Yuri Kurosu / Magikano
Combinar con modelo Prompt base/ Combine with base model Prompt:
School Uniform Sakuramori/ Uniforme Escolar Sakuramori = School uniform, dress, blue dress, capelet, ribbon, red ribbon, puffy short sleeves, white sleeves,
Gym Uniform/ Uniforme Gimnasia/ Buruma= buruma, blue buruma, sneakers, shirt, white shirt,
Bikini/Swimsuit Custome= swimsuit, one-piece swimsuit, bikini, strips, bare shoulders, breast, navel,
Use black color prompt with Swimsuit or Bikini / usa el color negro para el prompt bikini o swimsuit
ATTENTION!! Due to CivitAI's new policies, we are forced to remove all images containing NSFW content, We apologize for the inconvenience.
ATENCION!! Debido a las nuevas politicas de CivitAI nos vemos obligados a retirar todas las imágenes con contenido NSFW/adulto, disculpen las molestias.
Description
[ESP]Esta nueva versión esta entrenada con PonyXL-V6 en One trainer si lo comparo con sus versiones SD 1.5 tenemos un claro ganador, PonyXL aunque con un mayor consumo de Vram( uso una 3070TI 8gb-Vram) genera imagenes mucho más precisas y con menos fallos sin tener que hacer uso de demasiados Promps positivos, los resultados han al menos para mi han sido satisfactorios, espero que los fans de Magikano puedan disfrutar de esta nueva versión de Yuri Kurosu,
[EN] new version is trained with PonyXL-V6 in One trainer if I compare it with its SD 1.5 versions we have a clear winner, PonyXL although with a higher Vram consumption (I use a 3070TI 8gb-Vram) generates much more precise images and with fewer errors without having to use too many positive Promps, the results have been satisfactory, at least for me, I hope that Magikano fans can enjoy this new version of Yuri Kurosu,
One Trainer:
35 imagenes - screenshots
Profile default settings= SDXL 1.0 LoRA
BASE: Stable Diffusion XL Base
Type= LoRA (top right corner in one training)
In concept settings=
balancing [ 10.0 ] Repeats
On training settings:
Learning Rate Scheduler [Cosine with Restard],
Bath Size [1]->bfloat16
Epoch/Etapas: [10]->bfloat16,
On model settings:
Weight data type: bfloat16
Output data type: bfloat16
El resto de los parámetros los dejas con la configuración predeterminada del perfil SDXL-LoRA
You leave the rest of the parameters with the default configuration of the SDXL-LoRA profile