An AI image of Wakana Umezawa I created from a LoRA trained on 100 copies of the same image.
Since the LoRA is trained on 100 copies of the same image, its essence got reflected in the model, including the shading and background. Used the same base model that I used to make the original images.
Mostra parametri
- Dimensione
- 512 x 768
- Passaggi di campionamento
- 12
- Metodo di campionamento
- Euler a
- Scala CFG
- 6
- Seme
- 1
- Negativo
- worst quality, large head, low quality, extra digits, bad eye, EasyNegativeV2, ng_deepnegative_v1_75t
