A lora that creates images in Chiica's artstyle~
v2 better depicts the artist's style and works better with other models.
Recommended settings:
Model: SilvermoonMix02-Illustrious
Lora strength: 0.8
Samplet: Euler
Upscaler: R-ESRGAN 4x+ Anime6B
Description
FAQ
Comments (3)
Your style loras are amazing! If you don't mind, could you share your learning settings with me? Please don't feel pressured to respond if you'd rather not.
Thank you! I'm glad you like them.
I use the default Civitai training settings. The only thing I usually change is the number of epochs based on the size of the dataset (3 epochs for 30 images, 7 for 70, 10 for over 100 images, etc.)
memolemon123Feb 8, 2026
@misspixel Thank you for sharing that! I'll take it into consideration.