Train based on AnyLora model. Training resources include official arts , leader's spine animations and some fanarts from Shadowverse.
Fuente del modelo
Descripción de la fuente
Train based on AnyLora model. Training resources include official arts , leader's spine animations and some fanarts from Shadowverse.
Strongly recommend weights from 0.6 to 0.8,and enable hires.fix,and 0.8 to 1.0 when using lora block weights.
Some of my examples may have used lora block weights,my recommended weight is :
1,0.1,0.1,0.8,0.8,0.1,0.1,0.8,0.8,0.1,0.8,1,0.1,0.1,1,1,1,1,1,1,1,1,1,1,1,1
( For V2) Used some new pictures and trainning methods.
Now you may generate this character using the following prompts ( / for alternative prompts and quoted for optional prompts ) :
Basic Characteristics : Blonde hair,braids,two-tone hair, ( long hair ) ,green eyes ;
Fuentes
1 fuenteArtefactos del modelo
1 artefactoShadowverseNahtV2-000015.safetensors
safetensors · 58,3 MB · SHA-256 56542c980d2a…59c4 · Civitai
DescargarExtractos de fuentes
1 extractoSource context: 685 downloads · Type LoCon · Base model SD 1.5
Default costume : White shirt,ascot,jacket,gloves,high-waist black pants,belt,( boots ) ;
Extra elements : Magic cube ;
( From now on are for V1 )
Add “green eyes,multicolored hair,blonde hair,red hair" to prompts may help the character get closer to the origin set,add "(opened) magic cubes" to get some extra effects :)
Also,you may add"white(black,transparent,simple) background" to negative prompts to avoid those backgrounds caused by L2D trainning materials.