Type | |
Stats | 13,523 80,535 |
Reviews | (2,045) |
Published | Jan 19, 2023 |
Base Model | |
Training | Epochs: 70 |
Trigger Words | ratatatat74 |
Hash | AutoV2 362C9A5D72 |
ratatatat74 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 ☕
Since this author does a lot of hentai stuff, this net is very much nsfw.
Almost every example has been made using the 70 epoch version at 0.7 weight, but sometimes it feels a bit overbaked. I included the 30 epoch version that has also given me good results at 0.8 weight (the girl with the hat and the one with the mirror behind).
For the base model I suggest AbyssOrangeMix2_nsfw or Anything v4.5. Activates with ratatatat74
.
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)