Download
1 variant available
1,2160 1 2 3 4 5 6 7 8 9,0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
210 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
30 1 2 3 4 5 6 7 8 9
(178)
May 23, 2023
SD 1.5

1.8K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
23.1K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

LoRA trained on Spirit Blossom Vayne from League of Legends
Requested by @BangBangFukanawa
Next will be Dragononess Zyra
models used
anime: MeinaAlter, YabaL_Mix V3
2,5D: HELLmix, CamelliaMIx_2.5D_V2, DreamShaper - 6
tags: spirit blossom vayne, 1girl
add "blindfold" for the blindfold version
optional: kimono, hair ornament, blue hair
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

.jpeg)