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
What is better:
Overall better structured backgrounds, less random
Less double limbs
Slightly better prompt following
What is worse:
Color is a bit less colorful
Style is mostly the same to hassaku, but not with a nsfw focus, but a focus on stability and image quality
FAQ
Comments (12)
Currently my most used model. And what i just found out is that if you use Genshin Impact in the prompt, it will actually try to create characters like that, with Genshin hair etc.
Nice model, <3
Since yesterday, I can't use KOJI in Onsite. Is there any way to fix this?
civit limits the generator to 2 models per creator, this model fall out of it
@Ikena Understood.
Thank you for your reply.
This base model is useful for sd1 models, please, dont let it down 🙏
I know, i missed it so. I shelled out 4000 buzz to see if it would come back, but it'll be gone in a couple days. Use it while you can.
@paulvorbeck damn! its gone :( model sd1 is lacking for anime model
@W20h Aw well, i'll probably have to shell out more buzz for a later period. Going to have to see if can get a bunch of people to shell out a few hundred buzz each to make it more economical.
@paulvorbeck yep, so it means some models are temporals, its unffair because other models still exist, i wont complain but one character model requires sd1 checkpoint and the free ones for that are awful to use, this and others were good but sadly only temporal too. well just try only if you can, ill see another alternative
@W20h Don't i know it, so many models i cant use any more. I'll probably shill out in a couple weeks for it to return, i was really just testing it this time. I'll message you back when i do.
Really nice neat anime model!