I present my attempt at a Illustrious character LoRA for Munehisa Iwai from Persona 5.
V3 is my third version and attempt further increase the detail level of generations. I started over on my training set for this one to try and make it more versatile. In my testing this version worked a bit better with 2D/anime styles compared to my other versions.
LoRA strength recommendations
Use LoRA strength 0.7 with about CFG 3-4.
The tags for V3 are as follows:
main tags
m_iwai, 1boy, mature male, neck tattooneck tattoo - can be a bit temperamental at times, you can just leave this tag out if you don't care about full accuracy of the original character likeness (character asymmetry and AI do not go well together).
outfit tags
pinstripe hat, ear protection, black turtleneck, grey long coat, hood down, jeans, bootsoptional tags:
lollipop, pierced earThe settings I used for my generation testing were 3-5 CFG, 20 steps, DPM++ 2M SDE - Karras on Forge with an adetailer (face_yolov8s).
V2 is my second attempt and to try increasing the detail level of generations. In my testing this version definitely responded better to realistic prompt tags and looked much sharper on the results. If you want a softer look use anime and other such tags or just use V1 of the LoRA instead.
LoRA strength recommendations
Use LoRA strength 0.7 with about CFG 3-5.
The tags for V2 are as follows:
main tags
m_iwai, 1boy, mature male, grey hair, very short hair, grey eyes, long sideburns, stubble, neck tattooneck tattoo - can be a bit temperamental at times, you can just leave this tag out if you don't care about full accuracy of the original character likeness (character asymmetry and AI do not go well together).
outfit tags
pinstripe hat, ear protection, black turtleneck, grey long coat, hood down, jeans, bootsoptional tags:
lollipop, earringsThe settings I used for my generation testing were 3-5 CFG, 20 steps, DPM++ 2M SDE - Karras on Forge with an adetailer (face_yolov8s).
V1 is my initial attempt and produces rather nice results.
LoRA strength recommendations
Use LoRA strength 0.7 with about CFG 3-5.
The tags for V1 are as follows:
main tags
m_iwai, 1boy, mature male, grey hair, very short hair, grey eyes, long sideburns, stubble, neck tattooneck tattoo - can be a bit temperamental at times, you can just leave this tag out if you don't care about full accuracy of the original character likeness (character asymmetry and AI do not go well together).
outfit tags
pinstripe hat, ear protection, black turtleneck, grey long coat, hood down, jeans, bootsoptional tags:
lollipop, multiple earringsThe settings I used for my generation testing were 3-5 CFG, 20 steps, DPM++ 2M SDE - Karras on Forge with an adetailer (face_yolov8s).
Description
V2 is my second attempt and to try increasing the detail level of generations. In my testing this version definitely responded better to realistic prompt tags and looked much sharper on the results. If you want a softer look use anime and other such tags or just use V1 of the LoRA instead.
LoRA strength recommendations
Use LoRA strength 0.7 with about CFG 3-5.
FAQ
Looks like we don't have an active mirror for this one right now.
This archive is kept alive by community contributions, so there are still some gaps, especially for newly removed content.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.