👉 Re-trained to hopefully avoid hair and eye color mix-up, with pictures of Yamato and Sora together (which I did not do in V1);
👉 Re-tagged all images and improved clothing tags;
👉 Specifying hair and eye colors not needed when generating them.








Sora Takenouchi and Yamato / Matt Ishida from Digimon Adventure tri. for Illustrious~
Trigger words are sora_takenouchi_tri and yamato_ishida_tri.
Is it necessarily better than V1? It depends, you can be the judge of that... But what's new in this version?
👉 Re-trained to hopefully avoid hair and eye color mix-up, with pictures of Yamato and Sora together (which I did not do in V1);
👉 Re-tagged all images and improved clothing tags;
👉 Specifying hair and eye colors not needed when generating them.
Tags for their uniforms:
Sora: light blue blazer, white collared shirt, red bow, grey sweater vest, pleated skirt, kneehighs (for the summer version, remove "light blue blazer" and add "short sleeves")
Yamato/Matt: light blue blazer, white collared shirt, navy necktie, belt, pants (for the summer version, remove "light blue blazer" and add "sleeves rolled up")
Ahh, a very self-indulgent LoRA... Sora Takenouchi AND Yamato Ishida from Digimon Adventure tri. in 1 LoRA for my shipping needs! :)
I made them separately at first to try my hand at this LoRA making thing, then decided having them in a single LoRA could give me some better results if I wanted them together in pictures. I don't know. This was nearly a shot in the dark (except from some help from this great article), but I think I've sorta made it.
Trigger words for them in their uniforms:
sora_takenouchi_tri, blazer, collared shirt, bow, pleated skirt
yamato_ishida_tri, blazer, collared shirt, necktie, belt, pants
For their summer uniforms, just remove "blazer" and it should give you the right outfits.
Tip: Specifying their hair and eye colors is not needed, but can help. Depending on the checkpoint, "red eyes" will give Sora's eyes a closer match to the anime than "maroon eyes". You decide what works best for you. :)
As always, constructive criticism is welcome and greatly appreciated.
👉 Re-trained to hopefully avoid hair and eye color mix-up, with pictures of Yamato and Sora together (which I did not do in V1);
👉 Re-tagged all images and improved clothing tags;
👉 Specifying hair and eye colors not needed when generating them.
1. 재게시된 모델의 권리는 원 제작자에게 있습니다.
2. 모델 원작자가 모델을 인증받으려면 공식 채널을 통해 SeaArt.AI 직원에게 문의하세요. 저희는 모든 창작자의 권리를 보호하기 위해 노력합니다. 인증하러 이동
