Type | |
Stats | 60 36 |
Reviews | (14) |
Published | Oct 11, 2024 |
Base Model | |
Training | Epochs: 50 |
Usage Tips | Clip Skip: 2 |
Trigger Words | KaniNayuta grey hair, blue eyes, long hair, hair scrunchie, (blue scunchie:1.2), hair flaps, ahoge NayuSweater, black sweater, white shirt, collared shirt, ribbon NayuNun, black dress, nun dress, ribbon NayuCasual, black vest, turtleneck, sweater, layered clothes NayuCasual2, (purple sweater:1.3), white skirt, suspenders, shirt tucked in NayuRPG, dress, blue jacket, off shoulder, cross |
Hash | AutoV2 8DFCED6A46 |
"Nayuta Kani" is a character from the anime "A sister is all you need!". This Model is trained on SDXL / Pony, This is a SFW Model, This Model is capable of both Nsfw and SFW, but i dont promote NSFW, i encourage to make SFW. This Model is Capable for Perfect Face and Casual wear.
Recommendations:
Use danbooru tagging for prompts
Sampler: "Euler a" at / 25 steps
Cfg scale: 7
Clip Skip: 2 <---- VERY IMPORTANT
VAE : sdxl_vae
Add Before Prompt : score_9,score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, score_anime, score_realistic Negatives: (EasyNegative:0.8), (worst quality, low quality:1.2), blurry, bokeh, dof, fogRecommendations (Hires Fix):
Upscaler: 4x-Anime
Hires steps: 14
Denoising strength: 0.52
Upscale by: any
If you want to get mostly the same results, you definitely will need negative embedding:
DeepNegative, it's better to use it at 0.8 weight.
NegativeHands, it's better to use at 1 weight.
Don't use a lot negative embeddings at the same time. It definitely will ruin any possible output on all models! If you want to use negative embeddings - use one for quality, and one for hands.