ghost
Sign In

Muzan | Demon Slayer 2in1 Female & Male

243
1.6k
17
Verified:
SafeTensor
Type
LoRA
Stats
1,550
Reviews
Published
Apr 18, 2023
Base Model
SD 1.5
Training
Steps: 6,300
Epochs: 12
Trigger Words
MuzanMale
MuzanFemale
Hash
AutoV2
D0EEF3AA3B
default creator card background decoration
Holiday 2023: 5 lights
AhriMain's Avatar
AhriMain

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

  • 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