I got sick of all of the Lisa Manoban Loras being sub-par. So I decided to finetune my own, works well with most models. I tested this on DPM++3M SDE Exponential with 70 steps and CFG at 7 and got very good results. I tested a few other loras and they worked well together as long as you balance the weights properly. This is my first lora so any feedback is greatly appreciated, I am also taking requests as I would like to improve my training.
I Updated the captions and training data, it give me better results so let me know if this is an improvement or not.
1. Права на репостнутые модели принадлежат оригинальным создателям.
2. Для подтверждения авторства модели создателям следует обратиться к сотрудникам SeaArt AI через официальные каналы. Нажмите, чтобы подтвердить
