characters from anime: "Boku no Kokoro no Yabai Yatsu"
Trigger words:
annayamada
kyoutarouichikawa
chihiro kobayashi
moeko sekine
honoka hara
serina yoshida
//small dataset
kenta kanzaki
shou adachi
//small dataset
chikara oota
//small dataset
haruya nanjou
// small dataset
background
// small dataset
(small dataset ones is harder to control, but usable too)
strength 0.4-0.8, hiresfix or img2img for best results(it's works for every LoRa).
You can see it on preview - 2 main characters without hiresfix, other with.
if you get bad results - try https://civitai.com/models/4669/corneos-7th-heaven-mix this checkpoint and write in prompt position(like "front view, face"), because dataset not only front-face.
Train models isn't easy, crypto donations on some coffee are welcome:
https://plisio.net/donate/pm9qVYci
or here (not crypto) https://boosty.to/blessedworld/donate