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: <a target="_blank" rel="ugc" href="https://civarchive.com/models/9942/abyssorangemix3-aom3">AbyssOrangeMix3</a>Recommended VAE: orangemix or kl-f8Trigger words: agatsuma zenitsu, demon slayerOn all images from preview I used DPM++ 2M SDE sampler, but you can use what you like.Upscaler :<ul><li>Detailed illust → Latenet (nearest-exact) Denoise strength: 0.5 (0.5~0.6)</li><li>Simple upscale: Swin IR, ESRGAN, Remacri etc… Denoise strength: Can be set low. (0.35~0.6)</li></ul>This LoRA was made using my new <a target="_blank" rel="ugc" href="https://civarchive.com/articles/1746/anime-lora-dataset-automaker-using-original-screencaps-face-detection-and-similarity-models">Dataset Automaker</a>, which automatically make a dataset of 338 images for me from original anime screencaps.Download dataset of 338 images to train your own LoRA:<a target="_blank" rel="ugc" href="https://drive.google.com/file/d/1KcOJgrlvjGz59vhAUETxTW6DuQx7q72q/view?usp=sharing">https://drive.google.com/file/d/1KcOJgrlvjGz59vhAUETxTW6DuQx7q72q/view?usp=sharing</a>

Zenitsu Agatsuma (Demon Slayer)

Initial release of LoRA trained on 338 images from <a target="_blank" rel="ugc" href="http://fancaps.net">fancaps.net</a> which were automatically download and filtered using my new <a target="_blank" rel="ugc" href="https://civitai.com/articles/1746/anime-lora-dataset-automaker-using-original-screencaps-face-detection-and-similarity-models">Dataset Automaker</a>.

Files with SHA256: 8c31bfbea517f35727d4bb494a9f02d6e6a82ca70da689be894ee646dfd47689