YuriKurosu1girlsololong hairblack hairbangsschool uniformdressblue dressribbonred ribboncapeletpuffy short sleeveswhite sleves
License Scope:
Creative License Scope
Online Image Generation
Merge
Allow Downloads
Commercial License Scope
Sale or Commercial Use of Generated Images
Resale of Models or Their Sale After Merging
Model Parameters:
Base Model:
Pony
Epochs:
0
Iteration Steps:
0
Clip Skip:
0
Review:
0
Review
[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
[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