Sign In

Perth (Kancolle)

94
595
5
Verified:
SafeTensor
Type
LoRA
Stats
595
Reviews
Published
Jun 29, 2023
Base Model
SD 1.5
Training
Steps: 3,250
Epochs: 10
Usage Tips
Clip Skip: 2
Trigger Words
PerthKC
Hash
AutoV2
530716CF3C

An experimental character LoRA of Perth from Kantai Collection.

Info

Training with 65 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

PerthKC, school uniform, (white) short sleeves, shirt, (green) vest, (blue) pleated dress skirt, plaid, (blue) necktie, (green) thighhighs, ribbon, loafers, badge, (green) cape, cloak

Some additional tags that you may use for reference

-short hair, long hair
-purple eyes