Dettagli
Raccomandazioni
v3 LoRA
v2
hyperass

hyperass

52.7K
793
4.2K
#อนิเมะ
#concept
#สะโพก
#thighs
#ไฮเปอร์แอส
#thick
#????
#booty
#thicc
#???
#hyper
#อนิเมะ
#????
#สะโพก
#thighs
#ไฮเปอร์แอส
#thick
#????
#booty
#lora
#thicc
#???
#hyper

A model for thick bottom waifus or semi-realistic characters. This model tends to produce hourglass figured ladies compared to my bottomheavy model.

Hyperfusion is the successor to this model, I suggest giving it a try

V3 Info:

v3 now uses LoRA! Edit: A1111 now supports LoRA models with the latest version. Use the following extension in Automatic1111 to load LoRA models https://github.com/kohya-ss/sd-webui-additional-networks


What changed since v2? It's the same dataset as v2, but trained with LoRA at a higher resolution of 768. Honestly this version was just a test to see how well LoRA training worked, but it turned out so well, I decided to release it.

Mixes incredibly well with AbyssOrange at 80-90% strength! Examples are all on AbyssOrange

Tips:

  • Place "huge" before "hyperass ???" to add extra emphasis

  • If you want front facing shots, dont use "hyperass ???", use "(thick thighs, wide ????)" instead

Visualizza la traduzione

Valutazioni e recensioni

5.0 /5
0 valutazioni

Non ancora ricevute valutazioni o commenti sufficienti

T
Annuncio
2024-04-02
Pubblicare modello
2024-04-02
Aggiorna le informazioni del modello
Dettagli modello
Tipo
LORA
Data di pubblicazione
2023-03-20
Modello Base
SD 1.5
Parola Chiave
hyperass
ass
Copia
Introduzione alla versione

This version is a LoRA model.
A1111 now has support for LoRA models!

Unlike my latest ???????????? release, I kept this one simple with only one keyword "hyperass". The same keyword as previous versions.


Training Details:

  • 800 images

  • 43 epocs

  • learning rate 1e-4

  • only Unet training

  • total batch 16

  • base model Av3

  • clip skip 2

  • random flip

  • bucketing at 768

  • LoRA dim 4 (yes only 4)

Ambito di Licenza
Model Source: civitai

1. I diritti dei modelli ripubblicati appartengono ai creatori originali.

2. I creatori originali che desiderano reclamare il proprio modello devono contattare il personale di SeaArt AI tramite canali ufficiali. Clicca per rivendicare

Ambito di Licenza di Creazione
Immagini Online
Effettua una Fusione
Consenti Download
Licenza Commerciale
Le immagini generate possono essere vendute o utilizzate per scopi commerciali
Consenti la rivendita del modello o la vendita dopo la fusione
QR Code
Scarica l'app SeaArt
Continua il tuo viaggio di creazione AI su mobile