Downloads · 30 days
0
wlop_lora
SirVeggie/wlop_lora
wlop_lora is a machine learning model from SirVeggie. 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 creativeml-openrail-m.
Original artist: https://www.patreon.com/wlop
Access
Public
Updated Mar 23, 2023
Repo size
81.6 MB
Likes
5
Public
Repo makeup
Click a slice to open those files.
.safetensors76 MB · 93%
At a glance
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Mar 23, 2023
- Updated
- Mar 23, 2023
- SHA
- 05059f88
Model card
From the Hugging Face model README
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
- License
- creativeml-openrail-m
- Created
- Mar 23, 2023
- Updated
- Mar 23, 2023