An experimental character LoRA of Aquila from Kantai Collection.
Info
raining with 64 images
Followed the manual form [ [Guide] Make your own Loras, easy and free ],
You can access to this guide in Suggested Resources section.
Recommended set up
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: [1 - 0.8], (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
Basic prompts
AquilaKC, (Aquila) outfit, (Aquila) hairclip, (red) jacket, (black) miniskirt, (black) thighhighs, (white) garter straps, boots
Some additional tags that you may use for reference
-(long sleeves) jacket, juliet sleeves, puffy sleeves
-(white) collared shirt
-(Aquila) skirt
-(green) neck ribbon with (sliver) ornament
-armpit cutout, clothing cutout
-bow (weapon), holding bow (weapon)
-brown eyes, yellow eyes, orange eye => (brown|orange) eyes
