VRChat Furries

Discord server to see or share other generated images: Discord Link

New version : V4.2

Trained for the Yiffymix v3.3 model (https://civarchive.com/models/3671?modelVersionId=143769)

YOU NEED TO REDUCE THE STRENGTH OF THE MODEL TO <0.8

• Work better with CFG Scale between 3 and 6

• Works with clip skip 1 and 2

Contains :

• Rexouium (keyword: rexouium)

• Avali with kitavali and davali (keywords: avali, kitavali or avali, davali)

• Nardoragon (keyword: nardo)

• Deuzear (keyword: deuzear)

• Wickerbeast (keyword: wickerbeast)

• Protogen (keyword: protogen)

• Taidum (keyword: taidum)

• Awtter (keyword: awtter)

Also works well with anime boy and anime girl

LoRAs working well with VRCFurry

• Gacha splash LORA v3.1 and v4 : painting style + epic background and arrangements + improves faces (biased towards shorts + thinner body + centered subject) https://civarchive.com/models/13090?modelVersionId=26536

• HD Helper : avoid duplicate faces on high resolution pictures (https://civarchive.com/models/110071?modelVersionId=118644)

• Fluffyrock Quality Tags : slightly improve characters + more likely to generate furry instead of humans (https://civarchive.com/models/127533?modelVersionId=151790)

• Micro Waist : self descriptive (https://civarchive.com/models/4602/waist-slider-microwaist)

Negative Embedding working well with VRCFurry

I tried a bunch of different negative embedding and those are the ones that seems to give the best results

• Boring_e621 (https://civarchive.com/models/87781/boringe621-negative-embedding-improve-image-quality)

• veryBadImageNegative (https://civarchive.com/models/11772/verybadimagenegative)

• BadDream (https://civarchive.com/models/72437?modelVersionId=77169)

• EasyNegative (https://civarchive.com/models/7808?modelVersionId=9208)

I recommend to use all of them à the same time.

Keywords

Improvers :

• good lights : makes volumes pops more

• good colors : better color choices

• good composition : more assertive composition choices

• good face : faces I prefer

• bestart : used this keyword on the best art of my dataset (few example so it is pretty weak/random)

• aestheticcartoon : more assertive colors and texture choices

• aestheticmuscles : targets no fat, no steroid or bara look (sometimes the position gets a bit stiff)

• musculegs : to counter act the strong biasis of most models toward thick upper body and thin legs

Worsener : (to use in the negative prompt)

• bad face, ugly, dumb face : used in dataset, pretty self descriptive

• bad hands : used in dataset, pretty self descriptive

• bad muscles : unaesthetic muscle insertions, poor definition or disproportionned

• bad abs : same but specific to abs

• ghbelly : used in the dataset for muscular bodies with gh/steroid bubble gut, and distended abs

• thin legs : self descriptive

• small eyes : self descriptive (but pretty weak as there are very few examples in the dataset)

Non vrcfurry keywords but that I like to use with this model

• gorgeous eyes : improve eyes

• extremely detailed furs, 4k, 8k : add details but often biased towards small eyes

Styles (keywords) :

• comic

• thick lines

• photography

• render

• painting

• swaggy

• draft

• hardstyle

• detailed style

Composition (keywords):

• rim light

• dynamic scene

• complex scene

• bicolor

• monocolor

• morning

Body / Face (keywords):

• cute

• teenager

• ( - / slightly/ very / extremely) muscular

• ripped muscles

• (spiky / wavy / feather) hairs

• relaxed

• vore

Clothes (keywords):

• ( - / tight) shirt

• short

• legging

• hoodie

• bandana

• croppedhoodie

• muscles through clothes

Position (keywords):

• side view

• 3/4 view, three-quarter view

• back view

• looking back

• looking down

• looking away

• defying look

• dynamic position

• seated / sitting

• crouching

• lying on

• leaning on

• facing down

Suggestive / NSFW (keywords):

• dick through clothes

• dick sticking out

• autosucking

• jacko pose

• grabbing pec

• first person view

Others (keywords):

• hmoma : furry with human (at least 2 persons)

Tips & tricks:

• Improve avali look by adding those keywords: cute, big eyes, feathers, black eyes

• Get better faces by adding these keywords: close up portrait

• Sometimes you can get better faces by changing hairs / furs colors

Good positive prompt keywords :

Kind of a meta I found across all my models

good lights, good colors, good composition, monocolor, bicolor, good face, (cute:0.7), teenager, 

• good lights, good colors, good composition, are keywords I added on the best artworks in the dataset

• monocolor, bicolor, are often associated to higher quality / artistic artworks in the dataset with interesting color management

• (cute:0.7), teenager, cute put emphasis on eyes and make them much better and teenager couteract the "chibi"/"kid" look it could create while still keeping a cute look

and some bonus keywords that can make it look even better, even if it depends a lot on your tastes ^^

masterpiece, extremely detailed furs, 8k,  soft fur, perfect composition, detailed shading, dynamic pattern with accents, detailed style, soft,

Good negative prompt keywords :

(neck fluff, fluffy neck,:1.2), lores, bad anatomy, warped, bad hands, BadDream, easynegative, boring_e621_v4, (ghbelly, bad face, ugly, dumb face, thin legs, flat hairs, bad abs, fluffy neck, neck fluff, fluff on the neck:1.2), (anime boy, human, human ear:1.4), verybadimagenegative_v1.3

There seems to be a bias towards females, so if you want to generate males, use:

female, woman, girl, 1girl,

If the shirts are cropped / always lifted, use:

crop top, cropped shirt, bra, shirt lift, 

Planned for next version (V5):

• Better tail control

• Reference sheet addition ?

• better dataset captionning

• I don't really know, don't hesitate to send ideas

• no mamagen please