Testing my diffusers text2image lora model and kohya dreambooth lora model.fine tune on stingermix v3.0 checkpoint model, meaning it doesn't have many compatibility because not trained on base model.i will research what other model that can be used for this lora.this is link of my dataset, you can preprocessing it for better result :<a target="_blank" rel="ugc" href="https://huggingface.co/datasets/faizalnf1800/sidebags_hairstyle_and_earring_anime_woman">https://huggingface.co/datasets/faizalnf1800/sidebangs_hairstyle_and_earring_anime_woman</a>please mention me if you make better dataset from my dataset and lets work together collecting and merge dataset for goodness of ai art community.

Sidebangs Hairstyle Plus Earring

use kohya dreambooth lora training on epoch 6 at 4,200 steps, pick lora file near standard training 5000 steps on small dataset. more epoch training visit my huggingface account

Files with SHA256: 23c48cc1db743dbd95ab2c2aac8e867d0dd74cb3598663762539e9226492ba55