Type | |
Stats | 48,507 195,774 |
Reviews | (371) |
Published | Jan 28, 2023 |
Base Model | |
Training | Epochs: 35 |
Trigger Words | lucy \(cyberpunk\) |
Hash | AutoV2 2BB7EFC809 |
Lucy (Cyberpunk Edgerunners) 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 hard LoRA for another great character design. Both version (35 and 42) are flexible enough. I'd say that 35 is a bit better with her normal outfit, but 42 is a bit more precise with her naked (but it still needs some help with triggers like (robot joints:0.5)
and mechanical parts
). None of them seem to get her back pattern perfectly, as the dataset was not very consistent, but the 42 epoch version is a little bit more precise on that. Trigger is lucy \(cyberpunk\)
, weight should be around 1 for the offset version (0.65 for the old ones) on AnyLoRA ckpt.
The as a LoRA this is flexible enough to allow you to change her hairstyle, clothes, have just pieces of her outfit or all of it. But if you type jacket
you get her jacket, if you type shorts
you get her shorts, etc.
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)