🌕 LUMA
This is anime-based semi-realistic mix of checkpoints and loras tweaked for good results on simple prompts.
Model is fully compatible with all LoRA that I made and will make in the future.
All the content I make is and will be completely free on CivitAI.
But if you want to support me with a coin, then you can do it here.
Luma A3 VAE Style and Artist List (please note, that some of styles need additional tags like "retro artstyle, faux traditional media, painting", etc):
Please note that tags "3D, REALISTIC, ANIME" in positive or negative may change look of your images significantly.
I also higly recommend to add "score_5, score_4, ps1 screenshot, 3d, niji" in negative prompt, if you're not going to use it in positive.
Also note, that i added somme extra tags for concepts.
For example:
altshaped - will help you make humanoids with alternative anatomy
overdesigned - will help you make some complex designes if your prompt assumes it.
Complete style list:
123wsty
ahriman, anime
albrecht dürer
alex ross, retro artstyle
alexkonstad
aloija
amadmir
anato finnstark
anbudehuang
anime
arcane
asahiart, automaton, altshaped
boris valejo
brenda burke
burda, grungetech
castlevania, anime
cher-ro
cherrygig
chibi herowars
claude monet
cmg
darkest dungeon, high contrast
dashiana
degenesis
demessance
deus ex, cyberpunk
disney, flat color
dkeeno
drakonoart
dravacus
dreelrayk
eddie mendoza
edgerunners, anime
elden ring
fanfoxy
galyosef, 3d
ganas
greg rutkowski
hades
hearthstone
henry asencio
hizipro, high contrast
ikenaga yasunari
indus
ivan kramskoy
jandrew, scenery, environment
jeremy mann
jim lee
john william waterhouse
jojo
jose parra
jparked
junejenssen
kael ngu
krrat, overdesigned
kylepunk
laurelin
leicai
lol
lovk1y
makoto shinkai, style
mangamie
marta nael
max kostin
mengxuanli
mixppl
mohrbacher, divine, altshaped
mtg
nadar
nicolasaviori
niji
nixeu
othalam
painting \(medium\)
papsuev
peterskore
photo, realistic, cinematic
pixar, 3d
ps1 screenshot
qichao wang
rakavka
reliah
retrofuturism syd mead
saiya-art
sanchare
scenery, environment
shinjuku
smite
stephen pan
stumpyfongo
sugarpunk, cyberpunk
tck, altshaped
templarpainter
tixnen
tomas duchek
trufanov
valentin serov
valorant
vegera
viktor vasnetsov
vincent van gogh
warcraft
wayfinder
wlop
wroniec
wushenyou
yumingli
yuriiiko, flat color
zack snyder style, movie still, cinematic, realistic
zexiguo, overdesignedPDXL Usage:
Clip Skip 2
Sampler: Euler a / DPM ++3M SDE (SGM Uniform) (or any your favorite)
Steps: 30-40
CFG Scale: 5-7
Hires.fix: x1.5
Upscaler: 8x_NMKD-Superscale_150000_G for realism or R-ESRGAN 4x+ Anime6B for illustrations (Denoising strenght 0.2-0.3)
Hires steps: 15
Never use Face Restoration!
If you want better faces just use AutoChar or AfterDetailer.
Useful tags (negative):
wrinkled skin, double head, mutant, bad anatomy, fewer digits, bad hands, extra limbs, twisted, cropped, out of frame1.5 Usage
Recommended embeddings:
1. easynegative
2. easynegativev2
3. bad-hands-5
4. badhandv4
Recommended extensions:
1. AutoChar
2. AfterDetailer
My regular settings:
Clip Skip 2
Necessary negative prompt: easynegative or easynegativev2
VAE: kl-f8-anime2
Sampler: any
ENSD: 31337
Hires.fix: x1.5 and higher
Upscaler:
Option 1: 8x_NMKD-Superscale_150000_G for realism or R-ESRGAN 4x+ Anime6B for illustrations (Denoising strenght 0.3-0.5)
Option 2: Latent (any) or Lanczos (Denoising strength 0.5-0.6)
Never use Face Restoration!
If you want better faces just use AutoChar or AfterDetailer.
In 0.9X version you may use tags like 3d, realistic in positive or negative prompt to increase/decrease realistic shading. (Check sample images for examples)
But you may feel free to experiment.
Please note that this model is horny sometimes, so I strongly recommend to tag some clothes (pants or something) and using these tags in a negative prompt to avoid NSFW: nsfw, naked, nude
Useful tags (not necessary, just minor tweaks): volumetric light, realistic, dark atmosphere, volumetric light, caustics, absurdres, eye focus, contrast, dark scene, bright scene

Description
Completely remade version.
Much more stable than any other version.
Much more flexible than any other version.
Better faces.
Support more styles.
Can run with clip skip 2 or 1.
Less artifacts.
Less burn-in.
FAQ
Comments (27)
Hi, thanks for sharing!
But doesn't matter how hard I've tried, I just can't achieve similar results. I'm using ADetailer, correct prompt's words, kl-f8-anime. Could you please help me find out what the issue is?
Here's my generation:
https://civitai.com/posts/442784
Hi there. Do you have easynegative embedding? You may find link in model description.
@sadxzero It works! Thank you so much! Not just for sharing this amazing model, but also for the quick and detailed help. My bad, totally new here.
Can you please upload versions without the VAE? sometimes this complicates the use of LORAs
does anyone know of any prompt to make the women less busty ? no matter what prompt/negative prompt i enter they are always built like crazy
Gimme an example of you classic prompt so we can figure it out.
@sadxzero "1girl, russian, young, age 35, smooth skin, petite, heart shaped thin face, [flat chest::0.6], standing, house, choker, full body, kinky, lingerie, jewelry, leather, looking at camera, photo \(medium\), solo, standing, 3d, realistic, warm colors, detailed"
is my average positive prompt
@sneksnek24 have you tried prompting against large builds in your negative prompt?
@randallaware yeah yeah i did that too, putting "busty" "voluptuous", etc, but it doesnt work
@sneksnek24 Try using any combination of 'pettanko' in the positive prompt, 'big breasts' in the negative prompt and the 'Perfect Perky Breasts V3' LoRa. Doing all three has a major cumulative impact.
Positive Prompt: flatchested flat chest small breasts
Negative Prompt: busty
Works perfectly. Scale up/down the terms in positive and negative prompt as needed to adjust size.
Excellent model! Any idea what might be making me get glassy, pupil-less eyes though? It even happens after upscaling with Ultra-Sharp 4x.
This is one of my favorite checkpoints for Sci-Fi and Fantasy images, and I can't wait for an SDXL version.
0.9X is a pure masterpiece like no other models here
Could you upload prunned (fp16) versions for smaller size?
I like 0.98 the most as more recent version lost some concepts.
Easily my favorite model for both SFW and NSFW images, with some of the very best hands and feet of any model I've used. Strategic use of negative prompting can get you outside of the default muscular/stacked characters.
Could you share that prompt strategy
Kindly asking for pruned version
For V0.99,the dark part nearly solid black,0.98 is my favorite model, gonna try 0.9x
what you like 98 or 9x??
Really nice model, loving the style!
One of my most favorite checkpoints. As said in description: avoid face detailer ... it can change gender in face. ;D
nice model, will you be releasing a style of it for XL?
thanks for putting in effort to create this.
Please file it appropriately though.
Currently, this is registered as type "checkpoint trained", when it is actually a checkpoint merge. Could you edit the civitai page and fix please?
Thank you for creating this. It's my new main model for my DnD Illustrations.
Will you create and XL version of it too?
Awesome work! Just wanted to say thank you. Also, I'm curious, what are your thoughts on what will be possible with this checkpoint or updating it, in a year, or two?
will things get increasingly better, or have we hit the height of what its capable of?
Any update for future ?
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.










