Type | |
Stats | 5,305 736 |
Reviews | |
Published | Apr 20, 2023 |
Base Model | |
Training | Epochs: 100 |
Trigger Words | nixeu |
Hash | AutoV2 07C7639B64 |
Nixeu 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 ☕
I made this a while ago to fulfill a request on the Project AI discord. It doesn't imitate Nixeu's stile perfectly, so I think it's transformative enough. Still it's an interesting LoRA.
Activation is simply nixeu
. I suggest weight 1 for the offset version (0.6 for the old one).
If you add tags like artist name
you can also have it add the signature (with funny spelling usually). If you don't want that, just put it in the negative prompt. LoRA's are kind of made to overfit, so it's kind of expected as this author puts the signature everywhere.
How to use LoRA's in auto1111:
Update webui (use
git pull
like here or redownload it)Copy the file to
stable-diffusion-webui/models/lora
Select your LoRA like in this video
Make sure to change the weight (by default it's
:1
which is usually too high)