Komi Shouko (Komi-san wa Komyushou Desu) 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 ☕
Another LoRA that came from a user request. This wasn't easy, as the model didn't really want to overfit on her hair shape, which will maybe require a style LoRA or TI. The final result is pretty close and sometimes can even get the caricature version right.
Triggers with komi shouko but sometimes I even used ((komi shouko)) to get the hair shape, and also requires other descriptive tags, as it's usually the case with LoRA (check the example prompts I posted). Weight should be between 0.5 and 0.7. I've mostly used Anything V4.5 but it seems it works even better on Counterfeitv2.
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 (12)
Can you do Shadman please? Your lora-s are so good but there are is still shad lora out there(
what's shadman? :o
@lykon he is the artist, you can find his works on shadbase
I want a safetensor model for this so bad! Easy Diffusion UI can't use Loras
Why not use webui?
@lykon Long story is too much to type. Short story: It doesn't work on my computer anymore
unfortunately lora's are so much easier to train and are more versatile. Can be used on any model without taking up 5 gb of space
@lykon Yeah, that's what I heard, oh well. Some models can make her but only so-so quality
hello, very good, your loRA wanted to know how you do it, do you have a link where you learned from, thank you very much
I've been doind supervised learding for over 10 years. Sorry, didn't follow any tutorial
Very good LoRA
pure love on this model
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.