Amiee character lora from the queen bee manhwa. Trained on Img to Img processed original images from the queen bee manhwa.

UPDATE:

Version 0.2:

Updated dataset to match the original style more closely.

Version 0.3:

The trigger word of v0.3 has more effect on getting the character right. The lora can also double as a style lora for generating other character from the same universe.
The anima preview3 base model seems to generate with the most detail.
Tested using the turbo lora, it seems to reduce quality and detail.
The RDBT lora or checkpoint 0.27 seems to have the same diminishing quality return.

Version 1.0:

Trained on Anima base v1. Improved details. Used 1024 resolution dataset.