Type | |
Stats | 187 |
Reviews | (25) |
Published | Feb 23, 2024 |
Base Model | |
Usage Tips | Clip Skip: 1 Strength: 0.8 |
Trigger Words | evekda, light-purple hair, earings, |
Hash | AutoV2 01321B31A5 |
K/DA All Out Evelynn by ππππππ¨
This LoRA was trained with 100 images of the League of Legends Character Evelynn, each sized 768x768.
The preview images were generated using the model epiCRealism - pure Evolution V5
Info: This LoRA also works decently on animated and semi-real checkpoint models.
Settings used in the preview images:
LoRA Weight: (Operates from 0.6 to 1.0) - Recommended: (0.6 to 1)
Default Resolution: 768x768
Recommended Resolution: Depending on what you want (NOTE BELOW)
Sampler: DPM++ 3M SDE Exponential
Steps: 20
Cfg Scale: 2 (Depending on your model)
Keywords:
V1.0: evelol, white hair, earings,
V1.1: evekda, light-purple hair, earings,
βUse the next prompt if you want K/DA AttireβΊ
[For LoRA V1.0]: 1girl, evelol, white hair, earings, open short blue jacket, harness bra, (black tight skirt pantyhose),
[For LoRA V1.1]:
Full Body Prompt: 1girl, evekda, light-purple hair, earings, in black, latex bra, harness bodice, short jacket, blue snakeskin jacket, pantyhose skirt, high heels, full body,
Close Up Prompt: 1girl, evekda, light-purple hair, earings, in black, latex bra, harness bodice, short jacket, blue snakeskin jacket, headshot,
βIf you want your own outfit, simply use keywords with your own prompt :)βΊ
V2.0 [UPDATE]
Trained with other dataset.
Trained with more steps.
I don't know which version is better, so thats why :)
Note:
This model works well at most resolutions, so you won't have many problems. However, in case you get distorted or warped faces, simply try in other resolution. In the preview images, you'll notice that lower resolutions are used for close-up faces, while higher resolutions are used for full-body shots. So, always try to play around the resolution and give a try to this LoRA.
HAVE FUN :)