wlop_lora / README.md
SirVeggie's picture
Update README.md
05059f8
---
license: creativeml-openrail-m
---
# WLOP lora
Original artist: https://www.patreon.com/wlop
### Lora details
I haven't tested extensively yet, but sv_wlop is the 14 epoch version that I've mainly used and it works quite well.
Lora works pretty well at and below weight 1.
A good negative is helpful for optimal results. Here are some options:
```
(low quality, worst quality:1.4), (bad anatomy), extra digit, fewer digits, (extra arms:1.2), bad hands, by (bad-artist:0.6), bad-image-v2-39000
[low quality easynegative|worst quality 3d]
```
https://huggingface.co/datasets/gsdf/EasyNegative \
https://huggingface.co/nick-x-hacker/bad-artist \
https://huggingface.co/Xynon/models/tree/main/experimentals/TI
### Keywords
wlop, aeolian, yan, jade
The keywords other than `wlop` don't have much effect, but describing the characters will make them appear to a degree.
## Images
![img1](wlop_lora_1.png)
![img2](wlop_lora_2.png)
![img3](wlop_lora_3.png)
![img4](wlop_lora_4.png)
![img5](wlop_lora_5.png)