Sign In

Kyoukai no Kanata (Kyoto Animation / Kyoani) Style LoRA

249
1.3k
2.7k
15
Verified:
SafeTensor
Type
LoRA
Stats
1,252
2,737
Reviews
Published
Jun 8, 2023
Base Model
SD 1.5
Trigger Words
kyoukai no kanata
Hash
AutoV2
8A5F303DA8
default creator card background decoration
Lykon's Avatar
Lykon

Kyoukai no Kanata (Kyoto Animation / Kyoani) 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


Should work fine at around weight 1 on AAM and AnyLoRA ckpt. Use kyoukai no kanata to increase fidelity. From my experiments, it works a bit better on AAM.

Remember this is a style LoRA. To make characters accurately you need other networks too (but it can get pretty close with accurate descriptions).


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)