Four new ways to get seen and get paid: sticker placement, remix galleries, cosmetic packs and collab collections. Plus free placements on every image, so you can join in without spending a thing.

The Creator Collab Update

You can gift a membership to someone else, or buy one with Buzz instead of a card. Here's exactly what each one gets you.

Membership Update

Sell a set of cosmetics as one listing at one price, instead of one piece at a time. Two to twenty items, any kinds mixed, other creators' work included.

Cosmetic Packs

We're a Day-0 launch partner for MiniMax H3, a next-gen open-weights multimodal video model - and it's already in the generator. No waitlist. Open weights land in a few days.

MiniMax H3 is live: open-weights video, generate now

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.

Further improved Anima 1.0 version trained on a smaller but more photorealistic dataset at a higher resolution and for more steps. I found this version to be overall more realistic and detailed than prior ones, especially with the correct sampler settings and negatives. The trigger word is still "ph0t0an1ma", but I have found that "photograph" helps improves the realism, and if you are doing a specific character, use "cosplayer" after the character name to ensure realism. The ideal settings I have found to be are around 30 steps, a CFG of around 5, and most importantly, the DDIM sampler, as base euler and DPM samplers will produce more 3d CG results rather than photo-like ones.

Beta 0.4

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

Photo Anima

physical violence

weapon violence

wide hips

revealing clothes

downblouse

convenient censoring

pg-13

corpses

suggestive

oral invitation

pg13

sexy

huge breasts

thick thighs

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

female underwear

nude

nsfw

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