Bunnii O'Hare from Fortnite — all six of her in-game styles in one file.
Base, Hopper's, Auric, Phase, Rimebound and Cosmic Legacy, each on its own
trigger word, plus the character out of costume.
WHY I MADE THIS
This is only my second LoRA. I do this for fun and because it is a genuinely
good technical puzzle — that is the whole reason, there is no plan behind it.
It started as an entry for a bounty here on Civitai. I was too slow. The bounty
closed while my dataset was still unfinished and it went to someone else, fairly.
But by then I had looked properly at what already exists for this character, and
both public LoRAs stop at two styles. I wanted all six in one file. Nobody had
made that, so I finished it anyway, mostly out of stubbornness.
THE PART THAT WAS ACTUALLY HARD
Not the training. The captions.
If a tag appears on EVERY image of a concept, the model stops treating it as a
tag and folds it into the trigger word. It quietly becomes something you can no
longer turn off. All 114 of my reference images were 3D game captures, so 3d
sat at 114/114 — meaning the LoRA would have rendered everything as a game
screenshot forever, whatever you prompted.
What does not work is naming the thing you do not want. What works is
CONTRADICTING IT WITH IMAGES. I generated 28 extra pictures in flat anime
shading and folded them into the set. 3d dropped to 80%, and the render style
became something you can actually ask for or refuse.
Same trick for the suit: 18 out-of-costume images took bodysuit from 100% down
to 87%. That is the only reason this LoRA can put her in a sweater and jeans
instead of always armouring her up.
Two styles never got that treatment. Auric and Hopper's have no anime references
anywhere, so 3d is still at 100% for those two tokens and they will always look
more like game capture than the other four. It is an honest asymmetry and it is
in the limits below, with everything else I know is wrong with it.
THE TRIGGERS
bunniibase Bunnii O'Hare navy / white / gold
bunniihoppers Hopper's Legacy dark teal / white / pink
bunniiauric Auric Legacy black / gold
bunniiphase Phase Legacy iridescent / holographic
bunniirime Rimebound Legacy cyan / white / silver
bunniicosmic Cosmic Legacy starfield / nebula
bunnii her out of costume (use this one on its own)
You can put bunnii in front of a style token, but you do not have to — on
paired seeds, dropping it moves the image less than simply rerolling does.
One thing please keep in your prompt: adult woman, mature female. She has a
mascot silhouette and that wording is on all 143 training captions. It is there
for a reason.
Description
SETTINGS
Base Anima-Base v1.0. Trained against Base, so it carries over to
Anima-Turbo, JANIMA and the all-in-one; the reverse is not true.
Strength 1.0
Sampler er_sde Scheduler beta
CFG 4.5 Steps 30
Size 832x1216 portrait, or 1216x832
There is no clip skip. Anima encodes with a Qwen3 text encoder and an
adapter, not CLIP. Any clip-skip value is ignored.
TAG LISTS — one per style
Each style has a costume block that was trained on every single one of its
images. The trigger already carries it: writing it out changes nothing, and
it is reproduced here so you know what the token contains.
bunniibase purple hair, blue eyes, purple lips, white hood, gold trim,
navy blue bodysuit, white chest plate, white gloves,
white armor, gold armor, gold emblem, white boots,
rabbit tail, bodysuit, high heels
bunniihoppers blonde hair, blue eyes, pink lips, white hood, pink trim,
dark teal bodysuit, white chest plate, white gloves,
pink armor, white emblem, pink boots, rabbit tail,
bodysuit, high heels
bunniiauric blonde hair, brown eyes, gold lips, gold hood, orange lining,
black bodysuit, gold chest plate, black gloves, gold armor,
gold emblem, gold boots, rabbit tail, bodysuit, high heels
bunniiphase pink hair, pale lips, iridescent hood, iridescent bodysuit,
holographic, pearlescent, opalescent, iridescent armor,
iridescent gloves, white boots, rabbit tail, bodysuit,
high heels
bunniirime purple hair, cyan lips, white hood, silver trim,
cyan bodysuit, white chest plate, cyan gloves, silver armor,
white emblem, white boots, rabbit tail, bodysuit, high heels
bunniicosmic purple hair, dark purple lips, starfield, galaxy print,
nebula bodysuit, cyan gradient, magenta gradient, dark hood,
dark gloves, dark armor, dark boots, rabbit tail, bodysuit,
high heels
bunnii purple hair, blue eyes, purple lips
(out of costume — no style token, no bodysuit)
WHAT IT DOES — tested, with the pass and fail conditions written down first
Ten conditions, two seeds each, criteria fixed BEFORE generating. Eight
passed, one failed, one works poorly.
Works action and motion; complex environments (night streets, rain,
crowds); civilian clothes with no costume piece bleeding through;
forced anime rendering; stacking with a style LoRA; two characters
in one frame; nudity with correct anatomy; hands holding an object;
alternate styles under scene lighting rather than flat backdrops.
Fails hood down. 1 success in 4 attempts. See below.
Poorly two characters in DIFFERENT styles — you get two figures, but the
colourways bleed into each other and the composition drifts toward
a character sheet.
WHAT IT DOES NOT DO — known defects, named rather than hidden
HOOD DOWN IS UNRELIABLE — 1 success in 4.
hood down appeared on 43 of the 125 in-costume captions against 82 for hood up.
It is not absorbed, it is outvoted. Two things help:
- name NO hood in your prompt. white hood together with hood down gave
0 successes in 2; removing it gave 1 in 2.
- expect to reroll the seed.
THE EAR LINING COMES OUT CYAN ON AURIC AND COSMIC.
Auric's lining should be orange and Cosmic's should be a starfield. Five of
the six styles share a cyan lining in the reference captures, so the minority
cases had no contrast to separate against. No tag fixes this.
bunniiauric AND bunniihoppers CARRY 3D RENDERING AND CANNOT SHED IT.
3d appears on 23/23 auric captions and 18/18 hoppers captions, against
26/29 for base. At 100% a tag is absorbed by the token, so these two styles
will look more like game capture than the other four. This is asymmetric and
it is a limitation, not a preference.
DEFAULT RENDERING IS ANIME, NOT GAME CAPTURE.
Despite 114 of the 143 training images being 3D game captures, the LoRA
renders in anime by default. 28 counter-examples were generated on purpose to
make the render style detachable, and they over-corrected. Whether it can
produce the game look on demand has NOT been tested.
OUT OF COSTUME, IDENTITY IS THIN.
Without the suit the character is carried by hair, eyes and lips only. There
is no bodysuit-free variant of the five Legacy styles: bodysuit sits at
100% in all six style concepts, so it is absorbed by the token. For higher
ratings, OPEN the suit unzipped bodysuit, bodysuit pulled down) rather
than removing it.
HOW IT WAS MADE
Trained with kohya-ss/sd-scripts (anima_train_network) against Anima-Base
v1.0, on a single 8 GB card. 1 h 29, peak VRAM 7997 MB of 8192.
unet-only, dim/alpha 32, CAME (weight_decay 0.01), lr 7e-5 / unet 2e-5,
cosine with 5 warmup steps, sigmoid timestep sampling, l2 loss, 1024 with
aspect-ratio bucketing and no upscaling, batch 1, bf16, 1600 steps, seed 42.
Checkpointed every 200 steps so the epoch could be chosen by looking rather
than by taking the last one.
Dataset: 114 in-game reference captures across the six styles, plus 28
generated images whose only job was to introduce VARIATION the captures did
not have. Without them 3d sat at 114/114 and bodysuit at 114/114 —
constant, therefore absorbed, therefore imposed on every output. With them:
80% and 87%, therefore detachable. Verified afterwards, not assumed.
Seven concepts: the six styles plus one out-of-costume concept that carries
no style token, because there is no style to designate on a woman in a
t-shirt and attaching one would teach a false association.
Captions were built by merging a hand-written fact sheet per style with what
a WD14 tagger actually saw in each image, so the vocabulary describes the
pixels rather than a marketing blurb.