实验:yps98815

LORA
Original


Updated:

8

V1.3支持7种构图,并尝试支持“预览模式”图片(倾向于上半身),下面给出一组例子:

构图-yps98815-3_预览-off, 1girl, solo, pink_hair, heart_hands, one_eye_closed, pink_eyes, thighhighs, twintails, animal_ears, smile, gloves, long_hair, rabbit_ears, capelet, hair_ornament, white_thighhighs, open_mouth, heart, dress, garter_straps, white_gloves, hairclip, hat, blush, bow, thighs, fur_trim, pink_dress, looking_at_viewer, fur-trimmed_capelet,

在上述例子中,“3”可以被换成1~7之间的其他自然数,“off”可以换成“on",而下划线的效果和空格相等

当“预览”为“on”时,推荐加上“chibi”,一个额外的chibi高概率会出现在角落

是“分辨率提升工具”的平替,在潜空间层面使得模型性能向高分辨率倾斜(同时低分辨率性能降低),最高提升至原来的两倍,上限2176×2176,即:

以1024×1024训练的大模型通过此lora最多放大至2048×2048

以1088×1088训练的大模型通过此lora最多放大至2176×2176

以1152×1152训练的大模型通过此lora最多放大至2176×2176

最优分辨率1344×2176

次优分辨率2176×1344

是二次元模型,运用到三次元可能使得眼睛偏大

是256dim版本,如果在本地继续对维数进行对折,当dim低于64时,对折行为的影响会较为显著

Version Detail

SDXL 1.0

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