Type | |
Stats | 463 9,000 |
Reviews | (75) |
Published | Apr 7, 2024 |
Base Model | |
Training | Steps: 10,200 Epochs: 154 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Trigger Words | silvervale |
Hash | AutoV2 73557955E6 |
Character LoRA for Silvervale from Vshojo aka. your resident definitely-wholesome-and-not-lewd gamer wolf girl. Praise be to Todd.
If you like the LoRA, please leave a reaction, review and/or tip. Enjoy!
Usage
Trigger word:
silvervale
Tags for outfit:
fake animal ears, black crop top, black skirt, fishnet gloves, pink thighhighs, blue thighhighs, asymmetrical legwear
Often does not get the thighhighs right, since they are not very prominent in the training data
Leave out/replace tags for part of the outfits you do not want (e.g. no crop top or real wolf ears instead of fake ones)
Recommended strength 0.8 - 1.0
Use Clip skip=1 or Clip skip=2 (other values may also work, use at own risk)
Works best at 1024x1024. Similar resolutions (e.g. 800x1200) also work well.
Example
See preview images (generated with pruned version)
Unpruned vs. Pruned vs. Lite
I offer three variations of the model, which only differ in the file size and quality. Pick the one that best suits your preferences. If you can not decide, simply pick the "pruned" version. Note that the quality is relative, even the lite version usually produces images which closely resemble the intended subject.
unpruned: The originally trained model. Largest file size, best quality. Pick if you want the best possible quality, at the cost of disk space.
pruned: Downsized model. Almost same quality as the unpruned version, with noticably smaller file size.
lite: Drastically downsized model. Smallest file size. Still has good quality, but noticeably worse than unpruned and pruned.
Using training data
Feel free to contact me if you want access to the training data.
The training data (images and tags) have been mostly sourced from rule34.xxx and other images boards. They have been cleaned up manually by me. When using the training data or modified versions of it to create models or datasets, please credit me as appropriate.
Notes
Another brick in the Vshojo LoRA wall I am building. This LoRA was pretty straightforward. I would have liked there to be more outfits, but I could not find enough consistent images of her other outfits. To be fair, I didn't look too hard either.
Disclaimer
This LoRA is not affiliated with the character it is based on. If you like the character, check them out at one of their socials: