全网首发|基础模型XL|Cancer

LORA
Original · 创作者激励计划


Updated:

群号:909442853    刚建的群 大哥们来撑撑场面

进群下载本地版文件

The real Lora trained from the basic SDXL model using a large amount of materials has greatly improved the generation of facial features for Asian women. The effect will be better when combined with your favorite facial Lora. It is recommended to use a DPM renderer and use natural language to describe the prompts. Sometimes, there may be image collapse, so it is better to roll multiple times.

[Version Update]-悬溺

  1. Delete some incorrect TAGs

  2. Adjust Lora appropriately to make it easier to add more large models

  3. Adding trigger words

[Applicable prompt words]

  1. Clip skip:2

  2. Sampling method:DPM++ 2M SDE Karras

  3. Sampling steps:40

  4. CFG:7

  5. Weight 0.5-1, do not exceed 1

Version Detail

基础模型 XL

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in 吐司 Online

  • As a online training base model on 吐司

  • 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

Related Posts