Type | |
Stats | 18,731 24,810 |
Reviews | (1,011) |
Published | Jan 18, 2023 |
Base Model | |
Training | Epochs: 45 |
Trigger Words | ahri ahri \(league of legends\) k/da \(league of legends\) spirit blossom \(league of legends\) |
Hash | AutoV2 8FC0EFBDA9 |
Ahri (League of Legends) 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 ☕
Requested by plsdontultme.
As always, this is a LoRA, so you need to use it as additional network on top of your main model. For the example I set the weight to 0.6.
Activation words are ahri
, ahri \(league of legends\)
, k/da \(league of legends\)
, spirit blossom \(league of legends\)
. Yes, it works on alternate costumes too.
If Ahri doesn't show up, try to add animal ears, facial mark, fox ears, fox tail, orange eyes, multiple tails, tail
to the prompt. As for the model I suggest AbyssOrangeMix2 or AnyLoRA.
How to use LoRA's in auto1111:
Copy the file to
stable-diffusion-webui/models/lora
Click on the "show extra networks" button under "Generate" (purple icon)
Go to the
Lora
tabClick on the net you want to apply, it will be added in the prompt
Make sure to change the weight (by default it's
:1
which is usually too high)
45 epochs seem the sweet spot for this dataset. If the 45 version is too strong, lower the weight or grab the 30 epoch version. If you find it to weak even at 1.0, try the 50 epoch version.
The 30 epoch one is also a bit more sfw.