阿狸 净雪之月 Ahri

https://s2.xiaonaofu.top/material/b59ae5fb-7bcb-4cc0-8ca6-5f1ef6d10255.jpeghttps://s2.xiaonaofu.top/material/ba17d98f-02f3-449e-ae0e-63122c284947.jpeghttps://s2.xiaonaofu.top/material/ebd22e41-68c6-4062-aaba-812520e808ae.jpeghttps://s2.xiaonaofu.top/material/6eb4ed6c-eb34-4a95-b060-992522348352.jpeghttps://s2.xiaonaofu.top/material/27bc13d2-9754-4e9c-9506-70bb7d0eddbe.jpeghttps://s2.xiaonaofu.top/material/54006897-c47c-41fd-82db-c0362f75c876.jpegsnow moon ahri

LoRA trained on Snow Moon Ahri from League of Legends

requested by @Merkuriij

models used

anime: PrimeMix – v2.1, Sweet-mix – v1.8 – flat

2,5D: NijiDiffusedMix – v2.0, PastelDiffusedMix – V2.1, CamelliaMIx_2.5D – V2, ReV Animated

realistic: Paragon V1.0

tags: snow moon ahri, 1girl

optional tags: japanese clothes, pink hair, hair ornament, bare shoulders, fox girl, whisker markings, necklace, energy ball, fox tail

negative embeddings: bad_prompt, negative_hand, ng_deepnegative_v1_75t, bad-artist, 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(euler a for img2img upscaling) from time to time im also using DPM++ 2M alt Karras

Steps: 20 to 35

Clipskip: 2

Upscaler : GitHub – pkuliyi2015/multidiffusion-upscaler-for-automatic1111 4x-UltraSharp(for 2,5D & realistic), 4xAnimesharp(for anime)

CFG Scale : 5 to 9 (mostly 7)

LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8 and 1)

Denoise strength upscaling: 0.3 to 0.55

for full body shots i recommend using: ComfyUI Impact Pack

or the a1111 alternative GitHub – Bing-su/adetailer

Hide

发表回复

后才能评论