(1344P)律令:八面-参数1.00

LORA
Original


Updated:

使用danbooru_tag,但由于律令语法,应使用句号替换传统的逗号,以调用本模型性能

默认分辨率:1344×2176(主),2176×1344(辅)

推荐步数:28

额外概念(画风)格式:{

dim1_dim1-232f8e78.

dim1_dim1-fa37f8fe.

dim1_dim1-88d1f606.

dim1_dim1-5d8cb33c.

dim1_dim1-8a5a8212.

dim1_dim1-2c644842.

dim1_dim1-22caf18f.

dim1_dim1-8a6b7409.

}以上八选一,从上往下拟合程度越来越低,

额外概念(横向图或纵向图)格式:{

dim3_dim3-portrait.

dim3_dim3-paysage.

}以上二选一,若是paysage(法语),意味着该概念来自2176×1344的图片,而不是1344×2176,

额外概念(放大镜倍数)格式:{

dim2_dim2-0.(不放大)

dim2_dim2-1_dim2-1-a0.(提高良手率的一种方案,但要承担头部、肢体可能在图片之外的风险)

dim2_dim2-1_dim2-1-b0.

}以上三选一,若是b,意味着该概念来自2176×1344的图片,而不是1344×2176

Version Detail

FLUX.1

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • 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

No posts yet