Membresía PixAI
PixAI
PixAI
Generate
Sign in
Inicio
Generar
Modelos
Studio
NEW
Concurso
Crear con Mio.2
Caja de herramientas
NEW
Guía de PixAI

LoRA de usuario

XL
Otro

Giantess - Cramped [Concept] {Pony}

#Giantess

Crear

  • Generador de imágenes IA
  • Generador de animación con IA
  • Caja de herramientas
  • Generadores temáticos
  • Entrenar LoRA
  • Agente Mio.2
  • Studio

Descubrir

  • Etiquetas de tendencia
  • Clasificación
  • Mercado de modelos
  • Concurso
  • Noticias

Acerca de

  • Guía de PixAI
  • Cómo utilizar PixAI
  • Tsubaki.2
  • Conoce a Mio
  • Reglas de contenido

Precios y ayuda

  • Membresía
  • Paquetes de créditos
  • Contacto

Aplicación móvil

  • App Store
  • Google Play
© 2026 PixAI
  • Condiciones de uso
  • Política de privacidad
  • Política de derechos de autor
  • Ley de Transacciones Comerciales Especificadas
Giantess - Cramped [Concept] {Pony} - AI Model cover image
Entrenado por
Avatar image of ajice

ajice

Subido en
4 dic 2024, 12:00
Utiliza
45.9k
Reseñas
Excelente  (5)
Palabras clave

gtscramped

Permisos
  • Permitir la generación y el intercambio de imágenes
  • Permita que los usuarios descarguen su modelo
  • Usos comerciales

LoRAs recomendadas

Tomie Kawakami/川上 富江/Kawakami Tomie (Junji Ito) SDXL LoRA [Pony] - AI Model cover image

LoRA de usuario

Tomie Kawakami/川上 富江/Kawakami Tomie (Junji Ito) SDXL LoRA [Pony]
38
旧スクール水着 old school swimsuit - AI Model cover image

LoRA de usuario

旧スクール水着 old school swimsuit
128
Detailed Cute Style v1.0 -  Animagine XL - AI Model cover image

LoRA de usuario

Detailed Cute Style v1.0 - Animagine XL
72
Detailed? Background (probably unstable) - AI Model cover image

LoRA de usuario

Detailed? Background (probably unstable)
17

Descripción

Produces an image of a giantess character in a room or environment that they are too big for. The main triggerword is gtscramped.

I attempted to train in several subtrigger words, but your mileage will vary on their effectiveness. Head against ceiling, back against wall, and hand against wall/ceiling seem to work a decent amount of the time. Cracked ceiling and cracked wall usually work as expected. The most common issue will be that if the head goes to the ceiling, the hands like to try and follow. Due to extremely little training data with feet on walls/ceilings, feet are a crapshoot. I have managed to generate a foot causing damage to a ceiling a couple times, but neither time was I actually prompting for it.

The only locations this LoRA was trained on were bedroom, living room, and kitchen tags. But as can be seen from the sample images, prompting for things like a classroom, school gymnasium, or cave are still possible with a bit of prompt experimentation.

I heavily suggest getting creative with the kinds of prompts describing how someone would be positioned or posed when trapped in a tight space. Lying down on side or on back. Knees up and hugging own legs. All fours or bent over. Helps with getting the image you're looking for.

You can find my donation link(s) through ((https://linktr.ee/ajice)) if you wanna support me.

Comentarios