凯尔 Kayle

https://s2.xiaonaofu.top/material/a42d273c-465d-4442-b3e7-2c82e6254ef2.jpeghttps://s2.xiaonaofu.top/material/deff9a84-4bd7-4126-a1e2-dcab64608a83.jpeghttps://s2.xiaonaofu.top/material/1f671b18-2896-49dc-9ce7-8ebc15b9976b.jpeghttps://s2.xiaonaofu.top/material/cdbaf665-4759-4687-9930-164a220ec92c.jpeghttps://s2.xiaonaofu.top/material/04aa1fb1-a2b5-4075-98e7-41fd4161d328.jpeghttps://s2.xiaonaofu.top/material/054598ec-a3cd-4244-ad11-9e4cd520882b.jpegkayle \(league of legends\)

Lora trained on Kayle from League of Legends

models used

anime: CoffeeMix, Anything and Everything, PrimeMix – v2.1

2,5D: CamelliaMIx_2.5D_V2, GlassBones, HELLmix, ReV Animated

tags: kayle \(league of legends\), 1girl

optional tags: angel wings, bodysuit, armor, yellow 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: orangemix.vae (for 2,5D pictures), vae-ft-mse-840000-ema-pruned (for realistic models), 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 0.7)

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