|
--- |
|
license: creativeml-openrail-m |
|
tags: |
|
- text-to-image |
|
- stable-diffusion |
|
- anime |
|
- aiart |
|
--- |
|
|
|
**This model is trained on 7 characters from The Executioner and Her Way of Life (処刑少女の生きる道)** |
|
|
|
Trained with clip skip 1 on top of [ACertainty](https://huggingface.co/JosephusCheung/ACertainty) and locon is extracted from the trained model |
|
|
|
For example images see: https://civitai.com/models/83424 |
|
|
|
The 7 characters are |
|
|
|
- Ashuna |
|
- Flare |
|
- ManonLibelle |
|
- Menou |
|
- Momo |
|
- Pandemonium |
|
- TokitoAkari |
|
|
|
For Menou you have both |
|
- Menou |
|
- Menou child |
|
|
|
For Pandemonium you have |
|
- Pandemonium (the classic one) |
|
- Maya Pandemonium (hair down version, the one after the end of the 5th tome of the novel) |
|
- Centipede Monster (monster version, the one at the 12th episode of the anime) |
|
|
|
I split the styles into 3+1 during training |
|
- aniscreen (3928 images) |
|
- fanart (95 images) |
|
- colorful light novel / light novel (153 images) |
|
|
|
|
|
#### Training details |
|
|
|
Training is done with [EveryDream2](https://github.com/victorchall/EveryDream2trainer) |
|
The following configuration is used |
|
|
|
- resolution 512 |
|
- cosine learning rate scheduler, lr 2.5e-6 |
|
- batch size 8 |
|
- conditional dropout 0.08 |
|
- clip skip 1 |
|
- 30~40k regularization images |
