Sign In

Style Collection

64

357

73

16

Updated: Aug 1, 2025

style

Verified:

SafeTensor

Type

LoRA

Stats

138

29

23

Reviews

Published

Jul 29, 2025

Base Model

Illustrious

Usage Tips

Strength: 0.7

Hash

AutoV2
432FFAD5D7

Style Collection

This is my personal style collection. Anything could be here, except artist style.

Cover images are directly from the vanilla (the original) base model in a1111, at default 1MP resolution. No upscale, no imprinting fixes.

All LoRAs in this collection, by default:

  • Trained on illustrious v0.1.

  • Full natural language captions. No trigger words, just follow your heart cover images.

  • Version means nothing, just my training job ID.


elpe v0.22:

  • Dataset: Ultra-Ultra-Ultra-high-definition (~12K, no joke) renderings from the game engine. Mainly portraits. 100% homemade. Full of crazy lighting effects.

  • Style: Ultra realistic textures and details, light particles, cinematic lighting effects, fire effects, etc...

  • TBH, I did not believe SDXL can handle such complex dataset. But turns out it can, although not 100%, but looks cool enough.

  • Support both 2D anime and 3D game characters. Prefer 3D characters for best effect.

  • Prefer vanilla base model ONLY. Otherwise you won't get full effects, they will be suppressed.

dcr v0.7:

  • Dataset: Mixed dataset mainly from the game Azur Lane.

  • Style: Clean 2D anime illustrious, wallpaper.

  • Purpose: a style regulator for vanilla base model. Giving you the feeling of the game style (vibe, colors, clothing, etc.).