Type | |
Stats | 966 1,876 225 |
Reviews | (153) |
Published | Mar 27, 2024 |
Base Model | |
Training | Steps: 4,000 Epochs: 35 |
Usage Tips | Clip Skip: 2 Strength: 1 |
Trigger Words | pepe_silvia |
Hash | AutoV2 16D143181B |
Allows you to create an accurate image of your waifu (pointlessly) explaining why people should not lewd her.
If you like the LoRA, please leave a reaction, review and/or tip. Enjoy!
Usage
Trigger word (optional):
pepe_silvia
Recommend support tags:
open mouth, crazy eyes
Recommended strength 0.6 - 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.
Notes
I think this is my first concept LoRA. I kinda messed up the trigger word, but the result is still pretty good. Definitly good enough for a meme LoRA. Especially, considering that the training dataset is incredibly small (11 images) and not very high quality. SDXL models continue to surprise me.
Using training data
Feel free to contact me if you want access to the training data.