Hyouka (Kyoto Animation / Kyoani) style LoRA
Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
Should work fine at around weight 1 on AnyLoRA ckpt. Use hyouka to increase fidelity, and it also seems AnyLoRA is able to understand Chitanda's name.
Remember this is a style LoRA. To make characters accurately you need other networks too (but it can get pretty close with accurate descriptions).
How to use LoRA's in auto1111:
Update webui (use
git pulllike here or redownload it)Copy the file to
stable-diffusion-webui/models/loraSelect your LoRA like in this video
Make sure to change the weight (by default it's
:1which is usually too high)
Description
FAQ
Comments (11)
Nice :D
by the way i want to tell you that there is miss kobayashi style
if you want to make your own one it is up to you
nah I don't see much value in redoing something that already exists.
@Lykon I see, oh and also violet evergarden, forgot to mention it
@bombo64 yeah I know there are plenty of that. There was even a hypernetwork. I might still make it however. Just because I like it.
@Lykon make anything that you like bro (:
What a thrill, I was waiting for this one, thank you very much.
So good! Soo cute (✿◕‿◕✿)
Can you make Oshi no Ko style please?
wait, hasn't been made already?
@Lykon i cant find any
@lenagolovach I'll think about it
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.