Type | |
Stats | 460 17,703 3.2k |
Reviews | (87) |
Published | Mar 29, 2024 |
Base Model | |
Training | Steps: 11,000 Epochs: 99 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Trigger Words | lichvtuber |
Hash | AutoV2 B190220A6A |
Character LoRA for Froot aka Apricot aka Lichvtuber with ca. 0.5 outfits (one outfit, but it's not very consistent).
If you like the LoRA, please leave a reaction, review and/or tip. Enjoy!
Usage
Trigger word:
lichvtuber
Tags for outfit:
cropped hoodie, fishnet top, cross pasties, shorts, single pants leg
Recommended strength 0.8 - 1.0 (1.0 - 1.2 for lite)
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.
Notes
This one turned out pretty good. I experimented with some new training settings and the results speak for themselves. I would have liked to add some more outfit triggers to this one, but the dataset wasn't really big/consistent enough, so the cropped hoodie and fishnet top is all we get for now.
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.
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: