santa hat
deerdeer nosedeer glow
Sign In

Himehajime - VShojo [PonyXL]

37
311
359
10
Updated: Apr 18, 2024
charactervtuber
Verified:
SafeTensor
Type
LoRA
Stats
214
287
Reviews
Published
Apr 18, 2024
Base Model
Pony
Training
Steps: 10,000
Epochs: 99
Usage Tips
Clip Skip: 1
Strength: 1
Trigger Words
himehajime
Hash
AutoV2
E02F7E4528

Character LoRA for Hime Hajime from VShojo. I would like to make a funny insider joke here, but I'm not really involved in their community, so I can't. Bummer.

If you like the LoRA, please leave a reaction, review and/or tip. Enjoy!

Usage

  • Trigger word: himehajime

    • For wings/tail: red demon wings, tail

    • For bloody hands/claws: blood on hands, claws

  • Outfit tags: necklace, blue sweater, cleavage cutout

  • 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

Surprisingly, this LoRA gets the screws and hair ornament pretty consistently, even though the training data set is pretty. It of course struggles with getting the screws to look good, but I am positively surprised nevertheless.

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: