ユーザーLoRA

SD

Muzan(Male)

#鬼滅の刃
Muzan(Male) - AI Modelのカバー画像
アップロード日時
2023/07/11 10:50
採用数
1.6k
レビュー
大好評  (1)
トリガーワード

1boy red eyes male focus formal black suit white necktie white fedora

権限
  • 画像生成と共有を許可する
  • ユーザーによるモデルのダウンロードを許可する
  • 生成画像の商用利用を許可する

詳細説明

Lora trained on Muzan from Demon Slayer

Master model anime: Based65, AnyLoRA

2,5D: Lyriel

tags for Female Muzan: MuzanFemale, red eyes, kimono, black hair, red lips, hair ornament, earrings, jewelry

tags for Male Muzan: MuzanMale, 1boy, red eyes, male focus, formal, black suit, white necktie, white fedora

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

Hide

コメント

Muzan(Male)で生成した作品