阿狸 魔女 Ahri
AHRICOVEN
AHRI \(LEAGUE OF LEGENDS\)
1GIRL
Lora trained on Ahri from League of Legends
models used
anime: Based65, AnyLoRA
2,5D: Lyriel, fantasticmix_real, ReV Animated
tags: ahri \(league of legends\), AhriCoven, 1girl, blonde hair, multicolored hair
optional tags: hair over one eye, cleavage, animal ears, solo, long hair, blonde hair, fox ears, bare shoulders, tail, fox tail, facial mark, magic, makeup, fingernails, looking at viewer, purple lips, bangs, sharp fingernails, parted lips, dress, lipstick, detached sleeves
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
Trained with AnyLoRA checkpoint
for the pictures i used comfyui
设计人生
