Model used: AbyssOrangeMix3
Recommended VAE: orangemix or kl-f8
Recommended LoRA weight: 0.7-1 (I like 0.8 and 1)
Trigger words: saitama, anime, one punch
Recommended words in prompt: 1boy, bald, white cape, red gloves, belt
Negative prompt example:
(worst quality, low quality:1.4), 3d, realistic, tooth, rouge, lipstick, eyeshadow, greyscale, monochrome, text
On all images from preview I used DPM++ 2M SDE sampler, but you can use what you like.
All other settings the same as for AOM model:
Steps:
DPM++ SDE Karras: Test: 12~ ,illustration: 20~
DPM++ 2M Karras: Test: 20~ ,illustration: 28~
Clipskip: 1 or 2
Upscaler :
Detailed illust → Latenet (nearest-exact)
Denoise strength: 0.5 (0.5~0.6)
Simple upscale: Swin IR, ESRGAN, Remacri etc…
Denoise strength: Can be set low. (0.35~0.6)
This LoRA was trained on 234 images which I scraped from fancaps.net. I used wd14 tagger extension for Stable diffusion to automatically tag my images and LoRA trainer colab for training.
I plan to do a lot of LoRAs based on the One Punch Man anime. If you are interested, you can follow me.