凯特琳 泳池派对 Caitlyn

https://s2.xiaonaofu.top/material/8c6cb8a1-b335-4ffc-bf20-118dd344365c.jpeghttps://s2.xiaonaofu.top/material/755a8457-dc20-48c1-bc90-1c2294fb0b92.jpeghttps://s2.xiaonaofu.top/material/2382fa6b-62ed-4d13-9c45-1f0ca2b11720.jpeghttps://s2.xiaonaofu.top/material/f16c976f-3858-4e75-8f29-5430906ecb72.jpeghttps://s2.xiaonaofu.top/material/003ab213-c4f8-4cd3-8a55-5c151770d255.jpeghttps://s2.xiaonaofu.top/material/7a06089f-e99c-4bc3-8c4b-94f300233f7f.jpegpool party caitlyn

Lora trained on Pool Party Caitlyn from League of Legends

models used

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

realistic: fantasticmix_real

tags: pool party caitlyn, 1girl

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

发表回复

后才能评论