
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
(V3)Updates:Used some new arts and methods to retrain the model.
Now there's two forms of this character you may generate with these prompts:
( For V3 )
Silong :
-
Basic characteristic : Silver hair, ( short hair ) ,gradient hair,braids,yellow eyes,horns, ( wings ) , ( tail ) , ( scales ) ;
-
Default costume : White dress ( chinese clothes ) , ( white ) elbow gloves,white thighhighs, tassel,jewelry ;
-
Extra elements : Holding /folding (hand) fan ,water ;
Muzichi :
-
Basic characteristic : Silver hair, ( long hair ) , blue eyes,horns /single horn , ( wings /single wing ) , ( tail ) , ( scales ) ;
-
Default costume : Black dress ,gold trim, ( golden /yellow ) gloves,thigh strap ;
-
Extra elements : Holding /folding sword ,water ;
( From now on is for V2 )
-
Silong:silong,white dress,white gloves,white thighhighs,(horns),(wings),(tail)
-
Mizuchi:mizuchi,black dress,black gloves,black thighhighs,gold-trimmed,(single horn),(single wing),(tail)
By the way,you may need to add"simple(white,transparent,black) background" to negative prompts to avoid the effect of L2D training materials.
Hope you enjoy this:)
描述:
训练词语: no specific trigger words,just input the lora
名称: shadowverseSilong_v2.safetensors
大小 (KB): 36977
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success