Członkostwo PixAI
PixAI
PixAI
Generate
Sign in
Strona główna
Generowanie
Modele
Recipe
NEW
Studio
Konkurs
Mio.2

Conversational creation

Skrzynka narzędziowa
Guide

User LoRA

XL
Inne

Giantess - Cramped [Concept] {Pony}

#Giantess
Strona głównaModeleMio.2Profil

Narzędzia AI

  • OC Maker
  • AI Anime Generator
  • VTuber Maker
  • Sonic OC Maker
  • Hazbin Hotel OC Maker
  • Anime Character Creator
  • AI Figure Generator
  • Genshin OC Maker
  • All AI Tools

Odkrywaj

  • Popularne tagi
  • Ranking
  • Rynek Modeli
  • Konkurs
  • Aktualności

O nas

  • O PixAI
  • Guide
  • Jak używać PixAI
  • Tsubaki.2
  • Poznaj Mio
  • Zasady treści

Cennik i pomoc

  • Członkostwo
  • Pakiety kredytów
  • Kontakt

Aplikacja mobilna

  • Pobierz aplikację PixAI
  • App Store
  • Google Play
© 2026 PixAI
  • Regulamin
  • Polityka prywatności
  • Polityka praw autorskich
  • Attributions
  • Ustawa o Określonych Transakcjach Handlowych
Giantess - Cramped [Concept] {Pony} - AI Model cover image
Trenowane przez
Avatar image of ajice

ajice

Przesłano
4 gru 2024, 12:00
Użycia
47.5k
Opinie
Doskonały  (5)
Słowa kluczowe

gtscramped

Uprawnienia
  • Allow image generation & sharing
  • Zezwól użytkownikom pobierać Twój model
  • Zastosowania komercyjne

Recommended LoRAs

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

User LoRA

Tomie Kawakami/川上 富江/Kawakami Tomie (Junji Ito) SDXL LoRA [Pony]
41
旧スクール水着 old school swimsuit - AI Model cover image

User LoRA

旧スクール水着 old school swimsuit
133
Detailed Cute Style v1.0 -  Animagine XL - AI Model cover image

User LoRA

Detailed Cute Style v1.0 - Animagine XL
73
Detailed? Background (probably unstable) - AI Model cover image

User LoRA

Detailed? Background (probably unstable)
19

Opis

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.

Komentarze