# Cassy (Visual Novel Sprite Style) - Character LoRA
An anime/visual novel style character LoRA trained on a custom dataset optimized for expressive expressions, clean line art, and versatile 2.5D/anime generation using the Anima base model.
---
## 💡 Recommended Settings
* Base Model: Anima (or compatible anime/2.5D models)
* Weight: 0.7 to 1.0 (Start around 0.8 for best balance)
* Clip Skip: 2
* Sampler: DPM++ SDE Karras or Euler a
* Steps: 25 - 30
---
## 🔑 Trigger Word & Core Tags
Always use the main trigger word to activate the character:
> cassy1_vn
### Recommended Prompt Structure:
> cassy1_vn, 1woman, solo, blonde hair, blunt bangs, blue eyes, [expression/pose tags], anime style, manhwa artstyle, high contrast, cel shaded, visual novel sprite
---
## 🎨 Features & Expressions Trained
This LoRA was trained with a rich variety of facial expressions and poses to suit visual novel or storytelling generation needs:
* Expressions: Gentle smiles, neutral look, pouting, sad/serious, tired/weary eyes, angry/fierce glare, wide-eyed shock, and sparkling/starry eyes.
* Angles & Shots: Front views, three-quarter views, and dynamic leaning-forward/high-angle shots.
* Outfit: Casual red camisole (spaghetti straps, v-neck) with minimal, out-of-focus background bokeh to keep the absolute focus on the character.
Description
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.