Revision 2A. Reduce the strength if you need to merge with multiple LORAs. 2 version, Visual Novel and Anime ver.
It's recommended to run this LORA for IL version with advokat's Illustrious-XL SmoothFT - smoothFT-SOLID | Illustrious Checkpoint | Civitai OR with Ikena's Hassaku XL (Illustrious) - V1.2 - Style | Illustrious Checkpoint | Civitai OR Raelina's Raehoshi illust XL - v3.0 | Illustrious Checkpoint | Civitai. Recommended setting is 20 step, 5 CFG, euler a.
Use strength between 0.7 to 1.
Description
2 version, Visual Novel and Anime ver.
Preview are generated using HassakuXL 1.2. Upscaled using R-ESRGAN-ANIMEx6B
FAQ
Comments (2)
wayyyyyyyy too many watermarks
that depends on checkpoint model you are using it with
i did not train the model with ANY watermarked images
ANY of the NoobAI epsilon-pred is usually not suitable for my LORA.