[SDXL] Gacha Splash Alter版本v1.0 (ID: 326015)

Introducing a better way to use this LoRA with refiner. All sample images are generated in this way:

Settings:

1. Check "Hires fix: show hires checkpoint and sampler selection".

2. Set "Hires fix: which pass to enable refiner for" to first pass".

3. Merge LoRA into your base model.
   You may use SuperMergage https://github.com/hako-mikan/sd-webui-supermerger

Instruction:

1. Set base checkpoint to the merged one in Settings#3.

2. Set Hires, refiner, ADetailer (optional) checkpoint to the one with your desired style (For example, I merged my SDXL style LoRA into as Animagine XL V3 a style checkpoint)

3. Suggested configurations:
   Sampling steps 28

   Refiner switch at 0.425

基于refiner的模型使用手法 https://www.bilibili.com/video/BV1rN4y1B7eg/

前期设置：

• 在设置中开启高清修复模型选择

• 在设置中把refiner改为first pass,这样确保在高清修复的过程中不使用refiner

• 把立绘法LoRA融进你的基础模型中

• 融合插件推荐使用: SuperMergage https://github.com/hako-mikan/sd-webui-supermerger

• （可选）推荐使用ADetailer插件增加面部细节：https://github.com/Bing-su/adetailer

使用设置：

1. 把基础模型设置为融合了立绘法LoRA的模型

2. 把高清修复和Refiner模型设置为你想用的风格化模型

3. 根据我的测试，迭代步数28，refiner切入时机设置为0.425

4. 如果你使用了ADetailer插件，把ADetailer的inpaint模型也改成同样的风格化模型

描述:

训练词语: transparent background