Detalles
Recomendado
v4 ZIT
v4 WAI_IL
v4 noob_vpred
v3 pony
bubble_butt SDXL/ZIT

bubble_butt SDXL/ZIT

1.2M
755
3.8K
#Concepto
#thick
#Trasero
#booty
#thicc
#trasero con curvas
#hiper
#Illustrious

This LoRA generates bubble butts for a number of SDXL/ZIT models. Its nearly the same dataset as my SD1x bubble ???? but with a handful of larger sizes added, and better tagging.

Use the tag "bubble ????", with (optionally) one of the following size tags "medium ???", "big ???", "huge ???", "gigantic ???", "hyper ????" along with similar Hyperfusion tags.

If you want front facing images try "from front", or "??? visible from front" and negative "???????????, looking back, ?????????" at varying weights.

v4 ZIT Changelog:

  • Couldn't resist training a lora on Z-Image-turbo. Went pretty well, so ill probably be training more when the base model drops.

  • This one is just a quicky, probably not fully trained, but good enough as you can see.

  • Dataset is fully anime/furry, so you need to include realism related tags and words if you want that.

v4 WAI_IL Changelog:

  • No changes, just re-trained on WAI_IL-v14 because I was in a tinkering mood.


v4 noobai_vpred Changelog:

  • Not much changed. Added a few more images/captions/tags, and trained on noobAI_vpred_1.0 with somewhat similar settings to v3

  • Same tags as v3, you already know what to expect

  • "hyper ????" has a greater effect on this noob_vpred version as well if you want it really large.

Ver traducción

Calificaciones y comentarios

-- /5
0 calificaciones

Aún no se han recibido suficientes calificaciones o comentarios

T
Anuncio
2024-04-02
Publicar modelo
2025-12-03
Actualizar información del modelo
Detalles del modelo
Tipo
LORA
Fecha de lanzamiento
2025-12-03
Modelo básico
ZImageTurbo
Palabra activadora
bubble butt
Copiar
Introducción de versión

Just a quick bubble ???? lora on the new Z-image architecture. Ill do a full lora when the base model comes out, but I couldn't resist trying it out before then.

Pretty happy with results. Didn't require any tinkering. But I did need to use the ai-toolkit lora adapter to get stable results.

Same dataset as the last.

Training Details:

train_text_encoder: false

  • type: "lora"

  • linear: 16

  • linear_alpha: 16

  • conv: 8

  • conv_alpha: 8

  • caption_dropout_rate: 0.1

  • resolution: [ 768, 1024 ]

  • flip_x: true

  • batch_size: 1

  • gradient_accumulation: 8

  • optimizer: "adamw8bit"

  • lr: 4e-4

  • dtype: "bf16"

Alcance de la licencia
Fuente: civitai

1. Los derechos de los modelos republicados pertenecen a los creadores originales.

2. Si los creadores originales desean reclamar su modelo, contacten al personal de SeaArt AI a través de canales oficiales. Haz clic para reclamar

Alcance de la licencia de creación
Transmisión en vivo
Fusión
Permitir descargas
Licencia comercial
Las imágenes generadas se pueden vender o usar con fines comerciales
Permitir reventa de modelos o su venta tras la integración
QR Code
Descargar la aplicación SeaArt
Continúa tu viaje de creación con IA en móvil