Bleach: Thousand Year Blood War Style LoRA
Reviews are very appreciated and show me you enjoy my work, keeping me motivated in releasing more Models in the future! Would love to see the community create images with my work.
v1.0 (Anima Base 1.0)
Trained on the Anima 1.0 Base model for compatibility with other Anima models.
All preview images are created using the MiaoMiao Harem 1.1 Checkpoint.
For more information check the "About this version".
The settings used to create the images were:
Steps: 30
CFG: 4
Sampler: Eular a
Scheduler: Normal
Denoise: 1Best Results are at 1 weight, using the following trigger word is optional but increases influence:
@vslinxbleachtybwv1.0 (Anima 0.1)
Trained on the Anima 0.1 Preview model for compatibility with other Anima models.
All preview images are created using the WAI-Anima 1.0 Base Checkpoint.
For more information check the "About this version".
The settings used to create the images were:
Steps: 30
CFG: 4
Sampler: Eular a
Scheduler: Normal
Denoise: 1Best Results are at 1 weight & using the trigger word:
@vslinxbleachtybwv1.0-v1.1 (NoobAI V-Pred)
Trained on the base NoobAI 1.1 V-Pred Version model for compatibility with all other NoobAI V-Prediction models.
All preview images are created using the Noobai-Cyberfix-V2/Perpendicular-Cyberfix-V2 (VPred) Checkpoint.
The settings used to create the images were:
Steps: 30
CFG: 5
Sampler: Eular
Scheduler: SGM Uniform
Denoise: 1Best Results are at 1 weight & using the trigger word:
vslinxbleachtybwv1.0 (NoobAI EPS)
Trained on the base NoobAI 1.1 EPS Version model for compatibility with all other NoobAI models.
All preview images are created using the NoobAICyberFix 3.0 Checkpoint.
The settings used to create the images were:
Steps: 30
CFG: 7
Sampler: Eular
Scheduler: Normal
Denoise: 1Best Results are at 1 weight & using the trigger word:
vslinxbleachtybwv1.0 (IL)
Trained on the base Illustrious-XL Model for compatibility with all other Illustrious models.
All preview images are created using the NoobAI-XL Epsilon-pred 1.1-Version.
The settings used to create the images were:
Steps: 28
CFG: 5.8
Sampler: DPM 2
Scheduler: Karras
Denoise: 1Best Results are at 1 weight & using the trigger word:
vslinxbleachtybw styleAll images were upscaled using the Remacri-4x Model.
All images were generated using my ComfyUI workflow that you can find here, attached to preview images or in the suggested resources. This includes a Detailer that automatically inpaints body parts like eyes, lips, hands etc.
So if your results do not match mine it's probably because of this. I recommend using the workflow which is also attached to every image.
IMPORTANT
Creating the Characters from the Show is completely dependent on the Base Model or other LoRA's you're using. This was done to ensure the LoRA would only affect the style of the image and not the depiction of characters and their outfits.
The character names were added to the prompts while not removing their characteristic features to ensure the LoRA has an idea of who the character is without overwriting the prompt you're using. Meaning if the base model or another LoRA you're using do NOT know the character, it has to be prompted by their characteristic features and not by their names.
These Characters are included in the training data:
inoue orihime
kurosaki ichigo
sado yasutora
ishida uryu
genryusai yamamoto
young genryusai yamamoto
child nelliel tu odelschwanck
kyoraku shunsui
ukitake juushirou
mallia menoly
loly aivirrne
emilou apacci
franceska mila rose
cyan sung-sun
abarai renji
hitsugaya toushirou
sui feng
bambietta basterbine
sajin komamura
matsumoto rangiku
unohana retsu
unagiya ikumi
kurosaki masaki
kurotsuchi mayuri
asguiaro ebern
ayasegawa yumichika
yhwach
tier harribel
urahara kisuke
quilge opie
ishida ryuuken
haschwalth jugram
kuchiki byakuya
as nodt
kuchiki rukia
zaraki kenpachi
sasakibe choujirou
shinji hirako
aizen sousuke
mcallon meninas
tenjiro kirinji
hikifune kirio
hyosube ichibe
shutara senjumaru
shiba kukaku
kotetsu isane
kuna mashiroDescription
By popular demand i kept on trying with Anima and this is the best iteration i was able to train so far. It's trained on the 0.1 version of the Anima Preview but tested on Anima 0.2 and 0.3 and it worked fine there too.
All example images were generated using WAI-Anima.
Warning: I'm not 100% happy with the training results and i might re-train it later, but i've tried to train a good lora on anima for months by now - ever since the Anima 0.1 release - and while i do like the prompt adherence and being able to do danbooru tags as well as natural language, i still think that the results especially in complex scenes are very subpar to most illustrious checkpoints i've worked with so far.
With illustrious i feel like i can just hit generate a few times with different seeds and 8/10 times i'll have a great image, while with Anima i only get a good image 2/10 times...
I hope Anima will become better and i know a lot of users who have left illustrious behind for Anima, but in my opinion Illustrious/NoobAI is still better for 90% of all of my cases since i don't really need/want to create scenes with multiple named characters.
Sometimes i still get body horror on Anima, no matter if i use simple prompts or complex ones, that is worse than what i've had when using SD1.5 or SDXL, maybe i'm just bad at using Anima - so we'll see how that developes!