Very sick of the continuous concept blend of SD 1.5, I've created this embedding model (the first of a series, which I want to call "NStyles"), to obtain exactly the clothing I wanted, a now I want to share my work...
Fuente del modelo
Descripción de la fuente
V2 changelog:
Expanded the dataset from 54 to 86 images
Training resolution upgraded from 512 to 768
Added rectangle figure body type
Added side view angle
Added rear view angle
Fuentes
1 fuenteArtefactos del modelo
1 artefactoExtractos de fuentes
2 extractosSource context: 2031 downloads · Type TextualInversion · Base model SD 1.5
Source context: 1997 downloads · Type TextualInversion · Base model SD 1.5