This model is trained on 50 original images, uses wd-tagger for image tagging, all tagged kobayakawa_sae, {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, kobayakawa_sae, portrait, long hair, solo, school uniform, flower, hair ornament, hair flower, serafuku, black eyes, black hair, blush, skirt, <lora:kobayakawa_sae_v2_ssdt_lora32_epoch50:1>