Type
LORA
Publish Time
2023-06-26
Base Model
SD 1.5
Trigger Words
ZuikakuKC
Copy
Version Introduction
The basic version of this LoRA









Training with 207 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!
LoRA Weighting: [1 - 0.9], (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: res2 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 :PZuikakuKC, japanese clothes, twintails, white hair ribbon, red hakama short skirt, tasuki, black thighhighs, hair between eyes-single glove, partially fingerless gloves, yugake
-muneate
-hair down, white headband, hachimaki, breastplate
The basic version of this LoRA
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
