LoCon
Use these keywords to activate "Kyoto Animation screencap" "Anime screencap" recommended weight: 0.5~0.7
Suitable Model: anything, anylora, dpepmkm, detailed project v4
HiRes Fix: Latent - AnimeSharp - ESRGAN
LoHA
Use this word to activate "kyoto style"
Recommended weights : 0.4~0.7(1 works too)
Hires Fix Upscaler: R-ESRGAN 0.7 Denoise or 0.4, i prefer 0.7 usually. You can use anime sharp or any upscaler of your own choice
Suitable Model: AnyLora
The finalized version is better than the experimental and the locon.
Description
Trained as a LoHA, different base model. Same dataset, 768x768 and due of colab limits it wasn't fully trained.
Details
Downloads
951
Platform
CivitAI
Platform Status
Available
Created
6/6/2023
Updated
9/27/2025
Deleted
-
Trigger Words:
Kyoto Style
Files
kyoani_loha-e2.safetensors
Mirrors
CivitAI (1 mirrors)