Just like my pony version this is another attempt at merging characters and a style but this time for Illustrious, overall I would say both the style and character consistence is much better but the flexibility is not there some checkpoints just don't apply the style at all (never mind setting the weight to 1.2 seems to help), I have 3 images in the of comparison but checkpoints and using different charterers one being from this lora, another one being a random charterer and the other is another lora on top of this one, I might give this one more go but not anytime soon
trained over 262 images for 1024 using AAA as a training model
Style info:
trigger word: kmstyle
weight: 1 is perfect
Characters info:
Trigger word - looks tag
Kim: kimaps - long hair, orange hair, green eyes
Monique: moniiqkue - black eyes, black hair, dark-skinned female, dark skin
Bonnie: bomnkinie - short hair, brown hair, green eyes
Ann: ankkii - brown hair, short hair, blue eyes, doctor, lab coat
Shego: shmeikgo - black hair, long hair, green eyes, gloves, bodysuit, lipstick
Betty Director: kmdbd - brown hair, eyepatch, black eyes, short hair, smile, dark blue bodysuit, long sleeves, black belt
If you wanna support me ko-fi
Additional information:
Webui I use
AAA Anime VAE SDXL v1_4 as VAE
Sampling method: Euler a
Schedule type I set it to automatic
Sampling steps I go 20-30
4x-Ultrasharp as an Upscaler
Hires steps I go 8-15 (I don't always use hires fix)
Denoising strength I go 0.4
Upscale by 1.2 to 1.5 depending on the starting image dimensions
Detail Daemon at default settings
Imagine dimensions vary depending on what I'm trying to do
I use 5 CFG Scale and CFG Scale Fix set at 9
uddetailer for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full face