Dettagli
Raccomandazioni
V3 [1.5]
V2 [XL]
V2 - SD1.5
V1 - SD1.5
ARTV2_TEST
V0 - XL
Furry Living Balloons and Suits

Furry Living Balloons and Suits

8.3K
50
192
#animals
#balloon
#concept
#เฟอร์รี
#พอง
#fursona
#character.
#animals
#balloon
#concept
#เฟอร์รี
#พอง
#fursona
#character.

A model made to generate a variety of Furry Balloon/latex based creatures, from inflatable balloon friends to skintight suits.

v3 differences:

Improved lora, model compatibility, and humans as requested by many. More anthro overall as a result.

Improved consistency and seperation of tags; requires prompting to make use.

(The model defaults to anthro and hybrid art/photograph)

Improved handling of edge cases (see below)

Recommended weight: 0.6-1

1.5 version trained on dreamshaper_v8.

XL version trained on WOWXL_v3.

ESSENTIAL TAGS:

Art: Furry Art, Digital art, Furaffinity commission, e621, ref

Photograph: real life photograph, photograph, photo, image

Build: Human (use man/woman/person), Anthro (Furries), Feral (animals, quadruped)

Ballooniness:

Balloon: Balloon, pooltoy/toy, inflatable,

Hybrid: latex, rubber

Suits: skintight, skinny

LESS IMPORTANT TAGS:

Camera Distance:

Extreme-close-up: Face only

Close-up: Portrait shots, ????? up

Medium-shot: Waist up

Full-body: Full character, not much else

Distance-shot: Character + background

Long-distance-shot: Background + Character

Overhead: camera is above the subject

Underhead: camera is below the subject

Color:

For multiple colors, go by each color, then list all the parts with the color.

A blue nose, blue hands and blue feet becomes "A blue nose, hands and feet"

"A green dog with a white underside, red torso and paws, blue snout and ears"

Directionality: "Front, Front-side, Side, Side-back, Back view"

Hair: "Long hair" "Hair tuft", "Mohawk", "Puffy hair"

Material: "Matte" "Glossy" "Ultra-Glossy"- Least to most shiny

"Smooth" or "Wrinkly"

Poses: Standing, sitting on a, on knees, leaning again, ????????????, jumping, laying on back/belly, floating, flying, screaming, walking, running, begging, tripping, jumping, cuddling, sleeping, nuzzling..."

EDGE CASES: Special tags for niche uses!

"Bopper Paws" gives the characters big round paws instead of hands. "Bopper Mitts" excludes the pawpads, "Big", "Pointed", "Round Balloon Gloves". This is only used with anthro.

"Dewlap" A noticable puff of "fur" around the neck (not a collar, Eevee is a good example)

"Featureless" is used to remove all features, making them smooth instead.

For specific features,

("Faceless" "Eyeless", "Mouthless", "Tailless")

"Inanimate"- Generates realistic/plausible inflatables rather than living ones.

"In an empty [color] room"

"Multiple characters"

"Lenses" actual eyes behind lenses. "light pink eye lenses"

"NSFW/Suggestive" Dataset is about 85% SFW, anything else will have one of these tags.

"Pupsuit/Petsuit" Usually a person wearing a skintight suit with open eyes. Often uncanny valley territory. use "play" for more movement.

"Product Photo" Photos taken in empty rooms to work as listings for websites, expect relatively static poses and solid backgrounds

"Ref" Art version of product photo.

"Sphere"- makes the character round to the point of basically being a ball.

"Suit" Cases in which it is obvious it is a person or furry in a suit instead of a living inflatable. in the case of petsuits use that tag instead.

"Translucent" for anything not opaque.

Visualizza la traduzione

Valutazioni e recensioni

4.5 /5
0 valutazioni

Non ancora ricevute valutazioni o commenti sufficienti

avatar
Conversazione con il modello
Annuncio
2023-10-21
Pubblicare modello
2024-02-13
Aggiorna le informazioni del modello
Dettagli modello
Tipo
LORA
Data di pubblicazione
2024-02-13
Modello Base
SD 1.5
Introduzione alla versione

Improved lora, model compatibility, and humans as requested by many. More anthro overall as a result.

Improved consistency and seperation of tags; requires prompting to make use.

(The model will default to anthro and hybrid art/photograph)

Improved handling of edge cases (see below)

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