Tipo
LORA
Tempo de Publicação
2023-09-21
Modelo básico
SD 1.5
Palavra de ativação
FrenniFazclaire
Copiar




Trained with 50 high quality images at 512,512 with bucketting.
Fairly Unstable Lora, a work in progress. Im not sure why this character is so hard to train.
Will retrain soon with more images at 1024 now that this one was moderately successful
Im working on getting an SDXL lora going but its a work in progress
Best results in dreamshaper on SD1.5 with higres fix with the lora set to 0.8
1. Os direitos dos modelos repostados pertencem aos criadores originais.
2. Criadores originais que desejam reivindicar seus modelos devem contatar a equipe do SeaArt AI pelos canais oficiais. Clique para reivindicar
