Training with 65 images, contain few image of costume variation
Followed the manual form [ [Guide] Make your own Loras, easy and free ],
You can access to this guide in Suggested Resources section.
Sampler: Euler a, DPM family series
Sampling steps: 20 or 25+
CFG Scale: 7
CLIP Skip: 2
*Do not use [restore face] on anime character!*
LoRA Weighting: [0.95 - 0.85], (1 - 0.6)
Baking Step:
0. Drafting (512 x 512 res to find your desired sketch)
1. Hires fix (txt2img: 768 x 768, 768 x 512, 512 x 768, or above res)
2. inpaint (img2img: refine some unwanted effect, [Euler a] with 50+ step)
3. Upscaling (img2img: res*2 with [ControlNet Tile] & Ultimate SD upscale)
Upscaler for [Step 1 - 3]: [R-ESRGAN 4x+ Anime6B, 4x-AnimeSharp, 4x-UltraSharp]
I always skip Step 0, 2 :P
RangerKC, (blue and white)_two-tone dress, (blue skirt), short sleeves, blue necktie, white gloves, pantyhose, side braids
RangerSanma
RangerKC, RangerSanma, white jacket, long sleeves, blue denim skirt, black pantyhose, boots, black footwear
OPTIONAL:fishing rod, white fishing cooler
Rangerkimono (Ref to New Year costume)
RangerKC, Rangerkimono, light aqua kimono, big white fur collar covering neck
RangerOni
RangerKC, RangerOni, (tiger print)_pinafore dress, BREAK,(red sweater:1.3), BREAK, horn, black thighhighs
Drunk Ranger
closed eyes, blush, holding wine glass, drinking glass, alcohol, wine, drunk, drooling
-fang, 1.8L sake bottle