Intentionally subtracting features from my model, I merged various Asian-based models.
It gives off some oriental features without a separate Lora or EMBEDDING. In addition, it extracts some details without prompting for details. I pulled it out with a minimal prompt, but I did pull it out to a certain extent.
It's my prompt
(masterpiece:1.2), (best quality:1.15), (1girl:1.2), (solo:1.2), (korean mixed, kpop idol:1.3), complete eyes, complete face
Negative prompt: (lowest quality:1.3), (worst quality:1.3), (monochorme hair color:1.2), (black hair:1.1), (deteailed background:1.4), lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, bad_prompt, ugly, (empty eyes:1.25), (fucked eyes:1.25), (black-white:1.25), (monochrome:1.25), (out of perspective:1.25), (flat perspective:1.25), [네거티브 DeepNegative:0.2], uncomplete face, uncomplete eyes
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 12.5, Seed: 1926934296, Size: 512x704, Model hash: 83ddefb1e5, Model: Koreal, Clip skip: 2, ENSD: -1
don't use dynamic threshold that picture
描述:
训练词语:
名称: 3moonREALKo_3moonREALKoV1.safetensors
大小 (KB): 2082643
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
