锐雯 灵魂莲华 Riven

https://s2.xiaonaofu.top/material/a8e28b32-6890-4ec3-9716-f3352088475e.jpeghttps://s2.xiaonaofu.top/material/bb5b4f2e-a8ab-4263-8240-322172c066b1.jpeghttps://s2.xiaonaofu.top/material/d7246c14-d3f6-4503-8b25-28668977077b.jpeghttps://s2.xiaonaofu.top/material/6c951801-1e16-49c1-9e81-320149c350a8.jpeghttps://s2.xiaonaofu.top/material/a39d59e7-a21e-4735-bb25-35a9b25059fd.jpeghttps://s2.xiaonaofu.top/material/c44f7538-c895-444f-86cf-62702fb24c76.jpegspirit blossom riven

Lora trained on Spirit Blossom Riven from League of Legends

models used

anime: CoffeeMix, PrimeMix, MeinaAlter

2,5D: GlassBones, Dark Sushi 2.5D, CamelliaMIx_2.5D_V2, MeinaUnreal – V3

realistic: fantasticmix_real

tags: spirit blossom riven, 1girl

optional tags: white kimono, white hair, single horn, hair ornament

negative embeddings: embedding:bad-hands-5, embedding:ng_deepnegative_v1_75t, embedding:bad-artist, embedding:EasyNegative

Recommended settings:

Make sure you are aware on the usage instructions of LORA

VAE: vae-ft-mse-840000-ema-pruned (for realistic models & 2,5D), kl-f8-anime2, blessed2.vae (for anime models)

Sampler: DPM++ SDE Karras or DPM++ 2M Karras

Steps: 20 to 35

Clipskip: 1 or 2

Upscaler : img2img in comfyui using 4x-UltraMix_Smooth

CFG Scale : 5 to 9 (mostly 7 and 8)

LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8)

Denoise strength for img2img: 0.4 to 0.7

If you want the exact same settings, just drag and drop the picture into ComfyUI

for the pictures i used comfyui

Hide

发表回复

后才能评论