Sign In

Samuel B. Roberts (Kancolle)

Download

1 variant available

SafeTensor

18.12 MB

Verified:

Type
LoRA
Stats

635

Reviews
Published

Jun 24, 2023

Base Model

SD 1.5

Training
Steps: 4,920
Epochs: 10
Usage Tips
Clip Skip: 2
Hash
AutoV2
D317D05183
Trigger Words
SamuelKC
default creator card background decoration
Followers - 289

289

Likes - 6472

6.5K

preview.png

An experimental character LoRA of Samuel B. Roberts from Kantai Collection.

Info

Training with 140 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 - 0.5)

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

SamuelKC, serafuka, long sleeves shirt, sleeve cuffs, aqua pleated skirt, miniskirt, blue sailor collar, aqua neckerchief, dixie cup hat, hat ribbon, star symbol (hat ribbon)

Some additional tags that you may use for reference

-whale
-brown eyes, fang