This Lora is trained with illuXL 2.0.
Recommended Settings:
Cfg-Scale: 0.4
Scheduler: Euler A（on civitai)However, using different questions is also fine.
Size: 832 x 1216
Optional but recommended: High-Res fix, upscale, and perhaps face-fix
Description
This version is locally trained, with a style leaning towards 2.2D. The clip is more flexible and works better with other loras.