Character LORA model for yamada elf in Eromanga Sensei, trained on ACertainModel.
Since the previous model is removed for violation of TOS (Lolita), I decided to reupload it.
The dataset and training info is provided and you can download them, if you want to train yourself :)
The features of the models are described below.
Note: Since the name of the character contains keyword "elf" and it often generates sharp ears, I decided to use the alternative trigger word "eromanga_yamada".
Description
This model is trained on 20 original images, uses wd-tagger for image tagging, all tagged eromanga_yamada, {TXT_PROMPT}, contained in uploaded training data.
This LORA model works well on various models, and still keeps some generality. For better performance, try something like:
masterpiece, best_quality, 1girl, long hair, solo, blonde hair, thighhighs, pointy ears, open mouth, drill hair, hairband, bow, dress, white thighhighs, brown eyes, looking at viewer, red bow, pink dress, white background, pointing, hair bow, simple background, blush, twin drills, pointing at viewer, red hairband, smile, eromanga_yamada, <lora:eromanga_yamada_v2_ssdt_lora32_epoch50:1>