Тип
LORA
Время публикации
2023-07-10
Базовая модель
SD 1.5
Слово-триггер
ShigureKaiSanKC
ShigureKaiSanCasualKC
Копировать
Версия введения.
The basic version of this LoRA







Training with 101 images
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!*
This LoRa Weighting: [1 - 0.9], (1 - 0.65)
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 :PShigureKaiSanKC, (sleeveless) shirt, (black and white) two-tone shirt, (black) pleated skirt, (black) thighhighs, (red) necktie, (white) belt, (black) fingerless gloves, (red) hand ribbonShigureKaiSanCasualKC, (long sleeves), hat, (white) beret, (white) shirt, (white) dress, (black) jacket, (red) necktie-hair over shoulder, hair ornament, hair between eyes, blue eyesThe basic version of this LoRA
1. Права на репостнутые модели принадлежат оригинальным создателям.
2. Для подтверждения авторства модели создателям следует обратиться к сотрудникам SeaArt AI через официальные каналы. Нажмите, чтобы подтвердить
