伊芙琳 魔女 Evelynn

https://s2.xiaonaofu.top/material/a5cfadeb-1a28-4f4d-91cc-78b36219983a.jpeghttps://s2.xiaonaofu.top/material/6e4f9fdf-e265-4299-998c-b7c4e0bae4b1.jpeghttps://s2.xiaonaofu.top/material/bedd834c-809e-497b-9518-a07b52bd6fd9.jpeghttps://s2.xiaonaofu.top/material/67b2d759-8f87-49f9-92b0-bf2e5d78c0e4.jpeghttps://s2.xiaonaofu.top/material/f2d5807e-292d-42cd-8e27-943b312e4166.jpegcoven evelynn

LoRA trained on Coven Evelynn from League of Legends

requested by @BangBangFukanawa

models used

anime: MeinaAlter, PrimeMix, YabaL_Mix V3,

2,5D: MeinaUnreal – V3, HELLmix, DarkSun, CamelliaMIx_2.5D_V2

Coven Evelynn: coven evelynn, 1girl

optional tags: bodysuit, hair ornament, red eyes

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
Discussion

发表回复

后才能评论