Тип
LORA
Время публикации
2024-03-20
Базовая модель
SD 1.5
Слово-триггер
hikarisena_
Копировать
Версия введения.
v1. Initial release. All epoches perform similar. so the last epoch was picked. retaining last 3 epoch for testing.
trained on 86 images. at 512 reso.
Very good performance on most [asian] checkpoints. rework wont be necessary, I guess.
