推荐=0.8~1，调度器 simple，采样器 euler，建议搭配 anima-turbo-v1.0可以在获得速度的同时获得质量，不建议使用aesthetic模型，会导致Lora风格被淡化
- License
- other
- Created
- Aug 23, 2026
- Updated
- Aug 25, 2026