歌德混血 goth hafu

LORA
Original


Updated:

245

1.0 建議權重約0.3~0.5,Cut-Out Dress 在許多大模型都是有一定程度的效果,只是這Lora會多增加一些細節跟變化。Lora權重愈高,愈傾向於黑色衣服,場景也會轉向室內,可以靠Clip Skip 2 改善,或提高戶外場景的描述權重。Lora的權重超過0.8不適合寫實模型,頭型跟身體比例會開始不自然。

Checkpoint模型還是首推Asian Realism Fusion。ADetailer建議重繪幅度0.4~0.5,可以呈現較佳視覺效果,並盡量調整與LoRA外觀相似的年齡。

Adetailer Prompt: (((ulzzang belle))), (((pitiful eyes))), ((pretty lips)), ((gentle smile)), (shy face), Adetailer Negative: (((lowres, 2.5D render, CG texture, unreal engine))), (((low quality, worst quality))), (((makeup, eyebrows, eyelashes, lipstick:1.4))),

Version Detail

SD 1.5

Project Permissions

    Use Permissions

  • Use in TENSOR GREEN Online

  • As a online training base model on TENSOR GREEN

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.