薇恩 灵魂莲华 Vayne

https://s2.xiaonaofu.top/material/2d78678b-bf2e-4a57-a19c-09e493975aac.jpeghttps://s2.xiaonaofu.top/material/943f03dc-bbf2-43c9-9aef-778836e0d3f0.jpeghttps://s2.xiaonaofu.top/material/4fef3d1a-29b0-450d-83f4-02196f4ebb1c.jpeghttps://s2.xiaonaofu.top/material/ece534cd-5927-4fad-a002-483cb2a7b3b6.jpeghttps://s2.xiaonaofu.top/material/569e8fe1-bb74-4a4c-9832-04236276474d.jpeghttps://s2.xiaonaofu.top/material/00d85700-5b21-487e-9380-9231e5f2c1bf.jpeghttps://s2.xiaonaofu.top/material/c9e30778-66b3-452f-8547-9f8cbe12aaf1.jpeghttps://s2.xiaonaofu.top/material/e2e6926b-406b-409f-ae5e-cfee34805117.jpegspirit blossom vayne

LoRA trained on Spirit Blossom Vayne from League of Legends

Requested by @BangBangFukanawa

Next will be Dragononess Zyra

models used

anime: MeinaAlter, YabaL_Mix V3

2,5D: HELLmix, CamelliaMIx_2.5D_V2, DreamShaper – 6

tags: spirit blossom vayne, 1girl

add “blindfold” for the blindfold version

optional: kimono, hair ornament, blue hair

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: 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

for the pictures i used comfyui

Hide

发表回复

后才能评论