Melina (Elden Ring) 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 ☕
One of my favorite characters for one of my favorite games. This one was complicated because of the tattoo and the inconsistencies in the dataset. I left some tricks in the example images. Mostly requires 0.8 weight to get the eye right if you're generating full body or upper body images, for portraits and close ups 0.65 weight should be fine. Trigger is melina \(elden ring\) and should work on most booru based models and beyond. For the examples I used AnyPastel, AnyLoRA and AbyssOrangeMix2. You should get good results as long as you know what you're doing.
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 (5)
YOOOO, my guy, you got any advice for how to train LORAs for people, objects and styles? Im using kohya_ss-master over native dreambooth A1111 extension because it is more stable.
Put yourself in the shoes of an ai that can only do what the base model can do and ask yourself "what should I feed it to learn what I want it to learn?"
@Lykon Right XD, tbf that actually helps a lot, thx :) u got any advice though for getting faces right? I can match styles and compositions but can never get a face to show :(
@odawgthat what do you mean?
@Lykon U got DC? Add me at Odawgthat#4437, I get really weird results, super complicated to explain but you'll see what I mean :/
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.