Style lora to make Anima tend more toward realism. I will update it until I feel it is consistent and works with a wide enough range of characters and concepts. The initial version seems to work best with the DDIM sampler and a cfg around 5-6 with 20 steps. The trigger keyword is ph0t0an1ma, but depending on the version you may need to increase the trigger word strength and add in other descriptions of the realistic style.

Last beta version before I try training it on the Anima release version. Slightly reduced dataset seems to have further pushed the style toward realism, albeit more of a 3d render style rather than full photorealism. The trigger words and settings remain the same as prior versions.

Beta 0.2

Trained on the same dataset as the alpha version at a much higher resolution, still produces detailed images consistently, though may require additional prompting for higher realism. Since the dataset contained a few CGI and AI images, sometimes the results are a bit iffy, especially for certain characters, I will try and prune the dataset for future versions to fix this issue. The trigger keyword is "ph0t0an1ma" but I also recommend including a few negatives that are in the example pictures to further enhance the style.

Beta 0.1

Thanks to a training workflow kindly provided by <a rel="ugc" href="https://civitai.com/user/7err4">7err4 </a>,this version actually produces different outputs from the base model, increasing the realism of images across all sampler types and requiring less prompting for a realistic style. However, some character's/concepts may still have a plastic or overexposed look due to some of the images I used in the set being AI generated or CGI. I recommend using negatives and additional prompting to try and rectify this issue, but I will have to prune my dataset in hopes of making future versions work better. The trigger word is just "ph0t0an1ma" and it works fine enough to trigger the style, though I recommend using "cosplayer" to describe characters you want as that seems to nudge the base checkpoint toward realism. Since the base model is capable of some realism you can probably lower this LORA's strength if you think its altering the proportions or textures too much.

ALPHA

Photo Anima

physical violence

weapon violence

wide hips

revealing clothes

thick thighs

downblouse

convenient censoring

huge breasts

pg-13

corpses

suggestive

oral invitation

pg13

sexy

sexual situations

male nudity

disturbing

male swimwear or underwear

female swimwear or underwear

partial nudity

undressed

female nudity

breasts out

exposed female nipple

breast out

lingerie

male underwear

hair over breasts

female swimwear

gigantic breasts

no panties

graphic violence or gore

covered nipples

huge butt

strapless leotard

sitting on face

emaciated bodies

one breast out

nsfw

female underwear

nude

graphic male nudity

adult toys

illustrated explicit nudity

nudity

graphic female nudity

hentai

futanari

porn

sexual intent

genitals

peeing

vore

oral

sexual activity

anal

blowjob

dildo riding

incest

hanging

hate symbols

nazi party

white supremacy

diapers

scat

self injury

hate speech

urine

extremist

child on child

latex clothing

swimwear

bukkake

fellatio

cumshot

implied fellatio

eat_cum

cumdrip

cum in pussy

cum on face

after fellatio

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

triple fellatio

autofellatio

fucked silly

cum on pussy