Sign In

Nezuko (Demon Slayer)

66
436
4
Verified:
SafeTensor
Type
LoRA
Stats
436
Reviews
Published
Aug 24, 2023
Base Model
SD 1.5
Training
Steps: 1,515
Epochs: 10
Trigger Words
kamado nezuko
demon slayer
Hash
AutoV2
E3A237ADC8
default creator card background decoration
First Birthday Badge
Maximax67's Avatar
Maximax67

If you enjoyed this LoRA, please hit the like button and give it a 5-star rating. Your encouragement motivates me to keep creating LoRAs like this.

Model used: AbyssOrangeMix3

Recommended VAE: orangemix or kl-f8

Trigger words: kamado nezuko, demon slayer

On all images from preview I used DPM++ 2M SDE sampler, but you can use what you like.

Upscaler :

  • Detailed illust → Latenet (nearest-exact)
    Denoise strength: 0.5 (0.5~0.6)

  • Simple upscale: Swin IR, ESRGAN, Remacri etc…
    Denoise strength: Can be set low. (0.35~0.6)

This LoRA was made using my new Dataset Automaker, which automatically make a dataset of 101 images for me from original anime screencaps.

Download dataset of 101 images to train your own LoRA:

https://drive.google.com/file/d/1P09voU4-WuHDkoNwByQiBs8VBxCK9s3w/view?usp=sharing