, belt, black hair, cape, emblem, green eyes, jacket, (male focus), paradis.jpeg)
), bangs, ((male focus)), blonde hair, blood, blood splatter, blue eyes, cl_.jpeg)
,_gradient hair, grey hair, hair rings, jacket, grey hair, (((light purple hair.jpeg)
,_red hair, long braided hair, golden eyes, bangs, ringed eyes, _1girl, b.jpeg)
,_(animal ears), pipo, bare shoulders, (grey hair),_1girl, belt, belt buckle, b.jpeg)
,_1girl, belt, belt buckle, blue hair, hair loop, blue eyes, brown footwear, br.jpeg)
Type | |
Stats | 7,018 21,898 |
Reviews | (75) |
Published | Feb 3, 2023 |
Base Model | |
Trigger Words | aot style |
Hash | AutoV2 FAB86EE275 |
Shingeki no Kyojin (Attack on Titan) Anime style LoRA
(season 1)
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 DenjiBased on Discord, who also curated the dataset. This LoRA aims at recreating AoT anime screencaps. Despite being a style LoRA trained on a relatively small dataset from the first episodes, it's also able to reproduce some characters pretty well. In the Examples I also showed how it's possible to mix it with other LoRA's to introduce other fictional characters in this world. Works well at around 0.7 weight on Anything V4.5 and AbyssOrangeMix2 (better for female characters, but tends to make male characters a bit more feminine). Trigger is aot style.
How to use LoRA's in auto1111:
Update webui (use
git pulllike here or redownload it)Copy the file to
stable-diffusion-webui/models/loraSelect your LoRA like in this video
Make sure to change the weight (by default it's
:1which is usually too high)