Verified: 2 years ago
SafeTensor
Type | |
Stats | 522 |
Reviews | (88) |
Published | Aug 31, 2023 |
Base Model | |
Training | Steps: 3,280 Epochs: 10 |
Usage Tips | Clip Skip: 2 |
Trigger Words | AobaKC, (Aoba) uniform |
Hash | AutoV2 CD4735181B |
An experimental character LoRA of Aoba from Kantai Collection.
Info
raining with 130 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 :PBasic prompts
AobaKC, (Aoba) uniform, (white) serafuku, (hair) scrunchie, (lavender blue) sailor collar, (yellow) neckerchief, (lavender blue) shorts, (black) thighhighs, shoes
Some additional tags that you may use for reference
-(blue) scrunchie, (short sleeves) serafuku
-blue eyes