Type | |
Stats | 17,924 383,502 |
Reviews | (1,433) |
Published | Feb 6, 2024 |
Base Model | |
Usage Tips | Strength: 1 |
Hash | AutoV2 2B83812DFA |
Aesthetic Anime LoRA
The first LoRA I decide to publish. I trained it on AI generated artworks I liked, mostly impressive stuff to enforce a specific aesthetic. All the stuff I used comes from things posted here on Civitai, mostly by @Lykon, but also by @Semii and @mal27210, plus some of the highest rated on the platform. No human made or human edited artwork, hopefully.
I suggest you give a try at around 1 weight, but if you want to go for a more dramatic effect, try weighting a little higher (1.2 or more).
It's trained on top of AAM XL but should work on any XL model, even realistic/general ones (I also tested on DreamShaper XL Turbo). For cfg/sampler/steps follow the suggestions of the base model.
Please have fun and consider leaving a ❤️ and a good review.
Special thanks to Lykon for the tips and some of the showcase images.