Kojis goal are easy to archive high quality anime images. Model is trained on hassaku.
My Discord for everything related to anime models and art.
If you'd like to support my work, you can do so at: SubscribeStar, every bit helps and is truly appreciated!
____________________________________________________________
Supporters:
Thanks to my supporters tamashiicolle, pttcot, SETI and Kodokuna
_____________________________________________________
Using the model:
Use mostly danbooru tags. No extra vae needed. For better promting on it, use this LINK or LINK. But instead of {}, use (), stable-diffusion-webui use (). Use "masterpiece" and "best quality" in positive, "worst quality" and "low quality" in negative.
My negative ones are: (low quality, worst quality:1.4) with extra monochrome, signature, text or logo when needed.
Use clip skip 2 with sampler DPM++ 2M Karras or DDIM.
Don't use face restore and underscores _, type red eyes and not red_eyes.
_____________________________________________________
Every LoRA that is build to function on anyV3 or orangeMixes, works on koji too. Some can be found here, here or on civit by lottalewds, Trauter, Your_computer, ekune or lykon.
_____________________________________________________
Base model for koji is hassaku.
Black result fix (vae bug in web ui): Use --no-half-vae in your command line arguments
I use a Eta noise seed delta of 31337 or 0, with a clip skip of 2 for the example images. Model quality mostly proved with sampler DDIM and DPM++ SDE Karras. I love DDIM the most (because it is the fastest for model testing).
Description
Stabilized the model with further merged, but mostly with hassaku. To fix many problems from the training attempt.
Because of that, it looks and behave mostly like hassaku now. But is more swf oriented, produce better backgrounds and does't want to lewd everything (mostly). Drawback, it lost its trained "glow" look of V1 and the darker nights.