Ebora Artstyle Lora trained with 512 images (40-60% of the dataset were high quality images)
Removed chibi, doodles, English commentaries, texts, and background noises that will disrupt Lora's training

There are only two images with English commentary, and I made sure to put tags for them

Autotagged first with wd-vit-large-tagger-v3 / wd-eva02-large-tagger-v3 taggers and personally reviewed all the dataset tags to see if there are any errors or missing tags

There may be some images where I missed tagging some elements, but not every Lora is perfectly tagged
This is a somewhat moderate to highly curated dataset from 1300ish images down to 512 images in the end, personally photoshopped by me with every single one of them
There are some more things I've done, but I forgot the things I did

Recommended Strength : 0.7 - 1
The dataset is updated til July 17

The artist : https://x.com/youngmanisdown