An AI image of Wakana Umezawa I created from a LoRA trained on 100 copies of the same image.
3
Since the dataset image has usual AI hand mistakes, it kinda got reflected in the LoRA model as well. I used the same base model I used to make the original images.
umezawawakana1
Mostrar parámetros
- Talla
- 512 x 768
- Pasos de Muestreo
- 12
- Método de Muestreo
- Euler a
- Escala CFG
- 6
- Semilla
- 1
- Excluir de la Imagen
- worst quality, large head, low quality, extra digits, bad eye, EasyNegativeV2, ng_deepnegative_v1_75t
