Download
1 variant available
Initial release of LoRA trained on 106 images from fancaps.net which were automatically downloaded and filtered using my new Dataset Automaker.

1580 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
1.3K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

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: tomioka giyuu, demon slayer
(Unfortunately, I created the activation tag "tomioka giyuu" with a typo, the name is spelled giyu correctly)
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 106 images for me from original anime screencaps.
Download dataset of 106 images to train your own LoRA:
https://drive.google.com/file/d/1VTiyswi7DAIHYq9Y3N9JBAdJi2-it1Si/view?usp=sharing

